System for determining a cancer diagnosis score derived from stained nuclei

• US 10,176,577 B2
• Filed: 04/24/2018
• Issued: 01/08/2019
• Est. Priority Date: 10/24/2012
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Liu, Ming-Chang, Zhang, Ximin
• Primary Examiner(s): Liew, Alex
• Application Number:
  US15/961,807
• Publication Number:
  US 20180253845A1
• Time in Patent Office: 259 Days
• Field of Search: 382128-134, 382192-194, 382221, 382271
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10056 Microscopic image
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 2207/30096 Tumor; Lesion
• CPC Class Codes: G06T 7/0012 Biomedical image inspection
• CPC Class Codes: G06V 20/69 Microscopic objects, e.g. biological cells or cellular parts
• CPC Class Codes: G06V 20/695 Preprocessing, e.g. image segmentation
• CPC Class Codes: G06V 20/698 Matching; Classification

Abstract

Certain aspects of an apparatus and method for automatic ER/PR scoring of tissue samples may include for determining a cancer diagnosis score comprising identifying a positive stained nucleus in a slide image of the tissue sample, identifying a negative stained nucleus in the slide image, computing a proportion score based on number of the positive stained nucleus identified and number of the negative stained nucleus identified and determining the cancer diagnosis score based on the proportion.

Claims

1. A non-transitory computer-readable storage medium storing one or more computer programs adapted to cause a processor based system to execute steps comprising:

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei; and

outputting the cancer diagnosis score.

2. The non-transitory computer readable storage medium of claim 1, further comprising:

determining, from the tissue sample image information in the optical density format, negative stain image information indicating negative stained content of the tissue sample image information; and

using the negative stain image information in the generating of the cancer diagnosis score.

3. The non-transitory computer readable storage medium of claim 2, further comprising:

calculating a negative percentage from the number of negative stained nuclei and the number of total nuclei; and

wherein the outputting the cancer diagnosis score includes outputting a cancer diagnosis score derived at least in part form the positive percentage and the negative percentage.

4. The non-transitory computer readable storage medium of claim 1, further comprising:

converting at least a portion of the tissue sample image information to the optical density format.

5. The non-transitory computer readable storage medium of claim 1, further comprising:

receiving the tissue sample image information from a microscope.

6. The non-transitory computer readable storage medium of claim 1, where the tissue sample image information includes at least a portion of image information of tissue stained with an immunohistochemical stain.

7. The non-transitory computer readable storage medium of claim 1, where the tissue sample image information includes an indication of levels in the stained tissue of a marker for a particular cancer.

8. The non-transitory computer readable storage medium of claim 1, further comprising:

identifying a region of interest within the tissue sample image information in which to identify one or more nuclei.

9. The non-transitory computer readable storage medium of claim 1, further comprising:

differentiating nuclei among cellular compartments in the tissue sample image information.

10. The non-transitory computer readable storage medium of claim 1, further comprising:

identifying nuclei based in part on a size of one or more nuclei.

11. The non-transitory computer readable storage medium of claim 2, further comprising:

identifying whether nuclei are positive or negative based on at least one threshold.

12. The non-transitory computer readable storage medium of claim 11, where at least one of the thresholds is set automatically based on an analysis of the tissue sample image information.

13. A method for causing a processor-based system to perform the following acts:

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei; and

outputting the cancer diagnosis score.

14. The method of claim 13, further comprising:

determining, from the tissue sample image information in the optical density format, negative stain image information indicating negative stained content of the tissue sample image information; and

using the negative stain image information in the generating of the cancer diagnosis score.

15. The method of claim 14, further comprising:

calculating a negative percentage from the number of negative stained nuclei and the number of total nuclei; and

wherein the outputting the cancer diagnosis score includes outputting a cancer diagnosis score derived at least in part form the positive percentage and the negative percentage.

16. An apparatus comprising:

one or more processors;

one or more non-transitory computer-readable storage media storing one or more instructions executable by the one or more processors for;

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei; and

outputting the cancer diagnosis score.

17. The apparatus of claim 16, the one or more non-transitory computer readable storage media further including one or more instructions for:

determining, from the tissue sample image information in the optical density format, negative stain image information indicating negative stained content of the tissue sample image information; and

using the negative stain image information in the generating of the cancer diagnosis score.

18. The apparatus of claim 17, the one or more non-transitory computer readable storage media further including one or more instructions for:

calculating a negative percentage from the number of negative stained nuclei and the number of total nuclei; and

wherein the outputting the cancer diagnosis score includes outputting a cancer diagnosis score derived at least in part form the positive percentage and the negative percentage.

19. A non-transitory computer-readable storage medium storing one or more computer programs adapted to cause a processor based system to execute steps comprising:

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

identifying nuclei based in part on a size of one or more nuclei;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

receiving the tissue sample image information from a microscope, where the tissue sample image information includes at least a portion of image information of tissue stained with an immunohistochemical stain, and where the tissue sample image information includes an indication of levels in the stained tissue of a marker for a particular cancer;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei; and

outputting the cancer diagnosis score.

20. An apparatus comprising:

one or more processors;

one or more non-transitory computer-readable storage media storing one or more instructions executable by the one or more processors for;

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

identifying nuclei based in part on a size of one or more nuclei;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

receiving the tissue sample image information from a microscope, where the tissue sample image information includes at least a portion of image information of tissue stained with an immunohistochemical stain, and where the tissue sample image information includes an indication of levels in the stained tissue of a marker for a particular cancer;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei; and

outputting the cancer diagnosis score.

21. A method for causing a processor-based system to perform the following acts:

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

identifying nuclei based in part on a size of one or more nuclei;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

receiving the tissue sample image information from a microscope, where the tissue sample image information includes at least a portion of image information of tissue stained with an immunohistochemical stain, and where the tissue sample image information includes an indication of levels in the stained tissue of a marker for a particular cancer;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei; and

outputting the cancer diagnosis score.

22. A non-transitory computer-readable storage medium storing one or more computer programs adapted to cause a processor based system to execute steps comprising:

determining, from tissue sample image information in an optical density format, a first number of nuclei within the tissue sample image information;

determining, from the tissue sample image information in the optical density format, positive stain image information indicating positive stained content of the tissue sample image information;

determining, from the positive stain image information, a second number of positive stained nuclei within the tissue sample image information;

displaying on a display screen a displayed image of at least a portion of the positive stain image information, wherein the displayed image includes a plurality of pixels having values associated with analyzing the tissue sample image information to generate a cancer diagnosis score;

identifying one or more identified pixels corresponding to parts of the displayed image that meet a cancer scoring guideline by using the associated values of the pixels;

calculating a percentage of positive stained nuclei based at least in part on the first number and the second number, and the one or more identified pixels;

determining, from the positive stain image information, an intensity level of positive stain, the intensity level being selected from at least three predetermined levels indicating strength of the positive stain in the optical density format;

generating a cancer diagnosis score based at least in part on the percentage of positive stained nuclei and the intensity level; and

outputting the cancer diagnosis score.

23. The non-transitory computer-readable storage medium according to claim 22, wherein the intensity level of the positive stain is determined based on an average intensity of the positive stain.

24. The non-transitory computer-readable storage medium according to claim 22, further comprising:

identifying the positive stained nuclei based at least in part on the positive stain image information, wherein the intensity level of the positive stain is determined at least in part based on the identified positive stain nuclei.

25. The non-transitory computer-readable storage medium according to claim 24, wherein determining the second number of the positive stained nuclei includes:

comparing values in the positive stain image information with a predetermined threshold.

26. The non-transitory computer-readable storage medium according to claim 24, wherein the values in the positive stain image information include pixel values of a positive stain image included in the positive stain image information.

27. The non-transitory computer-readable storage medium according to claim 24, wherein said determining the second number of the positive stained nuclei further includes identifying positive stained nucleus centers based at least in part on a result of said comparing values.

28. The non-transitory computer-readable storage medium according to claim 24, further comprising:

visually indicating the percentage of positive stained nuclei in at least one portion of the displayed image.

29. The non-transitory computer-readable storage medium according to claim 24, further comprising:

visually indicating the intensity level in at least one portion of the displayed image.