U.S. patent application number 15/165644 was filed with the patent office on 2016-12-01 for method of forming a probability map.
The applicant listed for this patent is Moira F. SCHIEKE. Invention is credited to Moira F. SCHIEKE.
Application Number | 20160350933 15/165644 |
Document ID | / |
Family ID | 57398966 |
Filed Date | 2016-12-01 |
United States Patent
Application |
20160350933 |
Kind Code |
A1 |
SCHIEKE; Moira F. |
December 1, 2016 |
METHOD OF FORMING A PROBABILITY MAP
Abstract
A method of using a moving window to form a probability map is
disclosed. According to one embodiment, a method may include
obtaining measures of imaging parameters for stops of a moving
window on an image. Probabilities of an event associated with the
stops of the moving window are obtained, for example by matching
the measures of the imaging parameters to a classifier.
Inventors: |
SCHIEKE; Moira F.;
(Milwaukee, WI) |
|
Applicant: |
Name |
City |
State |
Country |
Type |
SCHIEKE; Moira F. |
Milwaukee |
WI |
US |
|
|
Family ID: |
57398966 |
Appl. No.: |
15/165644 |
Filed: |
May 26, 2016 |
Related U.S. Patent Documents
|
|
|
|
|
|
Application
Number |
Filing Date |
Patent Number |
|
|
62167940 |
May 29, 2015 |
|
|
|
Current U.S.
Class: |
1/1 |
Current CPC
Class: |
A61B 6/037 20130101;
G16H 30/40 20180101; A61B 5/0091 20130101; G06T 7/0012 20130101;
G06K 2209/053 20130101; A61B 5/055 20130101; A61B 2576/02 20130101;
G06T 2207/30096 20130101; G16H 50/30 20180101; G06T 2207/30068
20130101; A61B 5/7275 20130101; G06K 9/6278 20130101; G06T
2207/10088 20130101; G06T 2207/10108 20130101; A61B 6/032 20130101;
A61B 5/0075 20130101; G06T 2207/10081 20130101; G06K 9/6281
20130101; G06T 2207/20076 20130101; G06T 11/008 20130101; G06T
2207/30081 20130101; G06T 2207/10104 20130101 |
International
Class: |
G06T 7/00 20060101
G06T007/00; A61B 5/055 20060101 A61B005/055; A61B 5/00 20060101
A61B005/00; G06K 9/62 20060101 G06K009/62 |
Claims
1. A method for generating a probability map, comprising:
generating a moving window for application to a computation region
of a medical image; applying the moving window to the computation
of the medical image; obtaining measures of imaging parameters for
stops of the moving window, wherein at least two neighboring stops
of the moving window partially overlap; and obtaining first
probabilities of an event for each of the stops of the moving
window.
2. The method of claim 1, wherein obtaining the first probabilities
of the event comprises matching the measures of the imaging
parameters to a classifier for the event.
3. The method of claim 2, wherein the classifier comprises a
Bayesian classifier.
4. The method of claim 2, wherein the classifier is created based
on information associated with multiple measures of the imaging
parameters for biopsy tissues and diagnoses for the biopsy
tissues.
5. The method of claim 1, wherein the imaging parameters comprise
at least four types of magnetic resonance imaging (MRI) or other
imaging parameters.
6. The method of claim 1, further comprising creating a probability
map based on the first probabilities, wherein the probability map
comprises a plurality of voxels that provide an indication of a
likelihood of the event occurring with a portion of the medical
image associated with a respective voxel, and wherein the two
neighboring stops of the moving window are shifted from each other
by a distance substantially equal to a side length of one of the
voxels.
7. The method of claim 6, wherein the moving window overlaps areas
associated with multiple voxels of the probability map at each
stop.
8. The method of claim 1, wherein said event is occurrence of a
cancer.
9. The method of claim 1, further comprising obtaining second
probabilities of the event for multiple voxels of a probability map
based on information associated with the first probabilities.
10. The method of claim 9, wherein obtaining the second
probabilities of the event comprises calculating multiple assumed
probabilities for respective voxels of the probability map based on
the first probabilities of the event covering the respective
voxels.
11. The method of claim 1, wherein the medical image comprises a
magnetic resonance imaging (MRI) image.
12. The method of claim 1, wherein the moving window has a size
defined based on a volume of a biopsy tissue.
13. The method of claim 12, wherein the moving window has a volume
defined based on a volume of a biopsy tissue.
14. The method of claim 1, wherein the moving window has a circular
shape.
15. The method of claim 1, further comprising calculating a third
probability of the event for a voxel of a probability map based on
the first probability and a second probability of the first
event.
16. The method of claim 1, further comprising: obtaining a third
probability of a second event for a first stop of the moving window
by matching the first measure to a first classifier; obtaining a
fourth probability of the second event for a second stop of the
moving window by matching second measures of the imaging parameter
to the first classifier; calculating a fifth probability of the
first event based on the first and second probabilities of the
first event; calculating a sixth probability of the second event
based on the third and fourth probabilities of the second event;
and creating a composite probability map based on information
associated with the fifth probability of the first event and the
sixth probability of the second event.
17. The method of claim 16, wherein the first event is that a
cancer occurs, and the second event is associated with a Gleason
score.
18. The method of claim 1, further comprising reducing the measures
of the imaging parameters into a parameter set for each step of the
moving window.
19. The method of claim 18, wherein the obtaining the first
probabilities of the event comprises matching the parameter set to
a classifier for the event at each stop of the moving window.
20. The method of claim 18, wherein the obtaining the first
probabilities of the event comprises matching the parameter set to
a biomarker library having a plurality of stored parameters
associated with various events.
Description
CROSS-REFERENCE TO RELATED APPLICATIONS
[0001] This application claims priority to U.S. Provisional Patent
Application No. 62/167,940, filed May 29, 2015, the entirety of
which is incorporated herein by reference.
BACKGROUND OF THE DISCLOSURE
[0002] Field of the Disclosure
[0003] The disclosure relates to a method of forming a probability
map, and more particularly, to a method of forming a probability
map based on molecular and structural imaging data, such as
magnetic resonance imaging (MRI) parameters, computed tomography
(CT) parameters, positron emission tomography (PET) parameters,
single-photon emission computed tomography (SPECT) parameters,
micro-PET parameters, micro-SPECT parameters, Raman parameters,
and/or bioluminescence optical (BLO) parameters, or based on other
structural imaging data, such as from CT and/or ultrasound
images.
[0004] Brief Description of the Related Art
[0005] Big Data represents the information assets characterized by
such a high volume, velocity and variety to require specific
technology and analytical methods for its transformation into
value. Big Data is used to describe a wide range of concepts: from
the technological ability to store, aggregate, and process data, to
the cultural shift that is pervasively invading business and
society, both drowning in information overload. Precision medicine
is a medical model that proposes the customization of
healthcare--with medical decisions, practices, and/or products
being tailored to the individual patient. In this model, diagnostic
testing is often employed for selecting appropriate and optimal
therapies based on the context of a patient's genetic content or
other molecular or cellular analysis.
SUMMARY OF THE DISCLOSURE
[0006] The invention proposes an objective to provide a method of
using a moving window to form a probability map based on molecular
and structural imaging data, such as MRI parameters, CT parameters,
PET parameters, SPECT parameters, micro-PET parameters, micro-SPECT
parameters, Raman parameters, and/or BLO parameters, and/or other
structural imaging data, such as from CT and/or ultrasound images.
The method may build a dataset or database of big data based on
molecular and structural imaging data (and/or other structural
imaging data) and the corresponding biopsy tissue-based data. A
classifier or biomarker library may be constructed or established
from the big data dataset. In an embodiment, a biomarker is a
characteristic that is objectively measured and evaluated as an
indicator of normal biological processes, pathogenic processes, or
pharmacologic responses to a therapeutic intervention. The
invention introduces the use of a moving window as a basic process
for creating a probability map of a specific tissue or tumor
characteristic for an individual patient from the patient's
registered imaging dataset by using a matching dataset from the
established or constructed classifier or biomarker library
containing population-based information for the given set of
molecular imaging (and/or other imaging) data and other information
(such as clinical and demographic data). The method provides direct
biopsy tissue-based evidence for the medical or biological test or
diagnosis of tissues or organs of an individual patient and show
biomarker(s) within a single tumor focus with high sensitivity and
specificity.
[0007] The invention also proposes an objective to provide a method
of forming a probability change map based on imaging data before
and after a medical treatment. The imaging data may include (1)
molecular and structural imaging data, such as MRI parameters, CT
parameters, PET parameters, SPECT parameters, micro-PET parameters,
micro-SPECT parameters, Raman parameters, and/or BLO parameters,
and/or (2) other structural imaging data, such as from CT and/or
ultrasound images. The method may build a big data dataset based on
molecular and structural imaging (and/or other structural imaging)
data and the corresponding biopsy tissue-based data. A classifier
or biomarker library may be constructed or established from the big
data dataset. The invention introduces the use of a moving window
for creating a probability change map of a specific tissue or tumor
characteristic for a patient by matching the patient's molecular
imaging (and/or other imaging) information before and after the
treatment in the patient's registered (multi-parametric) image
dataset to the established or constructed classifier or biomarkers.
The method may use the molecular imaging (or other imaging) data
matching a classifier or biomarkers derived from direct biopsy
tissue-based evidence to obtain the change of probabilities for
treatment responses or progression and show biomarker(s) of
response and/or progression within a single tumor focus with high
sensitivity and specificity. The invention provides a method for
effective and timely evaluation of the effectiveness of the
treatment, such as neoadjuvant chemotherapy for breast cancer, or
radiation treatment for prostate cancer.
[0008] The invention also proposes an objective to provide a method
for collecting data for an image-tissue-clinical database for
cancer.
[0009] The invention also proposes an objective to apply a big data
technology to build a probability map from multi-parameter
molecular imaging data, including MRI parameters, PET parameters,
SPECT parameters, micro-PET parameters, micro-SPECT parameters,
Raman parameters, and/or BLO parameters, and/or from other imaging
data, including data from CT and/or ultrasound images. The
invention provides a non-invasive method (such as molecular imaging
methods, for example, MRI, Raman imaging, CT imaging) to diagnose a
specific tissue characteristic, such as breast cancer cells or
prostate cancer cells, with better resolution (resolution size is
50% smaller, or 25% smaller than the current resolution
capability), and with a higher confidence level. With data
accumulated in the dataset or database of big data, the confidence
level (for example, percentage of accurate diagnosis of a specific
cancer cell) can be greater than 90%, or 95%, and eventually,
greater than 99%.
[0010] The invention also proposes an objective to apply a big data
technology to build a probability change map from imaging data
before and after a treatment. The imaging data may include (1)
molecular and structural imaging data, including MRI parameters, CT
parameters, PET parameters, SPECT parameters, micro-PET parameters,
micro-SPECT parameters, Raman parameters, and/or BLO parameters,
and/or (2) other structural imaging data, including data from CT
and/or ultrasound images. The invention provides a method for
effective and timely evaluation of the effectiveness of a
treatment, such as neoadjuvant chemotherapy for breast cancer or
radiation treatment for prostate cancer.
[0011] In order to achieve the above objectives, the invention may
provide a method of forming a probability map composed of multiple
computation voxels with the same size. The method may include the
following steps described below. First, a big data database
including multiple data sets is created. Each of the data sets in
the big data database may include a first set of information data,
which may be obtained by a non-invasive method or a less-invasive
method (as compared to a method used to obtain the following second
set of information data), may be obtained more easily (than the
method used to obtain the following second set of information
data), or may provide information, obtained by a non-invasive
method, for a specific tissue, to be biopsied or to be obtained by
an invasive method, of an organ (e.g., prostate or breast) of a
subject with a spatial volume covering, e.g., less than 10% or even
less than 1% of the spatial volume of the organ of the subject. The
organ of the subject, for example, may be the prostate or breast of
a human patient. The first set of data information may include
measures of molecular imaging (and/or other imaging, Note: the
method in the invention can be used for other imaging data, and
therefore "the other imaging data" may not be mentioned hereafter.)
parameters, such as measures of MRI parameters and/or CT
parameters, for a volume and location of the specific tissue to be
biopsied (e.g., prostate or breast) from the organ of the subject.
Each of the molecular imaging parameters for the specific tissue
may have a measure calculated based on an average of measures, for
said each of the molecular imaging parameters, obtained from
regions, portions, locations or volumes of interest of multiple
registered images, such as MRI slices, PET slices, or SPECT images,
registered to or aligned with respective regions, portions,
locations or volumes of interest of the specific tissue to be
biopsied. All of the regions, portions, locations or volumes of
interest of the registered images may have a total volume covering
and substantially equaling the volume of the specific tissue to be
biopsied. Each of the data sets in the big data database may
further include a second set of information data, which may be
obtained by an invasive method or a more-invasive method (as
compared to the method used to obtain the above first set of
information data), may be obtained with more difficulty (as
compared to the method used to obtain the above first set of
information data), or may provide information for the specific
tissue, having been biopsied or obtained by an invasive method, of
the organ of the subject. The second set of information data may
provide information data with decisive, conclusive results for a
better judgment or decision making. For example, the second set of
information data may include a biopsy result, data or information
(i.e., pathologist diagnosis, for example cancer or no cancer) for
the biopsied specific tissue. Each of the data sets in the big data
database may also include: (1) dimensions related to molecular
imaging parameter measures, such as the thickness T of an MRI slice
and the size of an MRI voxel of the MRI slice, including the width
of the MRI voxel and the thickness or height of the MRI voxel
(which may be the same as the thickness T of the MRI slice), (2)
clinical data (e.g., age and sex of the patient and/or Gleason
score of a prostate cancer) associated with the biopsied specific
tissue and/or the subject, and (3) risk factors for cancer
associated with the subject (such as smoking history, sun exposure,
and premalignant lesions, gene). For example, if the biopsied
specific tissue is obtained by a needle, the biopsied specific
tissue is cylinder-shaped with a diameter or radius Rn (that is, an
inner diameter or radius of the needle) and a height tT normalized
to the thickness T of the MRI slice. The invention proposes a
method to transform the volume of the cylinder-shaped biopsied
specific tissue (or Volume of Interest (VOI)) into other shapes for
easy or meaningful computing purposes, for medical instrumentation
purposes, or for clearer final data presentation purposes. For
example, the long cylinder of the biopsy specific tissue (with
radius Rn and height tT) may be transformed into a planar cylinder
(with radius Rw, which is the radius Rn multiplied by the square
root of the number of registered images for the specific tissue to
be biopsied) to match the MRI slice thickness T. The information of
the radius Rw of the planner cylinder, which has a volume the same
or about the same as the volume of the biopsied specific tissue,
i.e., VOI, and has a height of the MRI slice thickness T, is used
to define the size (e.g., the radius) of a moving window in
calculating a probability map for a patient (e.g., human). The
invention proposes that, for each of the data sets, the volume of
the biopsy specific tissue, i.e., VOI, may be substantially equal
to the volume of the moving window to be used in calculating
probability maps. In other words, the volume of the biopsy specific
tissue, i.e., VOI, defines the size of the moving window to be used
in calculating probability maps. In above, the concept of obtaining
a feature size (e.g., the radius) of the moving window to be used
in calculating a probability map for an MRI slice is disclosed.
Statistically, the moving window may be determined with the radius
Rw (i.e., feature size), perpendicular to a thickness of the moving
window, based on a statistical distribution or average of the radii
Rw (calculated from VOIs) associated with a subset data from the
big data database. Next, a classifier for an event such as
biopsy-diagnosed tissue characteristic for e.g., specific cancerous
cells or occurrence of prostate cancer or breast cancer is created
based on the subset data associated with the event from the big
data database. The subset data may be obtained from all data
associated with the given event. A classifier or biomarker library
can be constructed or obtained using statistical methods,
correlation methods, big data methods, and/or learning and training
methods.
[0012] After the big data database and the classifier are created
or constructed, an image of a patient, such as MRI slice image
(i.e., a molecular image) or other suitable image, is obtained by a
device or system such as MRI system. Furthermore, based on the
feature size, e.g., the radius Rw, of the moving window obtained
from the subset data in the big data database, the size of a
computation voxel, which becomes the basic unit of the probability
map, is defined. In other words, a step size of the moving window
may determine a size of the voxels of a probability map. If the
moving window is circular, the biggest square inscribed in the
moving window is then defined. Next, the biggest square is divided
into n.sup.2 small squares each having a width Wsq, where n is an
integer, such as 2, 3, 4, 5, 6, or more than 6. The divided squares
define the size and shape of the computation voxels in the
probability map for the image of the patient. The moving window may
move across the patient's image at a regular step or interval of a
fixed distance, e.g., substantially equal to the width Wsq of the
computation voxels. A stop of the moving window overlaps with the
neighboring stop of the moving window. Alternatively, the biggest
square may be divided into n rectangles each having a width Wrec
and a length Lrec, where n is an integer, such as 2, 3, 4, 5, 6, 7,
8, or more than 8. The divided rectangles and step size of the
moving window defines the size and shape of the computation voxels
in the probability map for the image of the patient. The moving
window may move across the patient's image at a regular step or
interval of a fixed distance, e.g., substantially equal to the
width of the computation voxels (i.e., the width Wrec), in the x
direction and at a regular step or interval of a fixed distance,
e.g., substantially equal to the length of computation voxels
(i.e., the length Lrec), in the y direction. A stop of the moving
window overlaps with the neighboring stop of the moving window. In
an alternative embodiment, each of the stops of the moving window
may have a width, length or diameter less than the side length
(e.g., the width or length) of voxels in the image of the
patient.
[0013] After the size and shape of the computation voxel is
obtained or defined, the stepping of the moving window and the
overlapping between two neighboring stops of the moving window can
then be determined. Measures of specific imaging parameters for
each stop of the moving window are obtained from the patient's
imaging information or image. The specific imaging parameters may
include molecular imaging parameters, such as MRI parameters, PET
parameters, SPECT parameters, micro-PET parameters, micro-SPECT
parameters, Raman parameters, and/or BLO parameters, and/or other
imaging parameters, such as CT parameters and/or ultrasound imaging
parameters. Each of the specific imaging parameters for each stop
of the moving window may have a measure calculated based on an
average of measures, for said each of the specific imaging
parameters, for voxels of the patient's image inside said each stop
of the moving window. In the case that some voxels of the patient's
image may be only partially inside that stop of the moving window,
the average can be weighed by the area proportion. A registered
(multi-parametric) image dataset may be created for the patient to
include multiple imaging parameters, such as molecular parameters
and/or other imaging parameters, obtained from various modalities
(e.g., equipment, machines, etc.), or devices or from a defined
time-point (e.g., specific date) or time range (e.g., within five
days after treatment). Each of the image parameters in the
patient's registered (multi-parametric) image dataset requires
alignment or registration. The registration can be done by, for
examples, using unique anatomical marks, structures, tissues,
geometry, shapes or using mathematical algorithms and computer
pattern recognition.
[0014] Next, the specific imaging parameters for each stop of the
moving window may be reduced using, e.g., subset selection,
aggregation, and dimensionality reduction into a parameter set for
said each stop of the moving window. In other words, the parameter
set includes measures for independent imaging parameters. The
imaging parameters used in the parameter set may have multiple
types, such as two types, more than two types, more than three
types, or more than four types, independent from each other or one
another, or may have a single type. For example, the imaging
parameters used in the parameter set may include (a) MRI parameters
and PET parameters, (b) MRI parameters and SPET parameters, (c) MRI
parameters and CT parameters, (d) MRI parameters and ultrasound
imaging parameters, (e) Raman imaging parameters and CT parameters,
(f) Raman imaging parameters and ultrasound imaging parameters, (g)
MRI parameters, PET parameters, and ultrasound imaging parameters,
or (h) MRI parameters, PET parameters, and CT parameters.
[0015] Next, the parameter set for each stop of the moving window
is matched to the classifier to obtain a probability PW of the
event for each stop of the moving window. A probability of the
event for each of the computation voxels may be computed from the
probabilities PWs of the event for related stops of the moving
window. According to the described approach, multiple moving window
readings are used to determine final probability values for the
computation voxels of a probability map for an event. More
specifically, probabilities of the event for the computation voxels
are obtained based on overlapped stops of the moving window and
used to form the probability map of the event for the image (e.g.,
patient's MRI slice) for the patient having imaging information
(e.g., molecular imaging information). Using a moving window in the
x-y direction would create a two-dimensional (2D) probability map.
In order to obtain a three-dimensional (3D) probability map, the
above processes for all MRI slices of the patient would be
performed in the z direction in addition to the x-y direction.
[0016] After the probability map is obtained, the patient may
undergo a biopsy to obtain a tissue sample for a suspected region
of the probability map from an organ of the patient (i.e., that is
shown on the image of the patient). The tissue sample is then sent
to be examined by pathology. Based on the pathology diagnosis of
the tissue sample, it can be determined whether the probabilities
for the suspected region of the probability map are precise or not.
In the invention, the probability map may provide information for a
portion or all of the organ of the patient with a spatial volume
greater than 80% or even 90% of the spatial volume of the organ,
than the spatial volume of the tissue sample (which may be less
than 10% or even 1% of the spatial volume of the organ), and/or
than the spatial volume of the specific tissue provided for the
first and second sets of information data in the big data
database.
[0017] In order to further achieve the above objectives, the
invention may provide a method of forming a probability change map
between before and after a treatment. The method is described in
the following steps: (1) following methods and procedures described
above, the probability of the event for each stop of the moving
window in the MRI slice for a patient before the treatment can be
obtained, using molecular imaging parameters (or other images)
taken before the treatment. Similarly, the probability of the event
for each stop of the moving window in the MRI slice for the patient
after the treatment can be obtained, using molecular imaging
parameters (or other images) taken after the treatment. All
molecular imaging parameters (or other images) are from the
registered (multi-parametric) image dataset. (2) calculating a
probability change PMC between the probabilities of the event
before and after the treatment for each stop of the moving window;
(3) calculating a probability change PVC of each of computation
voxels in the MRI slice, associated with the treatment, using the
probability changes PMCs for the stops of the moving window, by
calculating the probability of each of computation voxels from the
probabilities of the stops of the moving window. The obtained
probability changes PVCs for the computation voxels then form a
probability change map for the MRI slice, associated with the
treatment. Performing the above processes for all MRI slices in the
z direction, a 3D probability change map can be obtained.
[0018] In general, the invention proposes an objective to provide a
method, system (including, e.g., hardware, devices, computers,
processors, software, and/or tools), device, tool, software or
hardware for forming or generating a clinical decision support data
map, e.g., a probability map, based on first data of a first type
(e.g., first measures of MRI parameters) from a first subject such
as a human or an animal. The method, system, device, tool, software
or hardware may include building a database of big data including
second data of the first type (e.g., second measures of the MRI
parameters) from a population of second subjects and third data of
a second type (e.g., biopsy results, data or information) from the
population of second subjects. The third data of the second type
may provide information data with decisive, conclusive results for
a better judgment or decision making (e.g., having cancer or not).
The second and third data of the first and second types from each
of the second subjects in the population, for example, may be
obtained from a common portion of said each of the second subjects
in the population. A classifier related to a decision-making
characteristic (e.g., occurrence of prostate cancer or breast
cancer) is established or constructed from the database of big
data. The method, system, device, tool, software or hardware may
provide an algorithm and a computing method for generating the
decision data map with finer voxels associated with the
decision-making characteristic for the first subject by matching
the first data of the first type to the established or constructed
classifier. The method, system, device, tool, software or hardware
provides a decisive-conclusive-result-based evidence for a better
judgment or decision making based on the first data of the first
type (without any data of the second type from the first subject).
The second data of the first type, for example, may be obtained by
a non-invasive method or a less-invasive method (as compared to a
method used to obtain the third data of the second type), may be
obtained more easily (as compared to the method used to obtain the
third data of the second type), or may provide information,
obtained by, e.g., a non-invasive method, for a specific tissue, to
be biopsied or to be obtained by an invasive method, of an organ of
each second subject with a spatial volume covering, e.g., less than
10% or even less than 1% of the spatial volume of the organ. The
second data of the first type may include measures or data of
molecular imaging (and/or other imaging) parameters, such as
measures of MRI parameters and/or CT data. The third data of the
second type, for example, may be obtained by an invasive method or
a more-invasive method (as compared to the method used to obtain
the second data of the first type), may be harder to obtain (as
compared to the method used to obtain the second data of the first
type), or may provide information for the specific tissue, having
been biopsied or obtained by an invasive method, of the organ of
each second subject. The third data of the second type may include
biopsy results, data, and information (for example having cancer or
no cancer) for the biopsied specific tissues of the second subjects
in the population. The decision making may be related to, for
example, a decision on whether the first subject has cancerous
cells or not. This invention provides a method to make better
decision, judgment or conclusion for the first subject (a patient,
for example) based on the first data of the first type, without any
data of the second type from the first subject. This invention
provides a method to use MRI imaging data to directly diagnose
whether an organ or tissue (such as breast or prostate) of the
first subject has cancerous cells or not without performing a
biopsy test for the first subject. In general, this invention
provides a method to make decisive conclusion, with 90% or over 90%
accuracy (or confidence level), or with 95% or over 95% accuracy
(or confidence level), or eventually, with 99% or over 99% accuracy
(or confidence level). Furthermore, the invention provides a method
for improvement of the spatial resolution of data or images with a
voxel 75%, 50% or 25%, in 1D dimension, smaller than that created
by the current available method.
[0019] These, as well as other components, steps, features,
benefits, and advantages of the present disclosure, will now become
clear from a review of the following detailed description of
illustrative embodiments, the accompanying drawings, and the
claims.
BRIEF DESCRIPTION OF THE DRAWINGS
[0020] The drawings disclose illustrative embodiments of the
present disclosure. They do not set forth all embodiments. Other
embodiments may be used in addition or instead. Details that may be
apparent or unnecessary may be omitted to save space or for more
effective illustration. Conversely, some embodiments may be
practiced without all of the details that are disclosed. When the
same reference number or reference indicator appears in different
drawings, it may refer to the same or like components or steps.
[0021] Aspects of the disclosure may be more fully understood from
the following description when read together with the accompanying
drawings, which are to be regarded as illustrative in nature, and
not as limiting. The drawings are not necessarily to scale,
emphasis instead being placed on the principles of the disclosure.
In the drawings:
[0022] FIG. 1A is a schematic drawing showing a "Big Data"
probability map creation in accordance with an embodiment of the
present invention;
[0023] FIGS. 1B-1G show a subset data table in accordance with an
embodiment of the present invention;
[0024] FIGS. 1H-1M show a subset data table in accordance with an
embodiment of the present invention;
[0025] FIG. 2A is a schematic drawing showing a biopsy tissue and
multiple MRI slices registered to the biopsy tissue in accordance
with an embodiment of the present invention;
[0026] FIG. 2B is a schematic drawing of a MRI slice in accordance
with an embodiment of the present invention;
[0027] FIG. 2C is a schematic drawing showing multiple voxels of a
MRI slice covered by a region of interest (ROI) on the MRI slice in
accordance with an embodiment of the present invention;
[0028] FIG. 2D shows a data table in accordance with an embodiment
of the present invention;
[0029] FIG. 2E shows a planar cylinder transformed from a long
cylinder of a biopsied tissue in accordance with an embodiment of
the present invention;
[0030] FIG. 3A is a schematic drawing showing a circular window and
a two-by-two grid array within a square inscribed in the circular
window in accordance with an embodiment of the present
invention;
[0031] FIG. 3B is a schematic drawing showing a circular window and
a three-by-three grid array within a square inscribed in the
circular window in accordance with an embodiment of the present
invention;
[0032] FIG. 3C is a schematic drawing showing a circular window and
a four-by-four grid array within a square inscribed in the circular
window in accordance with an embodiment of the present
invention;
[0033] FIG. 4 is a flow chart illustrating a computing method of
generating or forming a probability map in accordance with an
embodiment of the present invention;
[0034] FIG. 5 shows a MRI slice showing a prostate, as well as a
computation region on the MRI slice, in accordance with an
embodiment of the present invention;
[0035] FIG. 6A is a schematic drawing showing a circular window
moving across a computation region of a MRI slice in accordance
with an embodiment of the present invention;
[0036] FIG. 6B shows a square inscribed in a circular window having
a corner aligned with a corner of a computation region of a MRI
slice in accordance with an embodiment of the present
invention;
[0037] FIG. 7A is a schematic drawing showing multiple voxels of a
MRI slice covered by a circular window in accordance with an
embodiment of the present invention;
[0038] FIG. 7B shows a data table in accordance with an embodiment
of the present invention;
[0039] FIG. 8 shows a computation region defined with nine
computation voxels for a probability map in accordance with an
embodiment of the present invention;
[0040] FIGS. 9A, 9C, 9E, and 9G show four stops of a circular
moving window, each of which includes four non-overlapped small
squares, in accordance with an embodiment of the present
invention;
[0041] FIGS. 9B, 9D, 9F, and 9H show a circular window moving
across a computation region defined with nine computation voxels in
accordance with an embodiment of the present invention;
[0042] FIGS. 10A, 10B, and 10C show example initial probabilities
for computation voxels, updated probabilities for the computation
voxels, and optimal probabilities for the computation voxels,
respectively, in accordance with an embodiment of the present
invention;
[0043] FIG. 11 shows a computation region defined with thirty-six
computation voxels for a probability map in accordance with an
embodiment of the present invention;
[0044] FIGS. 12A, 12C, 12E, 12G, 13A, 13C, 13E, 13G, 14A, 14C, 14E,
14G, 15A, 15C, 15E, and 15G show sixteen stops of a circular moving
window, each of which includes nine non-overlapped small squares,
in accordance with an embodiment of the present invention;
[0045] FIGS. 12B, 12D, 12F, 12H, 13B, 13D, 13F, 13H, 14B, 14D, 14F,
14H, 15B, 15D, 15F, and 15H show a circular window moving across a
computation region defined with thirty-six computation voxels in
accordance with an embodiment of the present invention;
[0046] FIGS. 16A, 16B, and 16C show example initial probabilities
for computation voxels, updated probabilities for the computation
voxels, and optimal probabilities for the computation voxels,
respectively, in accordance with an embodiment of the present
invention;
[0047] FIGS. 17A-17C show three probability maps;
[0048] FIG. 17D shows a composite probability image or map;
[0049] FIG. 18 shows a MRI slice showing a breast, as well as a
computation region on the MRI slice, in accordance with an
embodiment of the present invention;
[0050] FIGS. 19A-19R show a description of various parameters
("parameter charts" and "biomarker" charts could be used to explain
many items that could be included in a big data database, this
would include the ontologies, mRNA, next generation sequencing,
etc., and exact data in "subset" databases could then be more
specific and more easily generated data);
[0051] FIG. 20 is a flow chart depicting a method of evaluating,
identifying, or determining the effect of a treatment (e.g.,
neoadjuvant chemotherapy or minimally invasive treatment of
prostate cancer) or a drug used in the treatment on a subject in
accordance with an embodiment of the present invention;
[0052] FIG. 21 is a flow chart depicting a method of evaluating,
identifying, or determining the effect of a treatment or a drug
used in the treatment on a subject in accordance with an embodiment
of the present invention;
[0053] FIG. 22 is a flow chart depicting a method of evaluating,
identifying, or determining the effect of a treatment or a drug
used in the treatment on a subject in accordance with an embodiment
of the present invention; and
[0054] FIG. 23 is a diagram showing two Gaussian curves of two
given different groups with respect to parameter measures.
[0055] While certain embodiments are depicted in the drawings, one
skilled in the art will appreciate that the embodiments depicted
are illustrative and that variations of those shown, as well as
other embodiments described herein, may be envisioned and practiced
within the scope of the present disclosure.
DETAILED DESCRIPTION OF THE INVENTION
[0056] Illustrative embodiments are now described. Other
embodiments may be used in addition or instead. Details that may be
apparent or unnecessary may be omitted to save space or for a more
effective presentation. Conversely, some embodiments may be
practiced without all of the details that are disclosed.
[0057] Computing methods described in the present invention may be
performed on any type of image, such as molecular and structural
image (e.g., MRI image, CT image, PET image, SPECT image,
micro-PET, micro-SPECT, Raman image, or bioluminescence optical
(BLO) image), structural image (e.g., CT image or ultrasound
image), fluoroscopy image, structure/tissue image, optical image,
infrared image, X-ray image, or any combination of these types of
images, based on a registered (multi-parametric) image dataset for
the image. The registered (multi-parametric) image dataset may
include multiple imaging data or parameters obtained from one or
more modalities, such as MRI, PET, SPECT, CT, fluoroscopy,
ultrasound imaging, BLO imaging, micro-PET, micro-SPECT, Raman
imaging, structure/tissue imaging, optical imaging, infrared
imaging, and/or X-ray imaging. For a patient, the registered
(multi-parametric) image dataset may be created by aligning or
registering in space all parameters obtained from different times
or from various machines. Methods in first, second and third
embodiments of the invention may be performed on a MRI image based
on the registered (multi-parametric) image dataset, including,
e.g., MRI parameters and/or PET parameters, for the MRI image.
[0058] Referring to FIG. 1A, a big data database 70 is created to
include multiple data sets, each of which may include: (1) a first
set of information data, which may be obtained by a non-invasive
method or a less-invasive method (as compared to a method used to
obtain the following second set of information data), wherein the
first set of data information may include measures for multiple
imaging parameters, including, e.g., molecular and structural
imaging parameters (such as MRI parameters, CT parameters, PET
parameters, SPECT parameters, micro-PET parameters, micro-SPECT
parameters, Raman parameters, and/or BLO parameters) and/or other
structural imaging data (such as from CT and/or ultrasound images),
for a volume and location of a tissue to be biopsied (e.g.,
prostate or breast) from a subject such as human or animal, (2)
combinations each of specific some of the imaging parameters, (3)
dimensions related to imaging parameters (e.g., molecular and
structural imaging parameters), such as the thickness T of an MRI
slice and the size of an MRI voxel of the MRI slice, including the
width or side length of the MRI voxel and the thickness or height
of the MRI voxel (which may be substantially equal to the thickness
T of the MRI slice), (4) a second set of information data obtained
by an invasive method or a more-invasive method (as compared to the
method used to obtain the first set of information data), wherein
the second set of the information data may include tissue-based
information from a biopsy performed on the subject, (5) clinical
data (e.g., age and sex of the subject and/or Gleason score of a
prostate cancer) associated with the biopsied tissue and/or the
subject, and (6) risk factors for cancer associated with the
subject.
[0059] Some or all of the subjects for creating the big data
database 70 may have been subjected to a treatment such as
neoadjuvant chemotherapy or (preoperative) radiation therapy.
Alternatively, some or all of the subjects for creating the big
data database 70 are not subjected to a treatment such as
neoadjuvant chemotherapy or (preoperative) radiation therapy. The
imaging parameters in each of the data sets of the big data
database 70 may be obtained from different modalities, including
two or more of the following: MRI, PET, SPECT, CT, fluoroscopy,
ultrasound imaging, BLO imaging, micro-PET, micro-SPECT, and Raman
imaging. Accordingly, the imaging parameters in each of the data
sets of the big data database 70 may include four or more types of
MRI parameters depicted in FIGS. 19A-19H, one or more types of PET
parameters depicted in FIG. 19I, one or more types of biomarker
features depicted in FIG. 19J, and other parameters depicted in
FIG. 19K. Alternatively, the first set of information data may only
include a type of imaging parameter (such as T1 mapping). In each
of the data sets of the big data database 70, each of the imaging
parameters (such as T1 mapping) for the tissue to be biopsied may
have a measure calculated based on an average of measures, for said
each of the imaging parameters, for multiple regions, portions,
locations or volumes of interest of multiple registered images
(such as MRI slices) registered to or aligned with respective
regions, portions, locations or volumes of the tissue to be
biopsied, wherein all of the regions, portions, locations or
volumes of interest of the registered images may have a total
volume covering and substantially equaling the volume of the tissue
to be biopsied. The number of the registered images for the tissue
to be biopsied may be greater than or equal to 2, 5 or 10.
[0060] In the case of the biopsied tissue obtained by a needle, the
biopsied tissue may be long cylinder-shaped with a radius Rn, which
is substantially equal to an inner radius of the needle, and a
height tT normalized to the thickness T of the MRI slice. In the
invention, the volume of the long cylinder-shaped biopsied tissue
may be transformed into another shape, which may have a volume the
same or about the same as the volume of the long cylinder-shaped
biopsied tissue (or Volume of Interest, VOI), for easy or
meaningful computing purposes, for medical instrumentation
purposes, or for clearer final data presentation purposes. For
example, the long cylinder of the biopsied tissue with the radius
Rn and height tT may be transformed into a planar cylinder to match
the MRI slice thickness T. The planar cylinder, for example, may
have a height equal to the MRI slice thickness T, a radius Rw equal
to the radius Rn multiplied by the square root of the number of the
registered images, and a volume the same or about the same as the
volume of the biopsied tissue, i.e., VOI. The radius Rw of the
planner cylinder is used to define the size (e.g., the radius Rm)
of a moving window MW in calculating a probability map for a
patient (e.g., human). In the invention, the volume of the biopsied
tissue, i.e., VOI, for each of the data sets, for example, may be
substantially equal to the volume of the moving window MW to be
used in calculating probability maps. In other words, the volume of
the biopsied tissue, i.e., VOI, defines the size of the moving
window MW to be used in calculating probability maps.
Statistically, the moving window MW may be determined with the
radius Rm, perpendicular to a thickness of the moving window MW,
based on the statistical distribution or average of the radii Rw
(calculated from multiple VOIs) associated with a subset data
(e.g., the following subset data DB-1 or DB-2) from the big data
database 70.
[0061] The tissue-based information in each of the data sets of the
big data database 70 may include (1) a biopsy result, data,
information (i.e., pathologist diagnosis, for example cancer or no
cancer) for the biopsied tissue, (2) mRNA data or expression
patterns, (3) DNA data or mutation patterns (including that
obtained from next generation sequencing), (4) ontologies, (5)
biopsy related feature size or volume (including the radius Rn of
the biopsied tissue, the volume of the biopsied tissue (i.e., VOI),
and/or the height tT of the biopsied tissue), and (6) other
histological and biomarker findings such as necrosis, apoptosis,
percentage of cancer, increased hypoxia, vascular reorganization,
and receptor expression levels such as estrogen, progesterone,
HER2, and EPGR receptors. For example, regarding the tissue-based
information of the big data database 70, each of the data sets may
include specific long chain mRNA biomarkers from next generation
sequencing that are predictive of metastasis-free survival, such as
HOTAIR, RP11-278 L15.2-001, LINC00511-009, AC004231.2-001. The
clinical data in each of the data sets of the big data database 70
may include the timing of treatment, demographic data (e.g., age,
sex, race, weight, family type, and residence of the subject), and
TNM staging depicted in, e.g., FIGS. 19N and 19O or FIGS. 19P, 19Q
and 19R. Each of the data sets of the big data database 70 may
further include information regarding neoadjuvant chemotherapy
and/or information regarding (preoperative) radiation therapy.
Imaging protocol details, such as MRI magnet strength, pulse
sequence parameters, PET dosing, time at PET imaging, may also be
included in the big data database 70. The information regarding
(preoperative) radiation therapy may include the type of radiation,
the strength of radiation, the total dose of radiation, the number
of fractions (depending on the type of cancer being treated), the
duration of the fraction from start to finish, the dose of the
fraction, the duration of the preoperative radiation therapy from
start to finish, and the type of machine used for the preoperative
radiation therapy. The information regarding neoadjuvant
chemotherapy may include the given drug(s), the number of cycles
(i.e., the duration of the neoadjuvant chemotherapy from start to
finish), the duration of the cycle from start to finish, and the
frequency of the cycle.
[0062] Data of interest are selected from the big data database 70
into a subset, used to build a classifier CF. The subset from the
big data database 70 may be selected for a specific application,
such as prostate cancer, breast cancer, breast cancer after
neoadjuvant chemotherapy, or prostate cancer after radiation. In
the case of the subset selected for prostate cancer, the subset may
include data in a tissue-based or biopsy-based subset data DB-1. In
the case of the subset selected for breast cancer, the subset may
include data in a tissue-based or biopsy-based subset data DB-2.
Using suitable methods, such as statistical methods, correlation
methods, big data methods, and/or learning and training methods,
the classifier CF may be constructed or created based on a first
group associated with a first data type or feature (e.g., prostate
cancer or breast cancer) in the subset, a second group associated
with a second data type or feature (e.g., non-prostate cancer or
non-breast cancer) in the subset, and some or all of the variables
in the subset associated with the first and second groups.
Accordingly, the classifier CF for an event, such as the first data
type or feature, may be created based on the subset associated with
the event from the big data database 70. The event may be a
biopsy-diagnosed tissue characteristic, such as having specific
cancerous cells, or occurrence of prostate cancer or breast
cancer.
[0063] After the database 70 and the classifier CF are created or
constructed, a probability map, composed of multiple computation
voxels with the same size, is generated or constructed for, e.g.,
evaluating or determining the health status of a patient (e.g.,
human subject), the physical condition of an organ or other
structure inside the patient's body, or the patient's progress and
therapeutic effectiveness by the steps described below. First, an
image of the patient is obtained by a device or system, such as MRI
system. The image of the patient, for example, may be a molecular
image (e.g., MRI image, PET image, SPECT image, micro-PET image,
micro-SPECT image, Raman image, or BLO image) or other suitable
image (e.g., CT image or ultrasound image). In addition, based on
the step size of a moving window and/or the radius Rm of the moving
window MW obtained from the subset, e.g., the subset data DB-1 or
DB-2, in the big data database 70, the size of the computation
voxel, which becomes the basic unit of the probability map, is
defined.
[0064] If the moving window MW is circular, the biggest square
inscribed in the moving window MW is then defined. Next, the
biggest square inscribed in the moving window MW is divided into
n.sup.2 small squares, i.e., cubes, each having a width Wsq, where
n is an integer, such as 2, 3, 4, 5, 6, or more than 6. The divided
squares define the size and shape of the computation voxels in the
probability map for the image of the patient. For example, each of
the computation voxels of the probability map may be defined as a
square, i.e., cube, having the width Wsq and a volume the same or
about the same as that of each of the divided squares. The moving
window MW may move across the image of the patient at a regular
step or interval of a fixed distance, e.g., substantially equal to
the width Wsq (i.e., the width of the computation voxels), in the x
and y directions. A stop of the moving window MW overlaps with the
neighboring stop of the moving window MW.
[0065] Alternatively, the biggest square inscribed in the moving
window MW may be divided into n rectangles each having a width Wrec
and a length Lrec, where n is an integer, such as 2, 3, 4, 5, 6, 7,
8, or more than 8. The divided rectangles define the size and shape
of the computation voxels in the probability map for the image of
the patient. Each of the computation voxels of the probability map,
for example, may be a rectangle having the width Wrec, the length
Lrec, and a volume the same or about the same as that of each of
the divided rectangles. The moving window MW may move across the
patient's molecular image at a regular step or interval of a fixed
distance, e.g., substantially equal to the width Wrec (i.e., the
width of the computation voxels), in the x direction and at a
regular step or interval of a fixed distance, e.g., substantially
equal to the length Lrec (i.e., the length of the computation
voxels), in the y direction. A stop of the moving window MW
overlaps with the neighboring stop of the moving window MW. In an
alternative embodiment, each of the stops of the moving window MW
may have a width, length or diameter less than the side length
(e.g., the width or length) of voxels in the image of the
patient.
[0066] After the size and shape of the computation voxels are
obtained or defined, the stepping of the moving window MW and the
overlapping between two neighboring stops of the moving window MW
can then be determined. Measures of specific imaging parameters for
each stop of the moving window MW may be obtained from the
patient's image and/or different parameter maps (e.g., MRI
parameter map(s), PET parameter map(s) and/or CT parameter map(s))
registered to the patient's image. The specific imaging parameters
may include two or more of the following: MRI parameters, PET
parameters, SPECT parameters, micro-PET parameters, micro-SPECT
parameters, Raman parameters, BLO parameters, CT parameters, and
ultrasound imaging parameters. Each of the specific imaging
parameters for each stop of the moving window MW, for example, may
have a measure calculated based on an average of measures, for said
each of the specific imaging parameters, for voxels of the
patient's image inside said each stop of the moving window MW. In
the case that some voxels of the patient's image only partially
inside that stop of the moving window MW, the average can be
weighed by the area proportion. The specific imaging parameters of
different modalities may be obtained from registered image sets (or
registered parameter maps), and rigid and nonrigid standard
registration techniques may be used to get each section of anatomy
into the same exact coordinate location on each of the registered
(multi-parametric) image dataset.
[0067] A registered (multi-parametric) image dataset may be created
for the patient to include multiple registered images (including
two or more of the following: MRI slice images, PET images, SPECT
images, micro-PET images, micro-SPECT images, Raman images, BLO
images, CT images, and ultrasound images) and/or corresponding
imaging parameters (including two or more of the following: MRI
parameters, PET parameters, SPECT parameters, micro-PET parameters,
micro-SPECT parameters, Raman parameters, BLO parameters, CT
parameters, and/or ultrasound imaging parameters) obtained from
various equipment, machines, or devices or from a defined
time-point (e.g., specific date) or time range (e.g., within five
days after treatment). Each of the imaging parameters in the
patient's registered (multi-parametric) image dataset requires
alignment or registration. The registration can be done by, for
example, using unique anatomical marks, structures, tissues,
geometry, and/or shapes or using mathematical algorithms and
computer pattern recognition. The measures of the specific imaging
parameters for each stop of the moving window MW, for example, may
be obtained from the registered (multi-parametric) image dataset
for the patient.
[0068] Next, the specific imaging parameters for each stop of the
moving window MW may be reduced using, e.g., subset selection,
aggregation, and dimensionality reduction into a parameter set for
said each stop of the moving window MW. In other words, the
parameter set includes measures for independent imaging parameters.
The imaging parameters used in the parameter set may have multiple
types, such as two types, more than two types, more than three
types, or more than four types, independent from each other or one
another, or may have a single type. For example, the imaging
parameters used in the parameter set may include (a) MRI parameters
and PET parameters, (b) MRI parameters and SPET parameters, (c) MRI
parameters and CT parameters, (d) MRI parameters and ultrasound
imaging parameters, (e) Raman imaging parameters and CT parameters,
(f) Raman imaging parameters and ultrasound imaging parameters, (g)
MRI parameters, PET parameters, and ultrasound imaging parameters,
or (h) MRI parameters, PET parameters, and CT parameters.
[0069] Next, the parameter set for each stop of the moving window
MW is matched to the classifier CF to obtain a probability PW of
the event for said each stop of the moving window MW. After the
probabilities PWs of the event for the stops of the moving window
MW are obtained, an algorithm may be performed based on the
probabilities PWs of the event for the stops of the moving window
MW to compute probabilities of the event for the computation
voxels.
[0070] Description of Subset Data DB-1:
[0071] Referring to FIGS. 1B-1G, the tissue-based or biopsy-based
subset data DB-1 from the big data database 70 includes multiple
data sets each listed in the corresponding one of its rows 2
through N, wherein the number of the data sets may be greater than
100, 1,000 or 10,000. Each of the data sets in the subset data DB-1
may include: (1) measures for MRI parameters associated with a
prostate biopsy tissue (i.e., biopsied sample of the prostate)
obtained from a subject (e.g., human), as shown in columns A-O; (2)
measures for processed parameters associated with the prostate
biopsy tissue, as shown in columns P and Q; (3) a result or
pathologist diagnosis of the prostate biopsy tissue, such as
prostate cancer, normal tissue, or benign condition, as shown in a
column R; (4) sample characters associated with the prostate biopsy
tissue, as shown in columns S-X; (5) MRI characters associated with
MRI slices registered to respective regions, portions, locations or
volumes of the prostate biopsy tissue, as shown in columns Y, Z and
AA; (6) clinical or pathology parameters associated with the
prostate biopsy tissue or the subject, as shown in columns AB-AN;
and (7) personal information associated with the subject, as shown
in columns AO-AR. Needles used to obtain the prostate biopsy
tissues may have the same cross-sectional shape (e.g., round shape
or square shape) and the same inner diameter or width, e.g.,
ranging from, equal to or greater than 0.1 millimeters up to, equal
to or less than 5 millimeters, and more preferably ranging from,
equal to or greater than 1 millimeter up to, equal to or less than
3 millimeters.
[0072] The MRI parameters in the columns A-O of the subset data
DB-1 are T1 mapping, T2 raw signal, T2 mapping, delta Ktrans
(.DELTA.Ktrans), tau, Dt IVIM, fp IVIM, ADC (high b-values), nADC
(high b-values), R*, Ktrans from Tofts Model (TM), Ktrans from
Extended Tofts Model (ETM), Ktrans from Shutterspeed Model (SSM),
Ve from TM, and Ve from SSM. For more information about the MRI
parameters in the subset data DB-1, please refer to FIGS. 19A
through 19H. The processed parameter in the column P of the subset
data DB-1 is average Ve, obtained by averaging Ve from TM and Ve
from SSM. The processed parameter in the column Q of the subset
data DB-1 is average Ktrans, obtained by averaging Ktrans from TM,
Ktrans from ETM, and Ktrans from SSM. All data can have normalized
values, such as z scores.
[0073] Measures in the respective columns T, U and V of the subset
data DB-1 are Gleason scores associated with the respective
prostate biopsy tissues and primary and secondary Gleason grades
associated with the Gleason scores; FIG. 19L briefly explains
Gleason score, the primary Gleason grade, and the secondary Gleason
grade. Measures in the column W of the subset data DB-1 may be the
diameters of the prostate biopsy tissues, and the diameter of each
of the prostate biopsy tissues may be substantially equal to an
inner diameter of a cylinder needle, through which a circular or
round hole passes for receiving said each of the prostate biopsy
tissues. Alternatively, measures in the column W of the subset data
DB-1 may be the widths of the prostate biopsy tissues, and the
width of each of the prostate biopsy tissues may be substantially
equal to an inner width of a needle, through which a square or
rectangular hole passes for receiving said each of the prostate
biopsy tissues. The clinical or pathology parameters in the columns
AB-AN of the subset data DB-1 are prostate specific antigen (PSA),
PSA velocity, % free PSA, Histology subtype, location within a
given anatomical structure of gland, tumor size, PRADS,
pathological diagnosis (e.g., Atypia, benign prostatic hypertrophy
(BPH), prostatic intraepithelial neoplasia (PIN), or Atrophy),
pimonidazole immunoscore (hypoxia marker), pimonidazole genescore
(hypoxia marker), primary tumor (T), regional lymph nodes (N), and
distant metastasis (M). For more information about the clinical or
pathology parameters in the subset data DB-1, please refer to FIGS.
19M through 19O. Other data or information in the big data database
70 may be added to the subset data DB-1. For example, each of the
data sets in the subset data DB-1 may further include risk factors
for cancer associated with the subject, such as smoking history,
sun exposure, premalignant lesions, gene information or data, etc.
Each of the data sets in the subset data DB-1 may also include
imaging protocol details, such as MRI magnet strength, and pulse
sequence parameters, and/or information regarding (preoperative)
radiation therapy, including the type of radiation, the strength of
radiation, the total dose of radiation, the number of fractions
(depending on the type of cancer being treated), the duration of
the fraction from start to finish, the dose of the fraction, the
duration of the preoperative radiation therapy from start to
finish, and the type of machine used for the preoperative radiation
therapy. A post-therapy data or information for prostate cancer may
also be included in the subset data DB-1. For example, data
regarding ablative minimally invasive techniques or radiation
treatments (care for early prostate cancer or post-surgery),
imaging data or information following treatment, and biopsy results
following treatment are included in the subset data DB-1.
[0074] Referring to FIGS. 1D and 1E, data in the column W of the
subset data DB-1 are various diameters; data in the column X of the
subset data DB-1 are various lengths; data in the column Y of the
subset data DB-1 are the various numbers of MRI slices registered
to respective regions, portions, locations or volumes of a prostate
biopsy tissue; data in the column Z of the subset data DB-1 are
various MRI area resolutions; data in the column AA of the subset
data DB-1 are various MRI slice thicknesses. Alternatively, the
diameters of all the prostate biopsy tissues in the column W of the
subset data DB-1 may be the same; the lengths of all the prostate
biopsy tissues in the column X of the subset data DB-1 may be the
same; all the data in the column Y of the subset data DB-1 may be
the same; all the data in the column Z of the subset data DB-1 may
be the same; all the data in the column AA of the subset data DB-1
may be the same.
[0075] Description of Subset Data DB-2:
[0076] Referring to FIGS. 1H-1M, the tissue-based or biopsy-based
subset data DB-2 from the big data database 70 includes multiple
data sets each listed in the corresponding one of its rows 2
through N, wherein the number of the data sets may be greater than
100, 1,000 or 10,000. Each of the data sets in the subset data DB-2
may include: (1) measures for MRI parameters associated with a
breast biopsy tissue (i.e., biopsied sample of the breast) obtained
from a subject (e.g., human or animal model), as shown in columns
A-O, R, and S; (2) measures for processed parameters associated
with the breast biopsy tissue, as shown in columns P and Q; (3)
features of breast tumors associated with the breast biopsy tissue,
as shown in columns T-Z; (4) a result or pathologist diagnosis of
the breast biopsy tissue, such as breast cancer, normal tissue, or
benign condition, as shown in a column AA; (5) sample characters
associated with the breast biopsy tissue, as shown in columns
AB-AD; (6) MRI characters associated with MRI slices registered to
respective regions, portions, locations or volumes of the breast
biopsy tissue, as shown in columns AE-AG; (7) a PET parameter
(e.g., maximum standardized uptake value (SUVmax) depicted in FIG.
19I) associated with the breast biopsy tissue or the subject, as
shown in a column AH; (8) clinical or pathology parameters
associated with the breast biopsy tissue or the subject, as shown
in columns AI-AT; and (9) personal information associated with the
subject, as shown in columns AU-AX. Needles used to obtain the
breast biopsy tissues may have the same cross-sectional shape
(e.g., round shape or square shape) and the same inner diameter or
width, e.g., ranging from, equal to or greater than 0.1 millimeters
up to, equal to or less than 5 millimeters, and more preferably
ranging from, equal to or greater than 1 millimeter up to, equal to
or less than 3 millimeters. Alternatively, an intra-operative
incisional biopsy tissue sampling may be performed by a surgery to
obtain the breast biopsy. Intraoperative magnetic resonance imaging
(iMRI) may be used for obtaining a specific localization of the
breast biopsy tissue to be biopsied during the surgery.
[0077] The MRI parameters in the columns A-O, R, and S of the
subset data DB-2 are T1 mapping, T2 raw signal, T2 mapping, delta
Ktrans (.DELTA.Ktrans), tau, Dt IVIM, fp IVIM, ADC (high b-values),
R*, Ktrans from Tofts Model (TM), Ktrans from Extended Tofts Model
(ETM), Ktrans from Shutterspeed Model (SSM), Ve from TM, Ve from
SSM, kep from Tofts Model (TM), kep from Shutterspeed Model (SSM),
and mean diffusivity (MD) from diffusion tensor imaging (DTI). For
more information about the MRI parameters in the subset data DB-2,
please refer to FIGS. 19A through 20H. The processed parameter in
the column P of the subset data DB-2 is average Ve, obtained by
averaging Ve from TM and Ve from SSM. The processed parameter in
the column Q of the subset data DB-2 is average Ktrans, obtained by
averaging Ktrans from TM, Ktrans from ETM, and Ktrans from SSM. The
features of breast tumors may be extracted from breast tumors with
dynamic contrast-enhanced MRI image (DCE-MRI).
[0078] Measures in the column AC of the subset data DB-2 may be the
diameters of the breast biopsy tissues, and the diameter of each of
the breast biopsy tissues may be substantially equal to an inner
diameter of a cylinder needle, through which a circular or round
hole passes for receiving said each of the breast biopsy tissues.
Alternatively, the measures in the column AC of the subset data
DB-2 may be the widths of the breast biopsy tissues, and the width
of each of the breast biopsy tissues may be substantially equal to
an inner width of a needle, through which a square or rectangular
hole passes for receiving said each of the breast biopsy tissues.
The clinical or pathology parameters in the columns AI-AT of the
subset data DB-2 are estrogen hormone receptor positive (ER+),
progesterone hormone receptor positive (PR+), HER2/neu hormone
receptor positive (HER2/neu+), immunohistochemistry subtype, path,
BIRADS, Oncotype DX score, primary tumor (T), regional lymph nodes
(N), distant metastasis (M), tumor size, and location. For more
information about the clinical or pathology parameters in the
subset data DB-2, please refer to FIGS. 19P through 19R. Other data
or information in the big data database 70 may be added to the
subset data DB-2. For example, each of the data sets in the subset
data DB-2 may further include specific long chain mRNA biomarkers
from next generation sequencing that are predictive of
metastasis-free survival, such as HOTAIR, RP11-278 L15.2-001,
LINC00511-009, and AC004231.2-001. Each of the data sets in the
subset data DB-2 may also include risk factors for cancer
associated with the subject, such as smoking history, sun exposure,
premalignant lesions, gene information or data, etc. Each of the
data sets in the subset data DB-2 may also include imaging protocol
details, such as MRI magnet strength, pulse sequence parameters,
PET dosing, time at PET imaging, etc.
[0079] Referring to FIG. 1K, data in the column AC of the subset
data DB-2 are various diameters; data in the column AD of the
subset data DB-2 are various lengths; data in the column AE of the
subset data DB-2 are the various numbers of MRI slices registered
to respective regions, portions, locations or volumes of a breast
biopsy tissue; data in the column AF of the subset data DB-2 are
various MRI area resolutions; data in the column AG of the subset
data DB-2 are various MRI slice thicknesses. Alternatively, the
diameters of all the breast biopsy tissues in the column AC of the
subset data DB-2 may be the same; the lengths of all the breast
biopsy tissues in the column AD of the subset data DB-2 may be the
same; all the data in the column AE of the subset data DB-2 may be
the same; all the data in the column AF of the data DB-2 may be the
same; all the data in the column AG of the subset data DB-2 may be
the same.
[0080] A similar subset data like the subset data DB-1 or DB-2 may
be established from the big data database 70 for generating
probability maps for brain cancer, liver cancer, lung cancer,
rectal cancer, sarcomas, cervical cancer, or cancer metastasis to
any organ such as liver, bone, and brain. In this case, the subset
data may include multiple data sets, each of which may include: (1)
measures for MRI parameters (e.g., those in the columns A-O, R, and
S of the subset data DB-2) associated with a biopsy tissue (e.g.,
biopsied brain sample, biopsied liver sample, biopsied lung sample,
biopsied rectal sample, biopsied sarcomas sample, or biopsied
cervix sample) obtained from a subject (e.g., human); (2) processed
parameters (e.g., those in the columns P and Q of the subset data
DB-2) associated with the biopsy tissue; (3) a result or
pathologist diagnosis of the biopsy tissue, such as cancer, normal
tissue, or benign condition; (4) sample characters (e.g., those in
the columns S-X of the subset data DB-1) associated with the biopsy
tissue; (5) MRI characters (e.g., those in the columns Y, Z and AA
of the subset data DB-1) associated with MRI slices registered to
respective regions, portions, locations or volumes of the biopsy
tissue; (6) a PET parameter (e.g., SUVmax depicted in FIG. 19I)
associated with the biopsy tissue or the subject; (7) CT parameters
(e.g., HU and Hetwave) associated with the biopsy tissue or the
subject; (8) clinical or pathology parameters (e.g., those in the
columns AB-AN of the subset data DB-1 or the columns AI-AT of the
subset data DB-2) associated with the biopsy tissue or the subject;
and (9) personal information (e.g., those in the columns AO-AR of
the subset data DB-1) associated with the subject.
[0081] Description of Biopsy Tissue, MRI Slices Registered to the
Biopsy Tissue, and MRI Parameters for the Biopsy Tissue:
[0082] Referring to FIG. 2A, a biopsy tissue or sample 90, such as
any one of the biopsied tissues provided for the pathologist
diagnosis depicted in the big data database 70, any one of the
prostate biopsy tissues provided for the pathologist diagnosis
depicted in the subset data DB-1, or any one of the breast biopsy
tissues provided for the pathologist diagnosis depicted in the
subset data DB-2, may be obtained from a subject (e.g., human) by
core needle biopsy, such as MRI-guided needle biopsy.
Alternatively, an intra-operative incisional biopsy tissue sampling
may be performed by a surgery to obtain the biopsy tissue 90 from
the subject. One or more fiducial markers that could be seen on
subsequent imaging may be placed during the surgery to match
tissues or identify positions of various portions of an organ with
respect to the one or more fiducial markers. The fiducial marker is
an object placed in the field of view of an imaging system which
appears in the image produced, for use as a point of reference or a
measure.
[0083] The core needle biopsy is a procedure used to determine
whether an abnormality or a suspicious area of an organ (e.g.,
prostate or breast) is a cancer, a normal tissue, or a benign
condition or to determine any other tissue characteristic such as
mRNA expression, receptor status, and molecular tissue
characteristics. With regard to imaging-guided needle biopsy,
magnetic resonance (MR) or CT imaging may be used to guide a
cylinder needle to the abnormality or the suspicious area so that a
piece of tissue, such as the biopsy tissue 90, is removed from the
abnormality or the suspicious area by the cylinder needle, and the
removed tissue is then sent to be examined by pathology.
[0084] During or before the core needle biopsy (e.g.,
imaging-guided needle biopsy), parallel MRI or CT slices SI.sub.1
through SI.sub.N registered to multiple respective regions,
portions, locations or volumes of the tissue 90 may be obtained.
The number of the registered MRI or CT slices SI.sub.1-SI.sub.N may
range from, equal to or greater than 2 up to, equal to or less than
10. The registered MRI or CT slices SI.sub.1-SI.sub.N may have the
same slice thickness T, e.g., ranging from, equal to or greater
than 1 millimeter up to, equal to or less than 10 millimeters, and
more preferably ranging from, equal to or greater than 3
millimeters up to, equal to or less than 5 millimeters.
[0085] Referring to FIGS. 2A and 2E, the biopsy tissue 90 obtained
from the subject by the cylinder needle may be long cylinder-shaped
with a height tT normalized to the slice thickness T and with a
circular cross section perpendicular to its axial direction AD, and
the circular cross section of the biopsy tissue 90 may have a
diameter D1, perpendicular to its height tT extending along the
axial direction AD, ranging from, equal to or greater than 0.5
millimeters up to, equal to or less than 4 millimeters. The
diameter D1 of the biopsy tissue 90 may be substantially equal to
an inner diameter of the cylinder needle, through which a circular
or round hole passes for receiving the biopsy tissue 90. The axial
direction AD of the tissue 90 to be biopsied may be parallel with
the slice thickness direction of each of the MRI or CT slices
SI.sub.1-SI.sub.N. As shown in FIG. 2B, each of the MRI or CT
slices SI.sub.1-SI.sub.N may have an imaging plane 92 perpendicular
to the axial direction AD of the tissue 90 to be biopsied, wherein
an area of the imaging plane 92 is a side length W1 multiplied by
another side length W2. The MRI or CT slices SI.sub.1-SI.sub.N may
have the same area resolution, which is a field of view (FOV) of
one of the MRI or CT slices SI.sub.1-SI.sub.N(i.e., the area of its
imaging plane 92) divided by the number of all voxels in the
imaging plane 92 of said one of the MRI or CT slices
SI.sub.1-SI.sub.N.
[0086] Regions, i.e., portions, locations or volumes, of interest
(ROIs) 94 of the respective MRI or CT slices SI.sub.1-SI.sub.N are
registered to and aligned with the respective regions, portions,
locations or volumes of the biopsy tissue 90 to determine or
calculate measures of imaging parameters for the regions, portions,
locations or volumes of the biopsy tissue 90. The ROIs 94 of the
MRI or CT slices SI.sub.1-SI.sub.N may have the same diameter,
substantially equal to the diameter D1 of the biopsy tissue 90,
i.e., the inner diameter of the needle for taking the biopsy tissue
90, and may have a total volume covering and substantially equaling
the volume of the biopsy tissue 90. As shown in FIG. 2C, the ROI 94
of each of the MRI or CT slices SI.sub.1-SI.sub.N may cover or
overlap multiple voxels, e.g., 96a through 96f. A MRI or other
imaging parameter (e.g., T1 mapping) for the ROI 94 of each of the
MRI slices SI.sub.1-SI.sub.N may be measured by summing values of
the MRI parameter for the voxels 96a-96f in said each of the MRI
slices SI.sub.1-SI.sub.N weighed or multiplied by the respective
percentages of areas A1, A2, A3, A4, A5 and A6, overlapping with
the respective voxels 96a-96f in the ROI 94 of said each of the MRI
slices SI.sub.1-SI.sub.N, occupying the ROI 94 of said each of the
MRI slices SI.sub.1-SI.sub.N. Accordingly, the MRI parameter for
the whole biopsy tissue 90 may be measured by dividing the sum of
measures for the MRI parameter for the ROIs 94 of the MRI slices
SI.sub.1-SI.sub.N by the number of the MRI slices
SI.sub.1-SI.sub.N. By this way, other MRI parameters (e.g., those
in the columns B-O of the subset data DB-1 or those in the columns
B-O, R and S of the subset data DB-2) for the whole biopsy tissue
90 are measured. The measures for the various MRI parameters (e.g.,
T1 mapping, T2 raw signal, T2 mapping, etc.) for the ROI 94 of each
of the MRI slices SI.sub.1-SI.sub.N may be derived from different
parameter maps registered to the corresponding region, portion,
location or volume of the biopsy tissue 90. In an alternative
example, the measures for some of the MRI parameters for the ROI 94
of each of the MRI slices SI.sub.1-SI.sub.N may be derived from
different parameter maps registered to the corresponding region,
portion, location or volume of the biopsy tissue 90, and the
measures for the others may be derived from the same parameter map
registered to the corresponding region, portion, location or volume
of the biopsy tissue 90. The aforementioned method for measuring
the MRI parameters for the whole biopsy tissue 90 can be applied to
each of the MRI parameters in the big data database 70 and the
subset data DB-1 and DB-2.
[0087] Taking an example of T1 mapping, in the case of (1) four MRI
slices SI.sub.1-SI.sub.4 having four respective regions, portions,
locations or volumes registered to respective quarters of the
biopsy tissue 90 and (2) the ROI 94 of each of the MRI slices
SI.sub.1-SI.sub.4 covering or overlapping the six voxels 96a-96f,
values of T1 mapping for the voxels 96a-96f in each of the MRI
slices SI.sub.1-SI.sub.4 and the percentages of the areas A1-A6
occupying the ROI 94 of each of the MRI slices SI.sub.1-SI.sub.4
are assumed as shown in FIG. 2D. A measure of T1 mapping for the
ROI 94 of the MRI slice SI.sub.1, i.e., 1010.64, may be obtained or
calculated by summing (1) the value, i.e., 1010, for the voxel 96a
multiplied by the percentage, i.e., 6%, of the area A1, overlapping
with the voxel 96a in the ROI 94 of the MRI slice SI.sub.1,
occupying the ROI 94 of the MRI slice SI.sub.1, (2) the value,
i.e., 1000, for the voxel 96b multiplied by the percentage, i.e.,
38%, of the area A2, overlapping with the voxel 96b in the ROI 94
of the MRI slice SI.sub.1, occupying the ROI 94 of the MRI slice
SI.sub.1, (3) the value, i.e., 1005, for the voxel 96c multiplied
by the percentage, i.e., 6%, of the area A3, overlapping with the
voxel 96c in the ROI 94 of the MRI slice SI.sub.1, occupying the
ROI 94 of the MRI slice SI.sub.1, (4) the value, i.e., 1020, for
the voxel 96d multiplied by the percentage, i.e., 6%, of the area
A4, overlapping with the voxel 96d in the ROI 94 of the MRI slice
SI.sub.1, occupying the ROI 94 of the MRI slice SI.sub.1, (5) the
value, i.e., 1019, for the voxel 96e multiplied by the percentage,
i.e., 38%, of the area A5, overlapping with the voxel 96e in the
ROI 94 of the MRI slice SI.sub.1, occupying the ROI 94 of the MRI
slice SI.sub.1, and (6) the value, i.e., 1022, for the voxel 96f
multiplied by the percentage, i.e., 6%, of the area A6, overlapping
with the voxel 96f in the ROI 94 of the MRI slice SI.sub.1,
occupying the ROI 94 of the MRI slice SI.sub.1. By this way, T1
mapping for the ROIs 94 of the MRI slices SI.sub.2, SI.sub.3, and
SI.sub.4, i.e., 1006.94, 1022, and 1015.4, are obtained or
measured. Accordingly, T1 mapping for the whole biopsy tissue 90,
i.e., 1013.745, is obtained or measured by dividing the sum, i.e.,
4054.98, of T1 mapping for the ROIs 94 of the MRI slices
SI.sub.1-SI.sub.4 by the number of the MRI slices
SI.sub.1-SI.sub.4, i.e., 4.
[0088] The volume of the long cylinder-shaped biopsied tissue 90
may be transformed into another shape, which may have a volume the
same or about the same as the volume of the long cylinder-shaped
biopsied tissue 90 (or Volume of Interest (VOI)), which may be
.pi..times.Rn.sup.2.times.tT, where Rn is the radius of the
biopsied tissue 90, and tT is the height of the biopsied tissue
90), for easy or meaningful computing purposes, for medical
instrumentation purposes, or for clearer final data presentation
purposes. For example, referring to FIG. 2E, the long cylinder of
the biopsied tissue 90 with the radius Rn and height tT may be
transformed into a planar cylinder 98 to match the slice thickness
T. The planar cylinder 98, having a volume, e.g., the same or about
the same as the VOI of the biopsied tissue 90, may be defined by
the following formula:
.pi..times.Rn.sup.2.times.M.times.St=r.times.Rw.sup.2.times.pT,
where Rn is the radius of the biopsy tissue 90 (which is
substantially equal to the inner radius of the needle for taking
the biopsy tissue 90), M is the number of the MRI slices
SI.sub.1-SI.sub.N, St is the slice thickness T of the MRI slices
SI.sub.1-SI.sub.N, Rw is the radius of the planar cylinder 98, and
pT is the height or thickness of the planar cylinder 98
perpendicular to the radius Rw of the planar cylinder 98. The
height tT of the biopsy tissue 90 may be substantially equal to the
slice thickness T multiplied by the number of the MRI slices
SI.sub.1-SI.sub.N. In the invention, the height pT of the planar
cylinder 98 is substantially equal to the slice thickness T, for
example. Accordingly, the planar cylinder 98 may have the height pT
equal to the slice thickness T and the radius Rw equal to the
radius Rn multiplied by the square root of the number of the
registered MRI slices SI.sub.1-SI.sub.N. The radius Rw of the
planner cylinder 98 may be used to define the radius Rm of a moving
window MW in calculating probability maps, e.g., illustrated in
first through sixth embodiments, for a patient (e.g., human). Each
of the biopsy tissue 90, the planar cylinder 98 and the moving
window MW may have a volume at least 2, 3, 5, 10 or 15 times
greater than that of each voxel of the MRI slices SI.sub.1-SI.sub.N
and than that of each voxel of an MRI image 10 from a subject
(e.g., patient) depicted in a step S1 of FIG. 4. In addition,
because the planar cylinder 98 is transformed from the biopsy
tissue 90, the measures of the MRI parameters for the whole biopsy
tissue 90 may be considered as those for the planar cylinder
98.
[0089] Further, each of biopsy tissues provided for pathologist
diagnoses in a subset data, e.g., DB-1 or DB-2, of the big data
database 70 may have a corresponding planar cylinder 98 with its
radius Rw, and data (such as pathologist diagnosis and measures of
imaging parameters) for said each of the biopsy tissues in the
subset data, e.g., DB-1 or DB-2, of the big data database 70 may be
considered as those for the corresponding planar cylinder 98.
Statistically, the moving window MW may be determined with the
radius Rm, perpendicular to a thickness of the moving window MW,
based on the statistical distribution or average of the radii Rw of
the planar cylinders 98 transformed from the volumes of the biopsy
tissues provided for the pathologist diagnoses in the subset data,
e.g., DB-1 or DB-2, of the big data database 70. In the invention,
each of the biopsy tissues provided for the pathologist diagnoses
in the subset data, e.g., DB-1 or DB-2, of the big data database
70, for example, may have a volume, i.e., VOI, substantially equal
to the volume of the moving window MW to be used in calculating one
or more probability maps. In other words, the volume of the biopsy
tissue, i.e., VOI, defines the size (e.g., the radius Rm) of the
moving window MW to be used in calculating one or more probability
maps.
[0090] Each of the prostate biopsy tissues provided for the
pathologist diagnoses in the subset data DB-1 may be referred to
the illustration of the biopsy tissue 90. In the column W of the
subset data DB-1, the diameter of each of the prostate biopsy
tissues may be referred to the illustration of the diameter D1 of
the biopsy tissue 90. The MRI slices registered to the respective
regions, portions, locations or volumes of each of the prostate
biopsy tissues provided for the pathologist diagnoses in the subset
data DB-1 may be referred to the illustration of the MRI slices
SI.sub.1-SI.sub.N registered to the respective regions, portions,
locations or volumes of the biopsy tissue 90. The measures of the
MRI parameters for each of the prostate biopsy tissues, i.e., for
each of the corresponding planar cylinders 98, in the respective
columns A-O of the subset data DB-1 may be calculated as the
measures of the MRI parameters for the whole biopsy tissue 90,
i.e., for the planar cylinder 98 transformed from the volume of the
biopsy tissue 90, are calculated. In the column Z of the subset
data DB-1, the MRI slices registered to the respective regions,
portions, locations or volumes of each of the prostate biopsy
tissues may have the same area resolution, which may be referred to
the illustration of the area resolution of the MRI slices
SI.sub.1-SI.sub.N registered to the respective regions, portions,
locations or volumes of the biopsy tissue 90. In the column AA of
the subset data DB-1, the MRI slices registered to the respective
regions, portions, locations or volumes of each of the prostate
biopsy tissues may have the same slice thickness, which may be
referred to the illustration of the slice thickness T of the MRI
slices SI.sub.1-SI.sub.N.
[0091] In the column S of the subset data DB-1, the percentage of
cancer for the whole volume of the prostate biopsy tissue in each
of all or some of the data sets may be replaced by the percentage
of cancer for a partial volume of the prostate biopsy tissue; a MRI
slice is imaged for and registered to at least a portion of the
volume of the prostate biopsy tissue. In this case, the MRI
parameters, in the columns A-O of the subset data DB-1, that are in
said each of all or some of the data sets are measured for a ROI of
the MRI slice registered to the partial volume of the prostate
biopsy tissue. The ROI of the MRI slice covers or overlaps multiple
voxels in the MRI slice, and each of the MRI parameters for the ROI
of the MRI slice may be measured by summing values of said each of
the MRI parameters for the voxels weighed or multiplied by
respective percentages of areas, overlapping with the respective
voxels in the ROI of the MRI slice, occupying the ROI of the MRI
slice. Measures for the MRI parameters for the ROI of the MRI slice
may be derived from different parameter maps registered to the
partial volume of the prostate biopsy tissue. In an alternative
example, the measures for some of the MRI parameters for the ROI of
the MRI slice may be derived from different parameter maps
registered to the partial volume of the prostate biopsy tissue, and
the measures for the others may be derived from the same parameter
map registered to the partial volume of the prostate biopsy
tissue.
[0092] Each of the breast biopsy tissues provided for the
pathologist diagnoses in the subset data DB-2 may be referred to
the illustration of the biopsy tissue 90. In the column AC of the
subset data DB-2, the diameter of each of the breast biopsy tissues
may be referred to the illustration of the diameter D1 of the
biopsy tissue 90. The MRI slices registered to the respective
regions, portions, locations or volumes of each of the breast
biopsy tissues provided for the pathologist diagnoses in the subset
data DB-2 may be referred to the illustration of the MRI slices
SI.sub.1-SI.sub.N registered to the respective regions, portions,
locations or volumes of the biopsy tissue 90. The measures of the
MRI parameters for each of the breast biopsy tissues, i.e., for
each of the corresponding planar cylinders 98, in the respective
columns A-O, R, and S of the subset data DB-2 may be calculated as
the measures of the MRI parameters for the whole biopsy tissue 90,
i.e., for the planar cylinder 98 transformed from the volume of the
biopsy tissue 90, are calculated. In the column AF of the subset
data DB-2, the MRI slices registered to the respective regions,
portions, locations or volumes of each of the breast biopsy tissues
may have the same area resolution, which may be referred to the
illustration of the area resolution of the MRI slices
SI.sub.1-SI.sub.N registered to the respective regions, portions,
locations or volumes of the biopsy tissue 90. In the column AG of
the subset data DB-2, the MRI slices registered to the respective
regions, portions, locations or volumes of each of the breast
biopsy tissues may have the same slice thickness, which may be
referred to the illustration of the slice thickness T of the MRI
slices SI.sub.1-SI.sub.N.
[0093] In the column AB of the subset data DB-2, the percentage of
cancer for the whole volume of the breast biopsy tissue in each of
all or some of the data sets may be replaced by the percentage of
cancer for at least a portion of the volume of the breast biopsy
tissue; a MRI slice is imaged for and registered to the partial
volume of the breast biopsy tissue. In this case, the MRI
parameters, in the columns A-O, R, and S of the subset data DB-2,
that are in said each of all or some of the data sets are measured
for a ROI of the MRI slice registered to the partial volume of the
breast biopsy tissue. The ROI of the MRI slice covers or overlaps
multiple voxels in the MRI slice, and each of the MRI parameters
for the ROI of the MRI slice may be measured by summing values of
said each of the MRI parameters for the voxels weighed or
multiplied by respective percentages of areas, overlapping with the
respective voxels in the ROI of the MRI slice, occupying the ROI of
the MRI slice. Measures for the MRI parameters for the ROI of the
MRI slice may be derived from different parameter maps registered
to the partial volume of the breast biopsy tissue. In an
alternative example, the measures for some of the MRI parameters
for the ROI of the MRI slice may be derived from different
parameter maps registered to the partial volume of the breast
biopsy tissue, and the measures for the others may be derived from
the same parameter map registered to the partial volume of the
breast biopsy tissue.
[0094] In an alternative example, the biopsied tissue 90 may be
obtained by a needle with a square through hole therein. In this
case, the biopsied tissue 90 may have a longitudinal shape with a
square-shaped cross-section having a width Wb (which is
substantially equal to an inner width of the needle, i.e., the
width of the square through hole of the needle) and a height Ht
(which is substantially equal to, e.g., the slice thickness T
multiplied by the number of the MRI slices SI.sub.1-SI.sub.N). The
volume of the biopsied tissue 90 may be transformed into a flat
square FS with a width Wf and a thickness or height fT. The flat
square FS, having a volume the same or about the same as the volume
of the biopsied tissue 90 (or Volume of Interest (VOI), which may
be the height Ht multiplied by the square of the width Wb), may be
defined by the following formula:
Wb.sup.2.times.M.times.St=Wf.sup.2.times.fT, where Wb is the width
of the biopsy tissue 90, M is the number of the MRI slices
SI.sub.1-SI.sub.N, St is the slice thickness T of the MRI slices
SI.sub.1-SI.sub.N, Wf is the width of the flat square FS, and fT is
the height or thickness of the flat square FS perpendicular to the
width Wf of the flat square FS. In the invention, the height or
thickness fT of the flat square FS is substantially equal to the
slice thickness T, for example. Accordingly, the flat square FS may
have the height or thickness fT equal to the slice thickness T and
the width Wf equal to the width Wb multiplied by the square root of
the number of the registered MRI slices SI.sub.1-SI.sub.N. In the
case of the moving window MW with a square shape, the width Wf of
the flat square FS may be used to define the width of the moving
window MW in calculating probability maps. Each of the biopsy
tissue 90, the flat square FS and the square moving window MW may
have a volume at least 2, 3, 5, 10 or 15 times greater than that of
each voxel of the MRI slices SI.sub.1-SI.sub.N and than that of
each voxel of an MRI image, e.g., 10 from a subject (e.g., patient)
depicted in a step S1 of FIG. 4. Further, each of biopsy tissues
provided for pathologist diagnoses in a subset data of the big data
database 70 may have a corresponding flat square FS with its width
Wf, and data (such as pathologist diagnosis and measures of imaging
parameters) for said each of the biopsy tissues in the subset data
of the big data database 70 may be considered as those for the
corresponding flat square FS.
[0095] Description of Area Resolution and Voxels of a Single MRI
Slice:
[0096] In the invention, an area resolution of a single MRI slice
such as single slice MRI image 10 shown in FIG. 5 or 18 is a field
of view (FOV) of the single MRI slice divided by the number of all
voxels in the FOV of the single MRI slice. Each of the voxels of
the single MRI slice may have a pixel (or pixel plane),
perpendicular to the slice thickness direction of the single MRI
slice, having a square area with the same four side lengths.
[0097] Description of Moving Window and Probability Map:
[0098] Any probability map in the invention may be composed of
multiple computation voxels with the same size, which are basic
units of the probability map. The size of the computation voxels
used to compose the probability map may be defined based on the
size of the moving window MW, which is determined or defined based
on information data associated with the biopsy tissues provided for
the pathologist diagnoses in the subset data, e.g., DB-1 or DB-2,
of the big data database 70. The information data, for example, may
include the radii Rw of planar cylinders 98 transformed from the
volumes of the biopsy tissues. In addition, each of the computation
voxels of the probability map may have a volume or size equal to,
greater than or less than that of any voxel in a single MRI slice,
such as MRI image 10 shown in FIG. 5 or 18, depicted in steps S1-S6
of FIG. 4.
[0099] The moving window MW may have various shapes, such as a
circular shape, a square shape, a rectangular shape, a hexagonal
shape, or an octagonal shape. In the invention, referring to FIG.
3A, the moving window MW is a circular moving window 2 with a
radius Rm, for example. The radius Rm of the circular moving window
2 may be calculated, determined, or defined based on the
statistical distribution or average of the radii Rw of planar
cylinders 98 obtained from biopsy tissues associated with a subset
data, e.g., DB-1 or DB-2, of the big data database 70. For example,
in the first embodiment of the invention, the radius Rm of the
circular moving window 2 may be calculated, determined or defined
based on the statistical distribution or average of the radii Rw of
the planar cylinders 98 obtained from the prostate biopsy tissues
associated with the subset data DB-1; the approach to obtain the
radius Rw of the planar cylinder 98 from the biopsy tissue 90 may
be applied to obtain the radii Rw of the planar cylinders 98 from
the prostate biopsy tissues associated with the subset data DB-1.
In the third embodiment of the invention, the radius Rm of the
circular moving window 2 may be calculated, determined or defined
based on the statistical distribution or average of the radii Rw of
the planar cylinders 98 obtained from the breast biopsy tissues
associated with the subset data DB-2; the approach to obtain the
radius Rw of the planar cylinder 98 from the biopsy tissue 90 may
be applied to obtain the radii Rw of the planar cylinders 98 from
the breast biopsy tissues associated with the subset data DB-2.
[0100] Referring to FIG. 3A, 3B or 3C, a square 4 having its four
vertices lying on the circular moving window 2, i.e., the biggest
square 4 inscribed in the circular moving window 2, is defined and
divided into multiple small units or grids 6. The small grids 6 may
be n.sup.2 small squares each having a width Wsq, where n is an
integer, such as 2, 3, 4, 5, 6, or more than 6. Based on the size
(e.g., the width Wsq) and shape of the divided squares 6, the size
and shape of the computation voxels used to compose the probability
map may be defined. In other words, each of the computation voxels
used to compose the probability map, for example, may be defined as
a square with the width Wsq and a volume the same or about the same
as that of each square 6 based on the radius Rm of the circular
moving window 2 and the number of the squares 6 in the circular
moving window 2, i.e., based on the width Wsq of the squares 6 in
the circular moving window 2.
[0101] The circular moving window 2 in FIG. 3A is shown with a
two-by-two square array in the square 4, each square 6 of which has
the same area (i.e., a quarter of the square 4). In FIG. 3A, the
four non-overlapped squares 6 have the same width Wsq, which is
equal to the radius Rm of the circular moving window 2 divided by
{square root over (2)}. In the case of the circular moving window 2
having the radius Rm of {square root over (2)} millimeters, each
square 6 may have an area of 1 millimeter by 1 millimeter, that is,
each square 6 has the width Wsq of 1 millimeter.
[0102] In an alternative example, referring to FIG. 3B, the square
4 may have a three-by-three square array, each square 6 of which
has the same area (i.e., a ninth of the square 4); the nine
non-overlapped squares 6 have the same width Wsq, which is equal to
the radius Rm of the circular moving window 2 divided by 2/3
{square root over (2)}. In an alternative example, referring to
FIG. 3C, the square 4 may have a four-by-four square array, each
square 6 of which has the same area (i.e., one sixteenth of the
square 4); the sixteen non-overlapped squares 6 have the same width
Wsq, which is equal to the radius Rm of the circular moving window
2 divided by 2 {square root over (2)}.
[0103] Accordingly, the moving window MW (e.g., the circular moving
window 2) may be defined to include four or more non-overlapped
grids 6 having the same square shape, the same size or area (e.g.,
1 millimeter by 1 millimeter), and the same width Wsq, e.g., equal
to, greater than or less than any side length of pixels of voxels
in a single MRI slice, such as MRI image 10 shown in FIG. 5 or 18,
depicted in the steps S1-S3 of FIG. 4. Each of the squares 6, for
example, may have an area less than 25% of that of the moving
window MW and equal to, greater than or less than that of the pixel
of each voxel of the single MRI slice; each of the squares 6, for
example, may have a volume equal to, greater than or less than that
of each voxel of the single MRI slice. In the case of the moving
window MW defined to include four or more non-overlapped squares 6
with the width Wsq, the moving window MW may move across the single
MRI slice at a regular step or interval of a fixed distance of the
width Wsq in the x and y directions so that the computation voxels
of the probability map are defined. A stop of the moving window MW
overlaps with the neighboring stop of the moving window MW.
[0104] Alternatively, the grids 6 may be n rectangles each having a
width Wrec and a length Lrec, where n is an integer, such as 2, 3,
4, 5, 6, 7, 8, or more than 8. Based on the size (e.g., the width
Wrec and the length Lrec) and shape of the divided rectangles 6,
the size and shape of the computation voxels used to compose the
probability map may be defined. In other words, each of the
computation voxels used to compose the probability map, for
example, may be defined as a rectangle with the width Wrec, the
length Lrec, and a volume the same or about the same as that of
each rectangle 6 based on the radius Rm of the circular moving
window 2 and the number of the rectangles 6 in the circular moving
window 2, i.e., based on the width Wrec and length Lrec of the
rectangles 6 in the circular moving window 2. Accordingly, the
moving window MW (e.g., the circular moving window 2) may be
defined to include four or more non-overlapped grids 6 having the
same rectangle shape, the same size or area, the same width Wrec,
e.g., equal to, greater than or less than any side length of pixels
of voxels in a single MRI slice, such as MRI image 10 shown in FIG.
5 or 18, depicted in the steps S1-S3 of FIG. 4, and the same length
Lrec, e.g., equal to, greater than or less than any side length of
the pixels of the voxels in the single MRI slice. Each of the
rectangles 6, for example, may have an area less than 25% of that
of the moving window MW and equal to, greater than or less than
that of the pixel of each voxel of the single MRI slice. Each of
the rectangles 6, for example, may have a volume equal to, greater
than or less than that of each voxel of the single MRI slice. In
the case of the moving window MW defined to include four or more
non-overlapped rectangles 6 with the width Wrec and the length
Lrec, the moving window MW may move across the single MRI slice at
a regular step or interval of a fixed distance of the width Wrec in
the x direction and at a regular step or interval of a fixed
distance of the length Lrec in the y direction so that the
computation voxels of the probability map are defined. A stop of
the moving window MW overlaps with the neighboring stop of the
moving window MW.
[0105] In the case of the moving window MW with a square shape, the
square moving window MW may be determined with a width Wsm based on
the statistical distribution or average of the widths Wf of flat
squares FS obtained from biopsy tissues associated with a subset
data of the big data database 70. The square moving window MW may
be divided into the aforementioned small grids 6. In this case,
each of the computation voxels of the probability map, for example,
may be defined as a square with the width Wsq and a volume the same
or about the same as that of each square 6 based on the width Wsm
of the square moving window MW and the number of the squares 6 in
the square moving window MW, i.e., based on the width Wsq of the
squares 6 in the square moving window MW. Alternatively, each of
the computation voxels of the probability map may be defined as a
rectangle with the width Wrec, the length Lrec, and a volume the
same or about the same as that of each rectangle 6 based on the
width Wsm of the square moving window MW and the number of the
rectangles 6 in the square moving window MW, i.e., based on the
width Wrec and length Lrec of the rectangles 6 in the square moving
window MW.
[0106] Description of Classifier CF:
[0107] The classifier CF for an event, such as biopsy-diagnosed
tissue or tumor characteristic for, e.g., specific cancerous cells
or occurrence of prostate cancer or breast cancer, may be created
or established based on a subset (e.g., the subset data DB-1 or
DB-2 or the aforementioned subset data established for generating
the voxelwise probability map of brain cancer, liver cancer, lung
cancer, rectal cancer, sarcomas, cervical cancer, or cancer
metastasis to any organ such as liver, bone, and brain) obtained
from the big data database 70. The subset may have all data
associated with the given event from the big data database 70. The
classifier CF may be a Bayesian classifier, which may be created by
performing the following steps: constructing database,
preprocessing parameters, ranking parameters, identifying a
training dataset, and determining posterior probabilities for test
data.
[0108] In the step of constructing database, a first group and a
second group may be determined or selected from a tissue-based or
biopsy-based subset data, such as the aforementioned subset data,
e.g., DB-1 or DB-2, from the big data database 70, and various
variables associated with each of the first and second groups are
obtained from the tissue-based or biopsy-based subset data. The
variables may be MRI parameters in the columns A-O of the subset
data DB-1 or the columns A-O, R, and S of the subset data DB-2.
Alternatively, the variables may be T1 mapping, T2 raw signal, T2
mapping, delta Ktrans, tau, Dt IVIM, fp IVIM, ADC (high b-values),
R*, Ktrans from TM, Ktrans from ETM, Ktrans from SSM, Ve from TM,
Ve from ETM, Ve from SSM, and standard PET.
[0109] The first group, for example, may be associated with a first
data type or feature in a specific column of the subset data DB-1
or DB-2, and the second group may be associated with a second data
type or feature in the specific column of the subset data DB-1 or
DB-2, wherein the specific column of the subset data DB-1 or DB-2
may be one of the columns R-AR of the subset data DB-1 or one of
the columns AA-AX of the subset data DB-2. In a first example, the
first data type is associated with prostate cancer in the column R
of the subset data DB-1, and the second data type is associated
with non-prostate cancer (e.g., normal tissue and benign condition)
in the column R of the subset data DB-1. In a second example, the
first data type is associated with breast cancer in the column AA
of the subset data DB-2, and the second data type is associated
with non-breast cancer (e.g., normal tissue and benign condition)
in the column AA of the subset data DB-2. In the case of the first
group associated with a cancer type (e.g., prostate cancer or
breast cancer) and the second group associated with a non-cancer
type (e.g., non-prostate cancer or non-breast cancer), the cancer
type may include data of interest for a single parameter, such as
malignancy, mRNA expression, etc., and the non-cancer type may
include normal tissue and benign conditions. The benign conditions
may vary based on tissues. For example, the benign conditions for
breast tissues may include fibroadenomas, cysts, etc.
[0110] In a third example, the first data type is associated with
one of Gleason scores 0 through 10, such as Gleason score 5, in the
column T of the subset data DB-1, and the second data type is
associated with the others of Gleason scores 0 through 10, such as
Gleason scores 0 through 4 and 6 through 10, in the column T of the
subset data DB-1. In a fourth example, the first data type is
associated with two or more of Gleason scores 0 through 10, such as
Gleason scores greater than 7, in the column T of the subset data
DB-1, and the second data type is associated with the others of
Gleason scores 0 through 10, such as Gleason scores equal to and
less than 7, in the column T of the subset data DB-1. In a fifth
example, the first data type is associated with the percentage of
cancer in a specific range from a first percent (e.g., 91 percent)
to a second percent (e.g., 100 percent) in the column S of the
subset data DB-1, and the second data type is associated with the
percentage of cancer beyond the specific range in the column S of
the subset data DB-1. In a sixth example, the first data type is
associated with a small cell subtype in the column AE of the subset
data DB-1, and the second data type is associated with a non-small
cell subtype in the column AE of the subset data DB-1. Any event
depicted in the invention may be the above-mentioned first data
type or feature, occurrence of prostate cancer, occurrence of
breast cancer, or a biopsy-diagnosed tissue or tumor characteristic
for, e.g., specific cancerous cells.
[0111] After the step of constructing database is completed, the
step of preprocessing parameters is performed to determine what the
variables are conditionally independent. A technique for
dimensionality reduction may allow reduction of some of the
variables that are conditionally dependent to a single variable.
Use of dimensionality reduction preprocessing of data may allow
optimal use of all valuable information in datasets. The simplest
method for dimensionality reduction may be simple aggregation and
averaging of datasets. In one example, aggregation may be used for
dynamic contrast-enhanced MRI (DCE-MRI) datasets. Ktrans and Ve
measures from various different pharmacokinetic modeling techniques
may be averaged to reduce errors and optimize sensitivity to tissue
change.
[0112] For the variables, averaging and subtraction may be used to
consolidate measures. Accordingly, five or more types of parameters
may be selected or obtained from the variables. The five or more
selected parameters are conditionally independent and may include
T1 mapping, T2 mapping, delta Ktrans (obtained by subtracting
"Ktrans from Tofts Model" from "Ktrans from Shutterspeed Model"),
tau, Dt IVIM, fp IVIM, R*, average Ve, and average Ktrans in the
respective columns A, C-G, J, P, and Q of the subset data DB-1 or
DB-2. Alternatively, the five or more selected parameters may
include T1 mapping, T2 mapping, delta Ktrans, tau, fp IVIM, R*,
average Ve, average Ktrans, standard PET, and a parameter D
obtained by averaging Dt IVIM and ADC (high b-values), wherein the
parameter D is conditionally independent of every other selected
parameter.
[0113] After the step of preprocessing parameters is complete, the
step of ranking parameters is performed to determine the optimal
ones of the five or more selected parameters for use in
classification, e.g., to find the optimal parameters that are most
likely to give the highest posterior probabilities, so that a rank
list of the five or more selected parameters is obtained. A
filtering method, such as t-test, may be to look for an optimal
distance between the first group (indicated by GR1) and the second
group (indicated by GR2) for every one of the five or more selected
parameters, as shown in FIG. 23. FIG. 23 shows two Gaussian curves
of two given different groups (i.e., the first and second groups
GR1 and GR2) with respect to parameter measures. In FIG. 23, X axis
is values for a specific parameter, and Y axis is the number of
tissue biopsies.
[0114] Four different criteria may be computed for ranking the five
or more selected parameters. The first criterion is the p-value
derived from a t-test of the hypothesis that the two features sets,
corresponding to the first group and the second group, coming from
distributions with equal means. The second criterion is the mutual
information (MI) computed between the classes and each of the first
and second groups. The last two criteria are derived from the
minimum redundancy maximum relevance (mRMR) selection method.
[0115] In the step of identifying a training dataset, a training
dataset of the first group and the second group is identified based
on the rank list after the step of ranking parameters, and thereby
the Bayesian classifier may be created based on the training
dataset of the first group and the second group. In the step of
determining posterior probabilities for test data, the posterior
probabilities for the test data may be determined using the
Bayesian classifier. Once the Bayesian classifier is created, the
test data may be applied to predict posterior probabilities for
high resolution probability maps.
[0116] In an alternative example, the classifier CF may be a neural
network (e.g., probabilistic neural network, single-layer feed
forward neural network, multi-layer perception neural network, or
radial basis function neural network), a discriminant analysis, a
decision tree (e.g., classification and regression tree, quick
unbiased and efficient statistical tree, Chi-square automatic
interaction detector, C5.0, or random forest decision tree), an
adaptive boosting, a K-nearest neighbors algorithm, or a support
vector machine. In this case, the classifier CF may be created
based on information associated with the various MRI parameters for
the ROIs 94 of the MRI slices SI.sub.1-SI.sub.N registered to each
of the biopsy tissues depicted in the subset data DB-1 or DB-2.
First Embodiment
[0117] After the big data database 70 and the classifier CF are
created or constructed, a (voxelwise) probability map (i.e., a
decision data map), composed of multiple computation voxels with
the same size, for an event (i.e., a decision-making
characteristic) may be generated or constructed for, e.g.,
evaluating or determining the health status of a subject such as
healthy individual or patient, the physical condition of an organ
or other structure inside the subject's body, or the subject's
progress and therapeutic effectiveness by sequentially performing
six steps S1 through S6 illustrated in FIG. 4. The steps S1-S6 may
be performed based on the moving window MW with a suitable shape
such as a circular shape, a square shape, a rectangular shape, a
hexagonal shape, or an octagonal shape. The moving window MW is
selected for a circular shape, i.e., the circular moving window 2,
to perform the steps S1-S6 as mentioned in the following
paragraphs. Referring to FIG. 4, in the step S1, a MRI image 10
(single slice) shown in FIG. 5 is obtained from the subject by a
MRI device or system. The MRI image 10 (i.e., a molecular image) is
composed of multiple voxels in its field of view (FOV) to show an
anatomical region of the subject, such as a prostate. In an
alternative embodiment, the MRI image 10 may show another
anatomical region of the subject, such as a breast, brain, liver,
lung, cervix, bone, sarcomas, metastatic lesion or site, capsule
around the prostate, pelvic lymph nodes around the prostate, or
lymph node.
[0118] In the step S2, a desired or anticipated region 11 is
determined on the MRI image 10, and a computation region 12 for the
probability map is set in the desired or anticipated region 11 of
the MRI image 10 and defined with the computation voxels based on
the size (e.g., the radius Rm) of the moving window 2 and the size
and shape of the small grids 6 in the moving window 2 such as the
width Wsq of the small squares 6 or the width Wrec and the length
Lrec of the small rectangles 6. A side length of the computation
region 12 in the x direction, for example, may be calculated by
obtaining a first maximum positive integer of a side length of the
desired or anticipated region 11 in the x direction divided by the
width Wsq of the small squares 6 in the moving window 2, and
multiplying the width Wsq by the first maximum positive integer; a
side length of the computation region 12 in the y direction may be
calculated by obtaining a second maximum positive integer of a side
length of the desired or anticipated region 11 in the y direction
divided by the width Wsq of the small squares 6 in the moving
window 2, and multiplying the width Wsq by the second maximum
positive integer. Alternatively, a side length of the computation
region 12 in the x direction may be calculated by obtaining a first
maximum positive integer of a side length of the desired or
anticipated region 11 in the x direction divided by the width Wrec
of the small rectangles 6 in the moving window 2, and multiplying
the width Wrec by the first maximum positive integer; a side length
of the computation region 12 in the y direction may be calculated
by obtaining a second maximum positive integer of a side length of
the desired or anticipated region 11 in the y direction divided by
the length Lrec of the small rectangles 6 in the moving window 2,
and multiplying the length Lrec by the second maximum positive
integer. The computation region 12 may cover at least 10, 25, 50,
80, 90 or 95 percent of the FOV of the MRI image 10, which may
include the anatomical region of the subject. The computation
region 12, for example, may be shaped like a parallelogram such as
square or rectangle.
[0119] The size and shape of the computation voxels used to compose
the probability map, for example, may be defined based on then step
size or radius Rm of the moving window 2, wherein the radius Rm is
calculated based on, e.g., the statistical distribution or average
of the radii Rw of the planar cylinders 98 transformed from the
volumes of the prostate biopsy tissues provided for the pathologist
diagnoses depicted in the subset data DB-1, as illustrated in the
section of "description of moving window and probability map." Each
of the computation voxels, for example, may be defined as a square
with the width Wsq in the case of the moving window 2 defined to
include the small squares 6 each having the width Wsq.
Alternatively, each of the computation voxels may be defined as a
rectangle with the width Wrec and the length Lrec in the case of
the moving window 2 defined to include the small rectangles 6 each
having the width Wrec and the length Lrec.
[0120] A step for abbreviated search functions (such as looking for
one or more specific areas of the MRI image 10 where diffusion
signals are above a certain signal value) may be performed between
the steps S1 and S2, and the computation region 12 may cover the
one or more specific areas of the MRI image 10. For clear
illustration of the following steps, FIGS. 6A and 6B show the
computation region 12 without the MRI image 10. Referring to FIG.
6A, in the step S3 of FIG. 4, after the computation region 12 and
the size and shape of the computation voxels of the probability map
are defined or determined, the stepping of the moving window 2 and
the overlapping between two neighboring stops of the moving window
2 are determined. In the step S3, the moving window 2, illustrated
in FIG. 3A, 3B or 3C for example, moves across the computation
region 12 at a regular step or interval of a fixed distance in the
x and y directions, and measures of specific MRI parameters (each,
for example, may be the mean or a weighted mean) for each stop of
the moving window 2 for the computation region 12 may be derived or
obtained from the MRI image 10 or a registered imaging dataset
including, e.g., the MRI image 10 and different MRI parameter maps
registered to the MRI image 10. In an alternative example, the
measures for some of the specific MRI parameters for each stop of
the moving window 2 may be derived from different MRI parameter
maps registered to the MRI image 10, and the measures for the
others may be derived from the same parameter map registered to the
MRI image 10. The fixed distance in the x direction may be
substantially equal to the width Wsq in the case of the computation
voxels defined as the squares with the width Wsq or may be
substantially equal to the width Wrec in the case of the
computation voxels defined as the rectangles with the width Wrec
and the length Lrec. The fixed distance in the y direction may be
substantially equal to the width Wsq in the case of the computation
voxels defined as the squares with the width Wsq or may be
substantially equal to the length Lrec in the case of the
computation voxels defined as the rectangles with the width Wrec
and the length Lrec.
[0121] For more elaboration, referring to FIGS. 6A and 6B, the
moving window 2 may start at a corner Cx of the computation region
12. In the beginning of moving the moving window 2 across the
computation region 12, the square 4 inscribed in the moving window
2 may have a corner Gx aligned with the corner Cx of the
computation region 12. In other words, the square 4 inscribed in
the moving window 2 has an upper side 401 aligned with an upper
side 121 of the computation region 12 and a left side 402 aligned
with a left side 122 of the computation region 12. Two neighboring
stops of the moving window 2 that are shifted from each other by
the fixed distance in the x or y direction partially overlap each
other, and the ratio of the overlap of the two neighboring stops of
the moving window 2 to the area of any one of the two neighboring
stops of the moving window 2 may range from, equal to or greater
than 50 percent up to, equal to or less than 99 percent.
[0122] The specific MRI parameters for each stop of the moving
window 2 may include T1 mapping, T2 raw signal, T2 mapping, delta
Ktrans, tau, Dt IVIM, fp IVIM, ADC (high b-values), nADC (high
b-values), R*, Ktrans from TM, ETM and SSM, and Ve from TM and SSM,
which may be referred to the types of the MRI parameters in the
columns A-O of the subset data DB-1, respectively. Alternatively,
the specific MRI parameters for each stop of the moving window 2
may include four or more of the following: T1 mapping, T2 raw
signal, T2 mapping, Ktrans from TM, ETM, and SSM, Ve from TM and
SSM, delta Ktrans, tau, ADC (high b-values), nADC (high b-values),
Dt IVIM, fp IVIM, and R*. The specific MRI parameters of different
modalities may be obtained from registered (multi-parametric) image
sets (or the MRI parameter maps in the registered
(multi-parametric) image dataset), and rigid and nonrigid standard
registration techniques may be used to get each section of anatomy
into the same exact coordinate location on each of the registered
(multi-parametric) image sets (or on each of the MRI parameter
maps).
[0123] Referring to FIG. 7A, the moving window 2 at each stop may
cover or overlap multiple voxels, e.g., 14a through 14f, in the
computation region 12, of the MRI image 10. A MRI parameter such as
T1 mapping for each stop of the moving window 2 may be calculated
or measured by summing values of the MRI parameter for the voxels
14a-14f weighed or multiplied by the respective percentages of
areas B1, B2, B3, B4, B5 and B6, overlapping with the respective
voxels 14a-14f in the moving window 2, occupying the moving window
2. By this way, other MRI parameters (e.g., those in the columns
B-O of the subset data DB-1) for each stop of the moving window 2
are measured. Taking an example of T1 mapping, in the case of the
moving window 2 at a certain stop, values of T1 mapping for the
voxels 14a-14f and the percentages of the areas B1-B6 occupying the
moving window 2 are assumed as shown in FIG. 7B. A measure, i.e.,
1010.64, of T1 mapping for the stop of the moving window 2 may be
obtained or calculated by summing (1) the value, i.e., 1010, of T1
mapping for the voxel 14a multiplied by the percentage, i.e., 6%,
of the area B1, overlapping with the voxel 14a in the moving window
2, occupying the moving window 2, (2) the value, i.e., 1000, of T1
mapping for the voxel 14b multiplied by the percentage, i.e., 38%,
of the area B2, overlapping with the voxel 14b in the moving window
2, occupying the moving window 2, (3) the value, i.e., 1005, of T1
mapping for the voxel 14c multiplied by the percentage, i.e., 6%,
of the area B3, overlapping with the voxel 14c in the moving window
2, occupying the moving window 2, (4) the value, i.e., 1020, of T1
mapping for the voxel 14d multiplied by the percentage, i.e., 6%,
of the area B4, overlapping with the voxel 14d in the moving window
2, occupying the moving window 2, (5) the value, i.e., 1019, of T1
mapping for the voxel 14e multiplied by the percentage, i.e., 38%,
of the area B5, overlapping with the voxel 14e in the moving window
2, occupying the moving window 2, and (6) the value, i.e., 1022, of
T1 mapping for the voxel 14f multiplied by the percentage, i.e.,
6%, of the area B6, overlapping with the voxel 14f in the moving
window 2, occupying the moving window 2. Alternatively, the measure
of each of the specific MRI parameters for each stop of the moving
window 2 may be the Gaussian weighted average of measures, for said
each of the specific MRI parameters, for the voxels, e.g., 14a-14f
of the MRI image 10 overlapping with said each stop of the moving
window 2.
[0124] The registered imaging dataset may be created for the
subject to include, e.g., multiple registered MRI slice images
(including, e.g., MRI image 10) and/or corresponding MRI parameters
obtained from various equipment, machines, or devices or from a
defined time-point (e.g., specific date) or time range (e.g.,
within five days after treatment). Each of the MRI parameters in
the subject's registered imaging dataset requires alignment or
registration. The registration can be done by, for examples, using
unique anatomical marks, structures, tissues, geometry, and/or
shapes or using mathematical algorithms and computer pattern
recognition. The measures of the specific imaging parameters for
each stop of the moving window 2, for example, may be obtained from
the registered imaging dataset for the subject.
[0125] Referring to FIG. 4, in the step S4 (optional), the
reduction of the MRI parameters may be performed using, e.g.,
subset selection, aggregation, and dimensionality reduction so that
a parameter set for each stop of the moving window 2 is obtained.
The parameter set for each stop of the moving window 2 may include
the measures for some of the specific MRI parameters from the step
S3 (e.g., T1 mapping, T2 mapping, delta Ktrans, tau, Dt IVIM, fp
IVIM, and R*) and values of average Ktrans (obtained by averaging
Ktrans from TM, Ktrans from ETM, and Ktrans from SSM) and average
Ve (obtained by averaging Ve from TM and Ve from SSM). T2 raw
signal, ADC (high b-values), and nADC (high b-values) are not
selected into the parameter set because the three MRI parameters
are not determined to be conditionally independent. T1 mapping, T2
mapping, delta Ktrans, tau, Dt IVIM, fp IVIM, and R* are selected
into the parameter set because the seven MRI parameters are
determined to be conditionally independent. Performing the step S4
may reduce parameter noise, create new parameters, and assure
conditional independence needed for (Bayesian) classification
described in the step S5.
[0126] In the step S5, the parameter set for each stop of the
moving window 2 from the step S4 (or the measures of some or all of
the specific MRI parameters for each stop of the moving window 2
from the step S3) may be matched to a biomarker library or the
classifier CF for an event (e.g., the first data type or feature
depicted in the section of "description of classifier CF", or
biopsy-diagnosed tissue characteristic for, e.g., specific
cancerous cells or occurrence of prostate or breast cancer) created
based on data associated with the event from the subset data DB-1.
Accordingly, a probability PW of the event for each stop of the
moving window 2 is obtained. In other words, the probability PW of
the event for each stop of the moving window 2 may be obtained
based on the parameter set (from the step S4) or the measures of
some or all of the specific MRI parameters (from the step S3) for
said each stop of the moving window 2 to match a matching dataset
from the established or constructed biomarker library or classifier
CF. The biomarker library or classifier CF, for example, may
contain population-based information of MRI imaging data and other
information such as clinical and demographic data for the event. In
the invention, the probability PW of the event for each stop of the
moving window 2 is assumed to be that for the square 4 inscribed in
said each stop of the moving window 2.
[0127] In the step S6, probabilities PVs of the event may be
computed for the respective computation voxels based on the
probabilities PWs of the event for the stops of the moving window
2, and the probabilities PVs of the event for the respective
computation voxels form the probability map. The probability map
may be obtained in a short time (such as 10 minutes or 1 hour)
after the MRI slice 10 obtained. The moving window 2 may be defined
to include at least four squares 6, as shown in FIG. 3A, 3B or 3C.
Each of the squares 6 within the moving window 2, for example, may
have an area less than 25% of that of the moving window 2. Two
neighboring stops of the moving window 2, for example, may have an
overlapped region with an area ranging from 20% to 99% of that of
any one of the two neighboring stops of the moving window 2, and
some of the squares 6 inside each of the two neighboring stops of
the moving window 2 may be within the overlapped region of the two
neighboring stops of the moving window 2. Alternatively, two
neighboring stops of the moving window 2 may have an overlapped
region with an area ranging from 1% to 20% of that of any one of
the two neighboring stops of the moving window 2.
[0128] The square 4 inscribed in the moving window 2 with the
radius Rm is divided into, e.g., four small squares 6 each having
width Wsq as shown in FIG. 3A, and in the step S2, the computation
region 12 for the probability map is defined with, e.g., nine
computation voxels V1 through V9 shown in FIG. 8 based on the width
Wsq of the four small squares 6 in the moving window 2. Each of the
nine computation voxels V1-V9 used to compose the probability map
is defined as a square with the width Wsq. Next, referring to FIGS.
9B, 9D, 9F and 9H, the moving window 2 moves across the computation
region 12 at a regular step or interval of a fixed distance in the
x and y directions, and measures of the specific MRI parameters for
four stops P.sub.1-1, P.sub.1-2, P.sub.2-1 and P.sub.2-2 of the
moving window 2 are obtained from the MRI image 10 or the
registered imaging dataset. In the example, the fixed distance is
substantially equal to the width Wsq. Referring to FIGS. 9A and 9B,
four small squares 6a, 6b, 6c and 6d, i.e., the four squares 6,
within the square 4 inscribed in the stop P.sub.1-1 of the moving
window 2 overlap or cover the four computation voxels V1, V2, V4
and V5, respectively, and each of the squares 6a, 6b, 6c and 6d has
an area less than 25% of that of the stop P.sub.1-1 of the moving
window 2. Referring to FIGS. 9C and 9D, four small squares 6e, 6f,
6g and 6h, i.e., the four squares 6, within the square 4 inscribed
in the stop P.sub.1-2 of the moving window 2 overlap or cover the
four computation voxels V2, V3, V5 and V6, respectively, and each
of the squares 6e, 6f, 6g and 6h has an area less than 25% of that
of the stop P.sub.1-2 of the moving window 2. Referring to FIGS. 9E
and 9F, four small squares 6i, 6j, 6k and 6l, i.e., the four
squares 6, within the square 4 inscribed in the stop P.sub.2-1 of
the moving window 2 overlap or cover the four computation voxels
V4, V5, V7 and V8, respectively, and each of the squares 6i, 6j, 6k
and 6l has an area less than 25% of that of the stop P.sub.2-1 of
the moving window 2. Referring to FIGS. 9G and 9H, four small
squares 6m, 6n, 6o and 6p, i.e., the four squares 6, within the
square 4 inscribed in the stop P.sub.2-2 of the moving window 2
overlap or cover the four computation voxels V5, V6, V8 and V9,
respectively, and each of the squares 6m, 6n, 6o and 6p has an area
less than 25% of that of the stop P.sub.2-2 of the moving window 2.
For details about the squares 6a-6p, please refer to the squares 6
illustrated in FIG. 3A.
[0129] After the measures of the specific MRI parameters for the
stops P.sub.1-1, P.sub.1-2, P.sub.2-1 and P.sub.2-2 of the moving
window 2 are obtained, the step S5 is performed to obtain the
probabilities PWs of the event for the respective stops P.sub.1-1,
P.sub.1-2, P.sub.2-1 and P.sub.2-2 of the moving window 2. The
probabilities PWs of the event for the four stops P.sub.1-1,
P.sub.1-2, P.sub.2-1 and P.sub.2-2 of the moving window 2, for
example, are 0.8166, 0.5928, 0.4407 and 0.5586, respectively. In
the example, the four probabilities PWs of the event for the four
stops P.sub.1-1, P.sub.1-2, P.sub.2-1 and P.sub.2-2 of the moving
window 2 are assumed to be those for the four squares 4 inscribed
in the respective stops P.sub.1-1, P.sub.1-2, P.sub.2-1 and
P.sub.2-2 of the moving window 2, respectively. In other words, the
four probabilities of the event for the four squares 4 inscribed in
the four stops P.sub.1-1, P.sub.1-2, P.sub.2-1 and P.sub.2-2 of the
moving window 2 are 0.8166, 0.5928, 0.4407 and 0.5586,
respectively.
[0130] Next, optimal probabilities of the event for the computation
voxels V1-V9 are determined based on the probabilities PWs of the
event for the respective stops P.sub.1-1, P.sub.1-2, P.sub.2-1 and
P.sub.2-2 of the moving window 2. FIG. 10A shows example initial
probabilities for computation voxels in accordance with an
embodiment of the present invention. FIG. 10B shows example updated
probabilities for the computation voxels, and FIG. 10C shows
example optimal probabilities for the computation voxels in
accordance with an embodiment of the present invention. In an
embodiment, the determination of the optimal probabilities could be
an averaging of the moving window values.
[0131] In an alternative example, the square 4 inscribed in the
moving window 2 with the radius Rm is divided into, e.g., nine
small squares 6 each having width Wsq as shown in FIG. 3B, and in
the step S2, the computation region 12 for the probability map is
defined with, e.g., 36 computation voxels X1 through X36 as shown
in FIG. 11 based on the width Wsq of the nine small squares 6 in
the moving window 2. Each of the 36 computation voxels X1-X36 used
to compose the probability map is defined as a square with the
width Wsq. Next, referring to FIGS. 12B, 12D, 12F, 12H, 13B, 13D,
13F, 13H, 14B, 14D, 14F, 14H, 15B, 15D, 15F, and 15H, the moving
window 2 moves across the computation region 12 at a regular step
or interval of a fixed distance in the x and y directions, and
measures of the specific MRI parameters for sixteen stops
P.sub.1-1, P.sub.1-2, P.sub.1-3, P.sub.1-4, P.sub.2-1, P.sub.2-2,
P.sub.2-3, P.sub.2-4, P.sub.3-1, P.sub.3-2, P.sub.3-3, P.sub.3-4,
P.sub.4-1, P.sub.4-2, P.sub.4-3, and P.sub.4-4 of the moving window
2 are obtained from the MRI image 10 or the registered imaging
dataset. In the example, the fixed distance is substantially equal
to the width Wsq.
[0132] Referring to FIGS. 12A and 12B, nine small squares G1
through G9, i.e., the nine squares 6, within the square 4 inscribed
in the stops P.sub.1-1 of the moving window 2 overlap or cover the
nine computation voxels X1, X2, X3, X7, X8, X9, X13, X14 and X15,
respectively, and each of the squares G1-G9 may have an area less
than 10% of that of the stop P.sub.1-1 of the moving window 2. For
details about the squares G1-G9, please refer to the squares 6
illustrated in FIG. 3B. Referring to FIGS. 12C and 12D, nine small
squares G10 through G18, i.e., the nine squares 6, within the
square 4 inscribed in the stop P.sub.1-2 of the moving window 2
overlap or cover the nine computation voxels X2, X3, X4, X8, X9,
X10, X14, X15 and X16, respectively, and each of the squares
G10-G18 may have an area less than 10% of that of the stop
P.sub.1-2 of the moving window 2. For details about the squares
G10-G18, please refer to the squares 6 illustrated in FIG. 3B.
Referring to FIGS. 12E and 12F, nine small squares G19 through G27,
i.e., the nine squares 6, within the square 4 inscribed in the stop
P.sub.1-3 of the moving window 2 overlap or cover the nine
computation voxels X3, X4, X5, X9, X10, X11, X15, X16 and X17,
respectively, and each of the squares G19-G27 may have an area less
than 10% of that of the stop P.sub.1-3 of the moving window 2. For
details about the squares G19-G27, please refer to the squares 6
illustrated in FIG. 3B. Referring to FIGS. 12G and 12H, nine small
squares G28 through G36, i.e., the nine squares 6, within the
square 4 inscribed in the stop P.sub.1-4 of the moving window 2
overlap or cover the nine computation voxels X4, X5, X6, X10, X11,
X12, X16, X17 and X18, respectively, and each of the squares
G28-G36 may have an area less than 10% of that of the stop
P.sub.1-4 of the moving window 2. For details about the squares
G28-G36, please refer to the squares 6 illustrated in FIG. 3B.
[0133] Referring to FIGS. 13A and 13B, nine small squares G37
through G45, i.e., the nine squares 6, within the square 4
inscribed in the stop P.sub.2-1 of the moving window 2 overlap or
cover the nine computation voxels X7, X8, X9, X13, X14, X15, X19,
X20 and X21, respectively, and each of the squares G37-G45 may have
an area less than 10% of that of the stop P.sub.2-1 of the moving
window 2. For details about the squares G37-G45, please refer to
the squares 6 illustrated in FIG. 3B. Referring to FIGS. 13C and
13D, nine small squares G46 through G54, i.e., the nine squares 6,
within the square 4 inscribed in the stop P.sub.2-2 of the moving
window 2 overlap or cover the nine computation voxels X8, X9, X10,
X14, X15, X16, X20, X21 and X22, respectively, and each of the
squares G46-G54 may have an area less than 10% of that of the stop
P.sub.2-2 of the moving window 2. For details about the squares
G46-G54, please refer to the squares 6 illustrated in FIG. 3B.
Referring to FIGS. 13E and 13F, nine small squares G55 through G63,
i.e., the nine squares 6, within the square 4 inscribed in the stop
P.sub.2-3 of the moving window 2 overlap or cover the nine
computation voxels X9, X10, X11, X15, X16, X17, X21, X22 and X23,
respectively, and each of the squares G55-G63 may have an area less
than 10% of that of the stop P.sub.2-3 of the moving window 2. For
details about the squares G55-G63, please refer to the squares 6
illustrated in FIG. 3B. Referring to FIGS. 13G and 13H, nine small
squares G64 through G72, i.e., the nine squares 6, within the
square 4 inscribed in the stop P.sub.2-4 of the moving window 2
overlap or cover the nine computation voxels X10, X11, X12, X16,
X17, X18, X22, X23 and X24, respectively, and each of the squares
G64-G72 may have an area less than 10% of that of the stop
P.sub.2-4 of the moving window 2. For details about the squares
G64-G72, please refer to the squares 6 illustrated in FIG. 3B.
[0134] Referring to FIGS. 14A and 14B, nine small squares G73
through G81, i.e., the nine squares 6, within the square 4
inscribed in the stop P.sub.3-1 of the moving window 2 overlap or
cover the nine computation voxels X13, X14, X15, X19, X20, X21,
X25, X26 and X27, respectively, and each of the squares G73-G81 may
have an area less than 10% of that of the stop P.sub.3-1 of the
moving window 2. For details about the squares G73-G81, please
refer to the squares 6 illustrated in FIG. 3B. Referring to FIGS.
14C and 14D, nine small squares G82 through G90, i.e., the nine
squares 6, within the square 4 inscribed in the stop P.sub.3-2 of
the moving window 2 overlap or cover the nine computation voxels
X14, X15, X16, X20, X21, X22, X26, X27 and X28, respectively, and
each of the squares G82-G90 may have an area less than 10% of that
of the stop P.sub.3-2 of the moving window 2. For details about the
squares G82-G90, please refer to the squares 6 illustrated in FIG.
3B. Referring to FIGS. 14E and 14F, nine small squares G91 through
G99, i.e., the nine squares 6, within the square 4 inscribed in the
stop P.sub.3-3 of the moving window 2 overlap or cover the nine
computation voxels X15, X16, X17, X21, X22, X23, X27, X28 and X29,
respectively, and each of the squares G91-G99 may have an area less
than 10% of that of the stop P.sub.3-3 of the moving window 2. For
details about the squares G91-G99, please refer to the squares 6
illustrated in FIG. 3B. Referring to FIGS. 14G and 14H, nine small
squares G100 through G108, i.e., the nine squares 6, within the
square 4 inscribed in the stop P.sub.3-4 of the moving window 2
overlap or cover the nine computation voxels X16, X17, X18, X22,
X23, X24, X28, X29 and X30, respectively, and each of the squares
G100-G108 may have an area less than 10% of that of the stop
P.sub.3-4 of the moving window 2. For details about the squares
G100-G108, please refer to the squares 6 illustrated in FIG.
3B.
[0135] Referring to FIGS. 15A and 15B, nine small squares G109
through G117, i.e., the nine squares 6, within the square 4
inscribed in the stop P.sub.4-1 of the moving window 2 overlap or
cover the nine computation voxels X19, X20, X21, X25, X26, X27,
X31, X32 and X33, respectively, and each of the squares G109-G117
may have an area less than 10% of that of the stop P.sub.4-1 of the
moving window 2. For details about the squares G109-G117, please
refer to the squares 6 illustrated in FIG. 3B. Referring to FIGS.
15C and 15D, nine small squares G118 through G126, i.e., the nine
squares 6, within the square 4 inscribed in the stop P.sub.4-2 of
the moving window 2 overlap or cover the nine computation voxels
X20, X21, X22, X26, X27, X28, X32, X33 and X34, respectively, and
each of the squares G118-G126 may have an area less than 10% of
that of the stop P.sub.4-2 of the moving window 2. For details
about the squares G118-G126, please refer to the squares 6
illustrated in FIG. 3B. Referring to FIGS. 15E and 15F, nine small
squares G127 through G135, i.e., the nine squares 6, within the
square 4 inscribed in the stop P.sub.4-3 of the moving window 2
overlap or cover the nine computation voxels X21, X22, X23, X27,
X28, X29, X33, X34 and X35, respectively, and each of the squares
G127-G135 may have an area less than 10% of that of the stop
P.sub.4-3 of the moving window 2. For details about the squares
G127-G135, please refer to the squares 6 illustrated in FIG. 3B.
Referring to FIGS. 15G and 15H, nine small squares G136 through
G144, i.e., the nine squares 6, within the square 4 inscribed in
the stop P.sub.4-4 of the moving window 2 overlap or cover the nine
computation voxels X22, X23, X24, X28, X29, X30, X34, X35 and X36,
respectively, and each of the squares G136-G144 may have an area
less than 10% of that of the stop P.sub.4-4 of the moving window 2.
For details about the squares G136-G144, please refer to the
squares 6 illustrated in FIG. 3B.
[0136] After the measures of the specific MRI parameters for the
sixteen stops P.sub.1-1-P.sub.4-4 of the moving window 2 are
obtained, the step S5 is performed to obtain the probabilities PWs
of the event for the respective stops P.sub.1-1-P.sub.4-4 of the
moving window 2. The probabilities PWs of the event for the sixteen
stops P.sub.1-1, P.sub.1-2, P.sub.1-3, P.sub.1-4, P.sub.2-1,
P.sub.2-2, P.sub.2-3, P.sub.2-4, P.sub.3-1, P.sub.3-2, P.sub.3-3,
P.sub.3-4, P.sub.4-1, P.sub.4-2, P.sub.4-3, and P.sub.4-4 of the
moving window 2, for example, are 0.6055, 0.5628, 0.5366, 0.4361,
0.4982, 0.5534, 0.5521, 0.4227, 0.4618, 0.5132, 0.6214, 0.5810,
0.4371, 0.4698, 0.5774, and 0.5613, respectively. In the example,
the sixteen probabilities PWs of the event for the sixteen stops
P.sub.1-1-P.sub.4-4 of the moving window 2 are assumed to be those
for the sixteen squares 4 inscribed in the respective stops
P.sub.1-1-P.sub.4-4 of the moving window 2, respectively. In other
words, the sixteen probabilities of the event for the sixteen
squares 4 inscribed in the sixteen stops P.sub.1-1-P.sub.4-4 of the
moving window 2 are 0.6055, 0.5628, 0.5366, 0.4361, 0.4982, 0.5534,
0.5521, 0.4227, 0.4618, 0.5132, 0.6214, 0.5810, 0.4371, 0.4698,
0.5774, and 0.5613, respectively.
[0137] Next, optimal probabilities of the event for the computation
voxels X1-X36 is determined based on the probabilities PWs of the
event for the sixteen stops P.sub.1-1-P.sub.4-4 of the moving
window 2. FIGS. 16A, 16B, and 16C show example initial
probabilities for computation voxels, updated probabilities for the
computation voxels, and optimal probabilities for the computation
voxels, respectively, in accordance with an embodiment of the
present invention.
[0138] The process described above is performed to generate the
moving window 2 across the computation regions 12 of the MRI slice
10 along the x and y directions to create a two-dimensional (2D)
probability map. In order to obtain a three-dimensional (3D)
probability map, the process, including the steps S1-S6, may be
applied to each of all MRI slices (including the MRI slice 10) of
the subject arranged in the z direction perpendicular to the x and
y directions.
[0139] The invention provides a computing method, i.e., the steps
S1-S6, to obtain measures of the specific MRI parameters for
multiple large regions or volumes of the MRI image 10 (i.e., the
stops of the moving window 2), each including multiple voxels of
the MRI image 10, and obtain a probability map having small regions
(i.e., computation voxels) with extremely accurate probabilities
based on the measures of the specific MRI parameters for the large
regions or volumes, which overlaps, of the MRI image 10. Because of
calculation for the probabilities based on the large regions or
volumes of the MRI image 10, registered or aligned errors between
the registered image sets (or registered parameter maps) can be
compensated.
[0140] In the computing method depicted in FIG. 4, the steps S1-S6,
for example, may be performed on a MRI system, which may include
one or more MRI machines. A probability map for occurrence of
prostate cancer, for example, may be formed by the MRI system to
perform the steps S1-S6 and shows a probability of cancer for a
small portion of the prostate.
[0141] By repeating the stops S1-S6 or the steps S5 and S6 for
various events such as occurrence of prostate cancer, occurrence of
small cell subtype, and occurrence of Gleason scores greater than
7, multiple probability maps for the various events are obtained or
formed. The probability maps, for example, include a prostate
cancer probability map shown in FIG. 17A, a small cell subtype
probability map shown in FIG. 17B, and a probability map of Gleason
scores greater than 7 shown in FIG. 17C. Some or all of the
probability maps may be selected to be combined into a composite
probability image or map to provide most useful information to
interpreting Radiologist and Oncologist. The composite probability
image or map may show areas of interest. For example, the composite
probability image or map shows areas with high probability of
cancer (>98%), high probability of small cell subtype, and high
probability of Gleason score >7, as shown in FIG. 17D.
[0142] In an alternative embodiment, the subset data DB-1 may
further include measures for a PET parameter (e.g., SUVmax) and a
SPECT parameter. In this case, the classifier CF, e.g., Bayesian
classifier, for the event (e.g., occurrence of prostate cancer) may
be created based on data associated with the event and specific
variables, including, e.g., the PET parameter, the SPECT parameter,
some or all of the MRI parameters depicted in the section of the
"description of classifier CF," and the processed parameters of
average Ve and average Ktrans, in the subset data DB-1. Next, by
using the computing method depicted in FIG. 4, the probability map
for the event may be generated or formed based on measures of the
specific variables for each stop of the moving window 2.
[0143] In the invention, the computing method (i.e., the steps
S1-S6) depicted in FIG. 4, for example, may be performed on a
software, a device, or a system including, e.g., hardware, one or
more computing devices, computers, processors, software, and/or
tools to obtain the above-mentioned probability map(s) for the
event(s) and/or the above-mentioned composite probability image or
map. Accordingly, a doctor questions the software, device or system
about a suspected region of an image such as MRI slice image, and
the latter provides a probability map for the event (e.g.,
occurrence of prostate cancer) and/or a likelihood measurement of
cancer (e.g., malignancy) as an answer.
Second Embodiment
[0144] In the case of the MRI image 10 obtained from the subject
(e.g., human patient) that has been given a treatment, such as
neoadjuvant chemotherapy or (preoperative) radiation therapy, or
has taken or been injected with one or more drugs for a treatment,
such as neoadjuvant chemotherapy, the effect of the treatment or
the drugs on the subject may be evaluated, identified, or
determined by analyzing the probability map(s) for the event(s)
depicted in the first embodiment and/or the composite probability
image or map depicted in the first embodiment. Accordingly, a
method of evaluating, identifying, or determining the effect of the
treatment or the drugs on the subject may include the following
steps: (a) administering to the subject the treatment or the drugs,
(b) after the step (a), obtaining the MRI image 10 from the subject
by the MRI system, (c) after the step (b), performing the steps
S2-S6 to obtain the probability map(s) for the event(s) depicted in
the first embodiment and/or obtaining the composite probability
image or map depicted in the first embodiment, and (d) after the
step (c), analyzing the probability map(s) for the event(s) and/or
the composite probability image or map.
Third Embodiment
[0145] The steps S1-S6 may be employed to generate a probability
map of breast cancer. In this case, in the steps S1 and S2, the MRI
image 10 shows the breast anatomical structure of the subject as
shown in FIG. 18, and the computation region 12, set in the desired
or anticipated region 11 of the MRI image 10, is defined with the
computation voxels and covers at least 10, 25, 50, 80, 90 or 95
percent of the FOV of the MRI image 10, which includes the breast
anatomical structure. The steps S3 and S4 are then sequentially
performed. Next, in the step S5, a probability of breast cancer for
each stop of the moving window 2 may be obtained by matching the
parameter set for said each stop of the moving window 2 from the
step S4 (or the measures of some or all of the specific MRI
parameters for said each stop of the moving window 2 from the step
S3) to the classifier CF created for breast cancer.
Fourth Embodiment
[0146] FIG. 20 is a flow chart of evaluating, identifying, or
determining the effect of a treatment, such as neoadjuvant
chemotherapy or (preoperative) radiation therapy, or a drug for the
treatment on a subject (e.g., human or animal). Referring to FIG.
20, in a step S21, a first MRI, or other imaging modality, slice
image is obtained from the subject by the MRI device or system. The
first MRI slice image is composed of multiple voxels in its field
of view (FOV) to show an anatomical region of the subject, such as
prostate or breast. In a step S22, the steps S2-S6 are performed on
the first MRI slice image to generate a first probability map.
[0147] After the step S21 or S22 is performed, step S23 is
performed. In the step S23, the subject is given the treatment,
such as a drug given intravenously or orally. For certain cancers
such as prostate cancer, the treatment may be the (preoperative)
radiation therapy (or called radiotherapy), a proton beam therapy,
a minimally invasive treatment (such as ablation or radiation), or
an ablation therapy such as high-intensity focused ultrasound
treatment. The (preoperative) radiation therapy for prostate cancer
may be performed by a radiotherapy device such as Truebeam or
CyberKnife and may use high-energy radiation (e.g., gamma rays) to
shrink tumors and kill cancer cells.
[0148] In a step S24, after the subject gets or receives the
treatment such as an oral or intravenous drug, a second MRI slice
image is obtained from the subject by the MRI device or system. The
second MRI slice image is composed of multiple voxels in its FOV to
show the same anatomical region of the subject as the first MRI
slice image shows. In a step S25, the steps S2-S6 are performed on
the second MRI slice image to generate a second probability map.
The first and second probability maps may be generated for an event
or data type, such as prostate cancer, breast cancer, one of
Gleason scores 0 through 10, two or more of Gleason scores 0
through 10 (e.g., Gleason scores greater than 7), tissue necrosis,
or the percentage of cancer in a specific range from a first
percent (e.g., 91 percent) to a second percent (e.g., 100 percent).
Next, in a step S26, by comparing the first and second probability
maps, the effect of the treatment or the drug used in the treatment
on the subject may be identified, determined, or evaluated as
effective or ineffective. Based on the result from the step S26, a
doctor can decide or judge whether the treatment or the drug should
be adjusted or changed. The method depicted in the steps S21-S26
can detect responses or progression after the treatment or the drug
within less than one week or two weeks, allowing earlier
adjustments to the treatment regime.
Fifth Embodiment
[0149] FIG. 21 is a flow chart of evaluating, identifying, or
determining the effect of a treatment, such as neoadjuvant
chemotherapy or (preoperative) radiation therapy, or a drug for the
treatment on a subject (e.g., human or animal). Referring to FIG.
21, in a step S31, a first MRI slice image is obtained from the
subject by the MRI device or system. The first MRI slice image is
composed of multiple voxels in its field of view (FOV) to show an
anatomical region of the subject, such as prostate or breast. In a
step S32, the steps S2-S5 are performed on the first MRI slice
image to obtain first probabilities of an event or data type for
stops of the moving window 2 for the computation region 12 of the
first MRI slice image. In other words, the first probabilities of
the event or data type for the stops of the moving window 2 on the
first MRI slice image for the subject before the treatment are
obtained based on measures of the specific MRI parameters for the
stops of the moving window 2 on the first MRI slice image to match
a matching dataset from the established classifier CF or biomarker
library. The measures of the specific MRI parameters for the stops
of the moving window 2 on the first MRI slice image, for example,
may be obtained from a registered (multi-parametric) image dataset
including, e.g., the first MRI slice image and/or different
parameter maps registered to the fist MRI slice. The event or data
type, for example, may be prostate cancer, breast cancer, one of
Gleason scores 0 through 10, two or more of Gleason scores 0
through 10 (e.g., Gleason scores greater than 7), tissue necrosis,
or the percentage of cancer in a specific range from a first
percent (e.g., 91 percent) to a second percent (e.g., 100
percent).
[0150] After the step S31 or S32 is performed, step S33 is
performed. In the step S33, the subject is given the treatment,
such as a drug given intravenously or orally. For certain cancers
such as prostate cancer, the treatment may be the (preoperative)
radiation therapy (or called radiotherapy), a proton beam therapy,
a minimally invasive treatment (such as ablation or radiation), or
an ablation therapy such as high-intensity focused ultrasound
treatment. The (preoperative) radiation therapy for prostate cancer
may be performed by a radiotherapy device such as Truebeam or
CyberKnife and may use high-energy radiation (e.g., gamma rays) to
shrink tumors and kill cancer cells.
[0151] In a step S34, after the subject gets or receives the
treatment such as an oral or intravenous drug, a second MRI slice
image is obtained from the subject by the MRI device or system. The
second MRI slice image is composed of multiple voxels in its FOV to
show the same anatomical region of the subject as the first MRI
slice image shows. In a step S35, the steps S2-S5 are performed on
the second MRI slice image to obtain second probabilities of the
event or data type for stops of the moving window 2 for the
computation region 12 of the second MRI slice image. In other
words, the second probabilities of the event or data type for the
stops of the moving window 2 on the second MRI slice image for the
subject after the treatment are obtained based on measures of the
specific MRI parameters for the stops of the moving window 2 on the
second MRI slice image to match the matching dataset from the
established classifier CF or biomarker library. The measures of the
specific MRI parameters for the stops of the moving window 2 on the
second MRI slice image, for example, may be obtained from a
registered (multi-parametric) image dataset including, e.g., the
second MRI slice image and/or different parameter maps registered
to the second MRI slice.
[0152] The stops of the moving window 2 for the computation region
12 of the first MRI slice may substantially correspond to or may be
substantially aligned with or registered to the stops of the moving
window 2 for the computation region 12 of the second MRI slice,
respectively. Each of the stops of the moving window 2 for the
computation region 12 of the first MRI slice and the registered or
aligned one of the stops of the moving window 2 for the computation
region 12 of the second MRI slice may substantially cover the same
anatomical region of the subject.
[0153] Next, in a step S36, the first and second probabilities of
the event or data type for each aligned or registered pair of the
stops of the moving window 2 on the first and second MRI slice
images are subtracted from each other into a corresponding
probability change PMC for said each aligned or registered pair of
the stops of the moving window 2 on the first and second MRI slice
images. For example, for each aligned or registered pair of the
stops of the moving window 2 on the first and second MRI slice
images, the probability change PMC may be obtained by subtracting
the first probability of the event or data type from the second
probability of the event or data type.
[0154] In a step S37, probability changes PVCs for respective
computation voxels used to compose a probability change map for the
event or data type are computed based on the probability changes
PMCs for the aligned or registered pairs of the stops of the moving
window 2 on the first and second MRI slice images.
[0155] The process uses the moving window 2 in the x and y
directions to create a 2D probability change map. In addition, the
above process may be applied to multiple MRI slices of the subject
registered in the z direction, perpendicular to the x and y
directions, to form a 3D probability change map.
[0156] In a step S38, by analyzing the probability change map, the
effect of the treatment or the drug used in the treatment on the
subject may be identified, determined, or evaluated as effective or
ineffective. Based on the result from the step S38, a doctor can
decide or judge whether the treatment or the drug should be
adjusted or changed. The method depicted in the steps S31-S38 can
detect responses or progression after the treatment or the drugs
within less than one week or two weeks, allowing earlier
adjustments to the treatment regime.
Sixth Embodiment
[0157] FIG. 22 is a flow chart of evaluating, identifying, or
determining the effect of a treatment, such as neoadjuvant
chemotherapy or (preoperative) radiation therapy, or a drug used in
the treatment on a subject (e.g., human or animal). Referring to
FIG. 22, in a step S41, a first MRI slice image is obtained from
the subject by the MRI device or system. The first MRI slice image
is composed of multiple voxels in its field of view (FOV) to show
an anatomical region of the subject, such as prostate or breast. In
a step S42, the steps S2-S6 are performed on the first MRI slice
image to generate a first probability map composed of first
computation voxels.
[0158] After the step S41 or S42 is performed, step S43 is
performed. In the step S43, the subject is given a treatment such
as an oral or intravenous drug. For certain cancers such as
prostate cancer, the treatment may be the (preoperative) radiation
therapy (or called radiotherapy), a proton beam therapy, or an
ablation therapy such as high-intensity focused ultrasound
treatment. The (preoperative) radiation therapy for prostate cancer
may be performed by a radiotherapy device such as Truebeam or
CyberKnife and may use high-energy radiation (e.g., gamma rays) to
shrink tumors and kill cancer cells.
[0159] In a step S44, after the subject gets or receives the
treatment such as an oral or intravenous drug, a second MRI slice
image is obtained from the subject by the MRI device or system. The
second MRI slice image is composed of multiple voxels in its FOV to
show the same anatomical region of the subject as the first MRI
slice image shows. In a step S45, the steps S2-S6 are performed on
the second MRI slice image to generate a second probability map
composed of second computation voxels. Each of the second
computation voxels may substantially correspond to or may be
substantially aligned with or registered to one of the first
computation voxels. The first and second probability maps may be
generated for an event or data type such as prostate cancer, breast
cancer, one of Gleason scores 0 through 10, two or more of Gleason
scores 0 through 10 (e.g., Gleason scores greater than 7), tissue
necrosis, or the percentage of cancer in a specific range from a
first percent (e.g., 91 percent) to a second percent (e.g., 100
percent).
[0160] In a step S46, by subtracting a probability for each of the
first computation voxels from a probability for the corresponding,
registered or aligned one of the second computation voxels, a
corresponding probability change is obtained or calculated.
Accordingly, a probability change map is formed or generated based
on the probability changes. Next, in a step S47, by analyzing the
probability change map, the effect of the treatment or the drug
used in the treatment on the subject may be identified, determined,
or evaluated as effective or ineffective. Based on the result from
the step S47, a doctor can decide or judge whether the treatment or
the drug should be adjusted or changed. The method depicted in the
steps S41-S47 can detect responses or progression after the
treatment or the drug within less than one week or two weeks,
allowing earlier adjustments to the treatment regime.
[0161] The steps, features, benefits and advantages that have been
discussed are merely illustrative. None of them, nor the
discussions relating to them, are intended to limit the scope of
protection in any way. Numerous other embodiments are also
contemplated. These include embodiments that have fewer,
additional, and/or different steps, features, benefits and
advantages. These also include embodiments in which the steps are
arranged and/or ordered differently.
* * * * *