Predicting biochemical recurrence in pre-treatment prostate magnetic resonance imaging (MRI) with field effect induced organ distension (FORGE)

Patent metadata

Field	Value
Publication number	US-10607112-B2
Application number	US-201815919865-A
Country	US
Kind code	B2
Filing date	Mar 13, 2018
Priority date	Mar 21, 2017
Publication date	Mar 31, 2020
Grant date	Mar 31, 2020

Abstract

Embodiments predict prostate cancer (PCa) biochemical recurrence (BCR) employing an image acquisition circuit that accesses a pre-treatment image of a region of tissue demonstrating PCa; a segmentation circuit that segments a prostate capsule represented in the image; a registration circuit that registers the segmented prostate with a BCR− median template, and generates a registered surface of interest (SOI) mask by registering an SOI mask with the registered prostate; a mask circuit that generates a patient-specific SOI mask from the registered prostate and the registered SOI mask, and generates a patient-specific SOI mesh from the patient-specific SOI mask; a field effect induced organ distension (FOrge) circuit extracts a set of FOrge features from the patient-specific SOI mesh, and computes a probability that the region of tissue will experience BCR; and a classification circuit classifies the region of tissue as likely to experience BCR based on the probability.

First claim

What is claimed is:

1. An apparatus for predicting prostate cancer (PCa) biochemical recurrence (BCR), the apparatus comprising:
a processor;
a memory;
an input/output (I/O) interface;
a set of circuits including an image acquisition circuit, a segmentation circuit, a registration circuit, a mask circuit, a field effect induced organ distension (FOrge) circuit, and a classification circuit; and
an interface that connects the processor, the memory, the I/O interface, and the set of circuits;
where the memory is configured to store an image of a region of tissue demonstrating PCa, a BCR negative (BCR−) median template, and a surface of interest (SOI) mask, the image having a plurality of voxels, a voxel having an intensity;
where the image acquisition circuit is configured to access a pre-treatment image of a region of tissue demonstrating PCa;
where the segmentation circuit is configured to generate a segmented prostate by segmenting a prostate capsule represented in the pre-treatment image;
where the registration circuit is configured to:
generate a registered prostate by registering the segmented prostate with the BCR− median template; and
generate a registered SOI mask by registering the SOI mask with the registered prostate;

where the mask circuit is configured to:
generate a patient-specific SOI mask from the registered prostate and the registered SOI mask; and
generate a patient-specific SOI mesh from the patient-specific SOI mask;

where the FOrge circuit is configured to:
extract a set of FOrge features from the patient-specific SOI mesh; and
compute a probability that the region of tissue will experience BCR based, at least in part, on the set of FOrge features; and

where the classification circuit is configured to classify the region of tissue as likely to experience BCR or unlikely to experience BCR based, at least in part, on the probability.

2. The apparatus of claim 1 , where the registration circuit is configured to register the segmented prostate with the BCR− median template using a rigid registration technique.

3. The apparatus of claim 1 , where the registration circuit is configured to register the SOI mask with the registered prostate using a B-spline registration technique.

4. The apparatus of claim 1 , where the set of FOrge features includes a curvature magnitude feature, an XY plane surface normal orientation feature, an XZ plane surface normal orientation feature, a curvature magnitude standard deviation feature, a curvature magnitude range feature, a curvature magnitude mean feature, an XY plane surface normal orientation mean feature, an XY plane surface normal orientation kurtosis feature, an XY plane surface normal orientation range feature, an XY plane surface normal orientation standard deviation feature, an XZ plane surface normal orientation standard deviation feature, and an XZ plane surface normal orientation range feature.

5. The apparatus of claim 1 , where the FOrge circuit includes a machine learning component configured to compute the probability based on the set of FOrge features.

6. The apparatus of claim 5 , where the machine learning component is configured as a random forest (RF) classifier having a depth of two, and 10000 trees.

7. The apparatus of claim 5 , the set of circuits further comprising a training circuit configured to train the machine learning component.

8. The apparatus of claim 1 , the set of circuits further including a display circuit configured to display the classification, the probability, the patient-specific SOI mask, or the pre-treatment image.

9. A non-transitory computer-readable storage device storing computer-executable instructions that when executed by a computer control the computer to perform a method for predicting biochemical recurrence (BCR), the method comprising:
accessing a pre-treatment image of a region of tissue demonstrating prostate cancer (PCa), where the image includes a plurality of voxels, a voxel having an intensity;
segmenting a prostate capsule represented in the image;
registering the segmented prostate with a BCR negative (BCR−) median template;
registering a surface of interest (SOI) mask with the registered segmented prostate;
generating a patient-specific SOI mask from the registered SOI;
generating a patient-specific SOI mesh from the patient-specific SOI mask, where the SOI mesh includes a plurality of vertices;
extracting a set of field effect induced organ distension (FOrge) features from the patient-specific SOI mesh;
providing the set of FOrge features to a machine learning classifier;
receiving, from the machine learning classifier, a probability that the region of tissue will experience BCR based on the set of FOrge features;
classifying the region of tissue as likely to experience BCR, or unlikely to experience BCR based, at least in part, on the probability, the set of FOrge features, the patient specific SOI mask, or the image.

10. The non-transitory computer-readable storage device of claim 9 , where the image is a three dimensional (3D) magnetic resonance imaging (MRI) image.

11. The non-transitory computer-readable storage device of claim 9 , where segmenting the prostate capsule includes segmenting the prostate capsule using a statistical shape and appearance model segmentation technique.

12. The non-transitory computer-readable storage device of claim 9 , where registering the segmented prostate with the BCR− median template includes registering the segmented prostate with the BCR− median template using a rigid registration technique.

13. The non-transitory computer-readable storage device of claim 9 , where registering the SOI mask with the registered segmented prostate includes registering the SOI mask with the registered segmented prostate using a B-spline registration technique.

14. The non-transitory computer-readable storage device of claim 9 , where the set of FOrge features includes a curvature magnitude feature, an XY plane surface normal orientation feature, and an XZ plane surface normal orientation feature.

15. The non-transitory computer-readable storage device of claim 14 , where the set of FOrge features further includes a curvature magnitude standard deviation feature, a curvature magnitude range feature, a curvature magnitude mean feature, an XY plane surface normal orientation mean feature, an XY plane surface normal orientation kurtosis feature, an XY plane surface normal orientation range feature, an XY plane surface normal orientation standard deviation feature, an XZ plane surface normal orientation standard deviation feature, and an XZ plane surface normal orientation range feature.

16. The non-transitory computer-readable storage device of claim 9 , where the machine learning classifier is a random forest (RF) classifier.

17. The non-transitory computer-readable storage device of claim 16 , where the RF classifier has a depth of two, and 10000 trees.

18. The non-transitory computer-readable storage device of claim 9 , the method further comprising displaying the classification, the probability, the set of FOrge features, the patient-specific SOI mesh, the patient-specific SOI mask, the SOI mask, or the image.

19. The non-transitory computer-readable storage device of claim 9 , the method further comprising generating a BCR positive (BCR+) atlas and a BCR− atlas.

20. The non-transitory computer-readable storage device of claim 19 , where generating the BCR+ atlas and the BCR-atlas comprises:
accessing a set of pre-treatment images of a region of tis

Assignees

• Univ Case Western Reserve

Inventors

• Madabhushi Anant
• Ghose Soumya

Classifications

• G16H30/40

  for processing medical images, e.g. editing · CPC title

• G06T7/0014

  using an image reference approach · CPC title

• A61B2576/02

  specially adapted for a particular organ or body part · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• A61B5/4381

  Prostate evaluation or disorder diagnosis · CPC title