Automated prostate tissue referencing for cancer detection and diagnosis

Patent metadata

Field	Value
Publication number	US-9230063-B2
Application number	US-201213353196-A
Country	US
Kind code	B2
Filing date	Jan 18, 2012
Priority date	Jan 5, 2011
Publication date	Jan 5, 2016
Grant date	Jan 5, 2016

Abstract

This application provides to a method for identifying one or more prostate tissue samples in a database that are closest to a test prostate sample, which can be used to aid pathologists when examining prostate tissues to attain reliable and consistent diagnoses of prostate cancer. Also provided are databases and computer algorithms that can be used with such methods.

First claim

We claim:

1. A method comprising:
obtaining, by a processor, a Hematoxylin and Eosin (HE) stained image of a test prostate sample;
obtaining, by the processor, an Infrared (IR) image of the test prostate sample;
performing segmentation, by the processor, for the test prostate sample utilizing the HE stained image and the IR image;
identifying, by the processor, epithelial cells, epithelial nuclei and lumens in the test prostate sample according to the segmentation;
selecting, by the processor, a group of morphological features from a plurality of morphological features associated with the epithelial cells, the epithelial nuclei and the lumens of the test prostate sample;
determining the group of morphological features for the epithelial cells, the epithelial nuclei and the lumens in the test prostate sample based on an analysis of at least the HE stained image;
performing, by the processor, a comparison of the group of morphological features for the test prostate sample with reference sample information stored in a database, wherein the reference sample information represents reference morphological features for reference prostate samples, wherein the reference prostate samples are identified in the database by a confirmed pathological status;
selecting, by the processor, a group of reference prostate samples from the reference prostate samples according to the comparison; and
presenting, by the processor, reference data for the group of reference prostate samples.

2. The method of claim 1 , wherein the IR image is generated using Fourier transform IR imaging.

3. The method of claim 1 , wherein the test prostate sample is a human sample, and wherein the plurality of morphological features comprise size of epithelial cells, size of a nucleus, number of nuclei, distance to lumen, distance to epithelial cell boundary, number of isolated nuclei, fraction of distant nuclei, entropy of nuclei spatial distribution, size of a lumen, number of lumens, lumen roundness, lumen distortion, lumen minimum bounding circle ratio, lumen convex hull ratio, symmetric index of lumen boundary, symmetric index of lumen area, spatial association of lumens and cytoplasm-rich regions, number of stroma cells, minimum lumen distance, minimum gland distance, ratio of lumen to epithelial cells, ratio of epithelial cells to stroma cells, ratio of cell separation, ratio of sheets of cells, degree of cell dispersion and spatial autocorrelation of cells, or any combination thereof.

4. The method of claim 1 , wherein the selecting of the group of morphological features comprises:
selecting a subset of morphological features from the plurality of morphological features, wherein the determining of the group of morphological features for the epithelial cells, the epithelial nuclei and the lumens in the test prostate sample includes analyzing at least the HE stained image according to the subset;
determining an additional morphological feature that is least redundant with the subset and that is correlated with a class label for the test prostate sample;
adjusting the subset to include the additional morphological feature to generate an adjusted subset; and
repeating the determining of the group of morphological features for the epithelial cells, the epithelial nuclei and the lumens in the test prostate sample by analyzing the at least the HE stained image according to the adjusted subset, wherein the additional morphological feature is utilized as a starting point for the analyzing.

5. The method of claim 1 , wherein the presenting of the reference data for the group of reference prostate samples includes presenting images at a display device coupled with the processor.

6. The method of claim 1 , wherein the selected group of reference prostate samples have a most similar k value to the test prostate sample according to a k-nearest neighbor analysis.

7. The method of claim 1 , wherein the segmentation is based on color intensities and geometric properties determined from the HE stained image and the IR image.

8. The method of claim 1 , wherein the reference prostate samples of the database comprises a plurality of Gleason grade 2, 3, 4, and 5 cancer samples, benign prostatic hyperplasia (BPH) samples, normal prostate samples, or combinations thereof.

9. The method of claim 1 , wherein the selecting of the group of morphological features from the plurality of morphological features includes utilizing a minimum-redundancy-maximal-relevance (mRMR) criterion.

10. The method of claim 9 , wherein the selecting of the group of morphological features from the plurality of morphological features further includes utilizing a sequential floating forward selection process.

11. The method of claim 1 , further comprising:
receiving, by the processor, user input indicating accuracy information associated with the reference data for the group of reference prostate samples.

12. The method of claim 11 , wherein the accuracy information is utilized for adjusting information in the database.

13. The method of claim 1 , further comprising:
adjusting, by the processor, accuracy data utilized in selecting a subsequent group of morphological features from the plurality of morphological features associated with epithelial cells, epithelial nuclei and lumens of a subsequent test prostate sample, wherein the adjusting of the accuracy data is based on user feedback.

14. The method of claim 1 , further comprising:
identifying, by the processor, stroma cells according to the segmentation.

15. The method of claim 1 , wherein the selecting of the group of morphological features comprises:
selecting a subset of morphological features from the plurality of morphological features, wherein the determining of the group of morphological features for the epithelial cells, the epithelial nuclei and the lumens in the test prostate sample includes analyzing at least the HE stained image according to the subset;
determining an accuracy associated with the subset utilized for determining the group of morphological features;
identifying an inaccurate morphological feature according to the determining of the accuracy;
adjusting the subset to remove the inaccurate morphological feature to generate an adjusted subset; and
repeating the determining of the group of morphological features for the epithelial cells, the epithelial nuclei and the lumens in the test prostate sample by analyzing the at least the HE stained image according to the adjusted subset.

16. The method of claim 1 , wherein the performing of the segmentation for the test prostate sample comprises overlaying the HE stained image and the IR image for image registration.

17. The method of claim 1 , wherein the selecting of the group of morphological features comprises selecting the group according to accuracy information stored in the database and adjusting the group to add or remove morphological features according to accuracy determinations associated with iterations of the performing of the comparison of the group of morphological features with the reference sample information stored in the database.

18. A database device comprising:
a memory that stores executable instructions; and
a processor coupled with the memory, wherein the processor, responsive to executing the instructions, performs operations comprising:
storing reference sample information in the memory, wherein the reference sample information represents reference morphological features for reference prostate samples, wherein the reference prostate samples are identified in the database by a

Assignees

• Bhargava Rohit
• Kwak Jin Tae
• Sinha Saurabh
• Univ Illinois

Inventors

• Bhargava Rohit
• Kwak Jin Tae
• Sinha Saurabh

Classifications

• G06F19/3443

  Physics · mapped topic

• G06F19/345 Primary

  Physics · mapped topic

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title