Method of storing and retrieving digital pathology analysis results

Patent metadata

Field	Value
Publication number	US-11959848-B2
Application number	US-202218146881-A
Country	US
Kind code	B2
Filing date	Dec 27, 2022
Priority date	Dec 6, 2017
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

Abstract

The present disclosure is directed, among other things, to automated systems and methods for analyzing, storing, and/or retrieving information associated with biological objects having irregular shapes. In some embodiments, the systems and methods partition an input image into a plurality of sub-regions based on localized colors, textures, and/or intensities in the input image, wherein each sub-region represents biologically meaningful data.

First claim

The invention claimed is:

1. A method of deriving data corresponding to irregularly-shaped cells from an image of a biological sample stained with at least one stain, the method comprising:
deriving one or more feature metrics from the image by identifying nuclei of cells depicted by the image and calculating at least one expression score based on the identified nuclei, wherein the at least one expression score is calculated based on a percentage of cells of the cells depicted by the image that are biomarker-positive cells;
segmenting the image using an image segmentation algorithm to identify a plurality of sub-regions within the image;
computing a series of representational objects that correspond to a set of sub-regions of the identified plurality of sub-regions; wherein:
each representational object of the series of representational objects identifies a particular cell type; and
each sub-region of the set of sub-regions identifies an amount of stain that exceeds a threshold amount of stain; and

associating the one or more derived feature metrics from the image with calculated coordinates of each of the series of representational objects.

2. The method of claim 1 , wherein the particular cell type includes a fibroblast or a macrophage.

3. The method of claim 1 , further comprising storing the one or more derived feature metrics and associated calculated representational object coordinates in a database.

4. The method of claim 1 , wherein each representational object of the series of representational objects is further identified by a corresponding seed point.

5. The method of claim 1 , wherein computing the series of representational objects includes applying a thresholding algorithm to identify the set of sub-regions from the plurality of sub-regions and exclude at least one sub-region of the plurality of sub-regions.

6. The method of claim 5 , wherein the image includes two or more color channels, and wherein identifying the set of sub-regions includes applying the thresholding algorithm to a color channel of the two or more color channels of the image.

7. The method of claim 1 , wherein computing the series of representational objects includes applying one or more image filters to identify the set of sub-regions from the plurality of sub-regions and exclude at least one sub-region of the plurality of sub-regions.

8. The method of claim 1 , wherein the image is an RGB image or a multispectral image.

9. The method of claim 1 , wherein the biological sample is stained in an IHC assay for presence of one or more biomarkers.

10. The method of claim 9 , wherein the one or more biomarkers include a fibroblast activation protein (FAP).

11. The method of claim 1 , further comprising:
storing, for each representational object of the series of representational objects, a derived feature metric for the respective representational object and the calculated coordinates for the respective representational object in a vector for the respective representational object.

12. A system for deriving data corresponding to irregularly-shaped cells from an image of a biological sample comprising at least one stain, the system comprising: (i) one or more processors, and (ii) a memory coupled to the one or more processors, the memory to store computer-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
deriving one or more feature metrics from the image by identifying nuclei of cells depicted by the image and calculating at least one expression score based on the identified nuclei, wherein the at least one expression score is calculated based on a percentage of cells of the cells depicted by the image that are biomarker-positive cells;
segmenting the image using an image segmentation algorithm to identify a plurality of sub-regions within the image;
computing a series of representational objects that correspond to a set of sub-regions of the identified plurality of sub-regions; wherein:
each representational object of the series of representational objects identifies a particular cell type; and
each sub-region of the set of sub-regions identifies an amount of stain that exceeds a threshold amount of stain; and

associating the one or more derived feature metrics from the image with calculated coordinates of each of the series of representational objects.

13. The system of claim 12 , wherein the particular cell type includes a fibroblast or a macrophage.

14. The system of claim 12 , wherein the one or more derived feature metrics comprise at least one expression score selected from percent positivity, an H-score, and a staining intensity.

15. The system of claim 12 , wherein computing the series of representational objects includes applying a thresholding algorithm to identify the set of sub-regions from the plurality of sub-regions and exclude at least one sub-region of the plurality of sub-regions.

16. The system of claim 12 , wherein computing the series of representational objects includes applying one or more image filters to identify the set of sub-regions from the plurality of sub-regions and exclude at least one sub-region of the plurality of sub-regions.

17. The system of claim 12 , wherein the biological sample is stained in an IHC assay for presence of one or more biomarkers, and wherein the one or more biomarkers include a fibroblast activation protein (FAP).

18. A non-transitory computer-readable medium for deriving data corresponding to irregularly-shaped cells from an image of a biological sample stained with at least one stain, the non-transitory computer-readable medium storing instructions for analyzing data associated with biological objects having irregular shapes, the instructions comprising:
deriving one or more feature metrics from the image by identifying nuclei of cells depicted by the image and calculating at least one expression score based on the identified nuclei, wherein the at least one expression score is calculated based on a percentage of cells of the cells depicted by the image that are biomarker-positive cells;
segmenting the image using an image segmentation algorithm to identify a plurality of sub-regions within the image;
computing a series of representational objects that correspond to a set of sub-regions of the identified plurality of sub-regions; wherein:
each representational object of the series of representational objects identifies a particular cell type; and
each sub-region of the set of sub-regions identifies an amount of stain that exceeds a threshold amount of stain; and

associating the one or more derived feature metrics from the image with calculated coordinates of each of the series of representational objects.

19. The non-transitory computer-readable medium of claim 18 , wherein the particular cell type includes a fibroblast or a macrophage.

20. The non-transitory computer-readable medium of claim 18 , wherein the one or more derived feature metrics comprise at least one expression score selected from percent positivity, an H-score, and a staining intensity.

Assignees

• Ventana Med Syst Inc

Inventors

• Bredno Joerg
• Lorsakul Auranuch

Classifications

• G01N15/0227 Primary

  using imaging; using holography · CPC title

• G01N15/1463

  Physics · mapped topic

• G06F18/232

  Non-hierarchical techniques · CPC title

• G06K1/00

  Methods or arrangements for marking the record carrier in digital fashion · CPC title

• G06V10/25

  Determination of region of interest [ROI] or a volume of interest [VOI] · CPC title