Pathology case review, analysis and prediction

Patent metadata

Field	Value
Publication number	US-10049447-B2
Application number	US-201415034683-A
Country	US
Kind code	B2
Filing date	Nov 6, 2014
Priority date	Nov 6, 2013
Publication date	Aug 14, 2018
Grant date	Aug 14, 2018

Abstract

Systems and methods for personalized cancer therapy using analysis of pathology slides to target regions in a single sample that interrogates the feature data of a relatively large number of cells. The disclosure describes pathology case review tools of the future which include analysis, visualization and prediction modeling to provide novel information to the pathologist for the diagnosis of disease. This disclosure further describes a user interface to assist the physicians that make that diagnosis, pathologists. Complex computer learning algorithms will combine and mine these data sets to recommend optimal treatment strategies. A computer interface is provided which allows a pathologist to access those data instantly to make a more informed and accurate diagnosis.

First claim

What is claimed:

1. A method for providing visualizations of features within a digital image that is generated from image data, comprising:
obtaining image data associated with a tissue;
identifying regions of interest within the image data;
identifying objects of interest by superimposing a checkerboard over the digital image to identify first objects having a first relative size and using pattern recognition to identify second objects, wherein the second objects have a second size smaller than the first relative size;
extracting feature data associated with each second object of interest;
classifying the feature data in groups; and
displaying the groups in accordance with predetermined sets of the feature data.

2. The method of claim 1 , classifying the feature data in groups further comprising classifying cells into the groups in accordance with multiple features within the feature data.

3. The method of claim 1 , further comprising providing the groups in an interactive interface to enable interrogation of characteristics of the groups.

4. The method of the claim 3 , wherein the interrogation comprises one of altering views, metrics, scales, features, objects to visualize a wide spectrum of data on a monitor.

5. The method of claim 4 , further comprising, providing the visualization as a heat map showing a display of where particular classifications of the feature data exist within the groups.

6. The method of claim 1 , further comprising determining cellular and environmental heterogeneity within the tissue.

7. The method of claim 6 , further comprising determining regional variations of ecological and evolutionary forces in the tissue from the image data.

8. The method of claim 1 , wherein the feature data comprises multiparametric morphological features of cells in the tissue.

9. The method of claim 1 , further comprising:
determining spatial arrangements of tumor cell phenotype; and
determining a tumor progression and relationship with a physical microenvironment.

10. The method of claim 9 , further comprising:
identifying clusters of cell subpopulations with like phenotypes;
illuminating a correspondence between phenotypic changes and tumor progression; and
correlating changes to the physical microenvironment.

11. The method of claim 9 , wherein the feature data comprises morphometric features of sets of cancer cells and subpopulations that are used identify clusters of similar phenotypes.

12. The method of claim 1 , further comprising identifying cells that predict tumor progression.

13. A method for providing visualizations of features within a digital image that is generated from image data, comprising:
obtaining image data associated with a tissue;
identifying regions of interest within the image data;
identifying objects of interest by superimposing a checkerboard over the digital image to identify first objects having a first relative size and using pattern recognition to identify second objects, wherein the second objects have a second size smaller than the first relative size;
extracting feature data associated with each second object of interest;
classifying the feature data as multiparametric feature data in groups, wherein each group includes objects having at least one feature in common; and
displaying the groups to identify data of interest.

14. The method of claim 13 , wherein the first objects are super objects that are higher-level objects than the second objects that are objects of interest.

15. The method of claim 13 , further comprising characterizing evolutionary dynamics of cells within the tissue, wherein the evolutionary dynamics include spatial and temporal variability.

16. The method of claim 13 , further comprising quantifying metrics in the data of interest, wherein the metrics comprise one of cell area, intensity, roundness or regional tissue features.

17. The method of claim 13 , further comprising determining morphological or phenotypic properties of cells within a region of interest.

18. The method of claim 17 , further comprising quantifying intratumoral variation.

19. The method of claim 13 , further comprising redisplaying the groups in the visualization in response to results of a received query.

Assignees

• H Lee Moffitt Cancer Ct & Res
• H Lee Moffitt Cancer Center And Res Insititute Inc

Inventors

• Lloyd Mark Cassidy Cridlin
• Bui Marilyn Yuanxin Ma
• Rejniak Katarzyna Anna
• Puri Munish

Classifications

• G06F18/24

  Classification techniques · CPC title

• G06T2207/10056

  Microscopic image · CPC title

• G06T2207/30024

  Cell structures in vitro; Tissue sections in vitro · CPC title

• G06T2207/30096

  Tumor; Lesion · CPC title

• G06T2207/20081

  Training; Learning · CPC title