System for predicting the recurrence of cancer in a cancer patient

• US 10,579,935 B2
• Filed: 08/11/2019
• Issued: 03/03/2020
• Est. Priority Date: 03/20/2016
• Status: Active Grant

• Current Assignee: Definiens GmbH (Astrazeneca PLC)
• Original Assignee: Definiens AG (Astrazeneca PLC)
• Inventors: Harder, Nathalie, Athelogou, Maria
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US16/537,619
• Publication Number:
  US 20190362259A1
• Time in Patent Office: 205 Days
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 2207/30024 Cell structures in vitro; Tissue sections in vitro
• CPC Class Codes: G06T 2207/30081 Prostate
• CPC Class Codes: G06T 2207/30242 Counting objects in image
• CPC Class Codes: G06T 7/0012 Biomedical image inspection

Abstract

A system predicts the recurrence of cancer. A first slice of a prostate tissue sample is stained so that luminal epithelial cells and basal epithelial cells are stained different colors. A first digital image is taken of the first slice. The second slice of the sample is stained so that M1 type macrophages and M2 type macrophages are differentially stained. A second digital image is taken of the second slice. The system analyzes the first digital image and defines regions of non-intact glands. Intact gland regions are then determined, and regions of stroma are identified. The system defines influence zones between non-intact regions and stroma regions. Using information from the second image, macrophages in the tissue corresponding to the influence zones are identified and counted. Based at least in part on this count, the system determines a score. The score is indicative of whether the patient will experience PSA recurrence.

Claims

1. A method involving a system for predicting a risk of cancer recurrence in a patient, the method comprising:

(a) reading a portion of a digital image from a storage device, wherein the digital image was acquired by a digital camera imaging a tissue section removed from the patient, wherein the tissue section was immunohistochemically stained with a first stain marking M1 macrophages with a first color so that the digital image includes first color information, and with a second stain marking M2 macrophages a second color so that the digital image includes second color information;

(b) using geometric region information to identify a region of the portion of the digital image;

(c) detecting first and second objects in the portion of the digital image, wherein the detecting involves using the first color information, the second color information, a predefined object size lower threshold, and a predefined object size upper threshold;

(d) counting those first objects that are not located in the region identified in (b) but rather are disposed within a predetermined distance of the region, wherein the counting of (d) results in a first object count;

(e) counting those second objects that are not located in the region identified in (b) but rather are disposed within the predetermined distance of the region, wherein the counting of (e) results in a second object count;

(f) computing a score using the first object count and using the second object count, wherein the score predicts the risk of cancer recurrence in the patient; and

(g) storing the score to a storage device, wherein (a) through (g) are performed by the system.

2. The method of claim 1, wherein the geometric region information of (b) is generated outside the system, the method further comprising:

receiving the geometric region information onto the system.

3. The method of claim 1, further comprising:

generating the geometric region information on the system.

4. The method of claim 1, wherein some regions of the portion of the digital image are stroma regions of stroma cells, and wherein other regions of the portion of the digital image are intact regions of intact gland cells, wherein the counting of (d) involves counting first objects that are located in both stroma regions and in intact regions, and wherein the counting of (e) involves counting second objects that are located in both stroma regions and in intact regions.

5. The method of claim 1, wherein some regions of the portion of the digital image are stroma regions of stroma cells, and wherein other regions of the portion of the digital image are intact regions of intact gland cells, wherein the counting of (d) involves counting first objects that are located in stroma regions but not in intact regions, and wherein the counting of (e) involves counting second objects that are located in stroma regions but not in intact regions.

6. The method of claim 1, wherein the score predicts that the patient will likely have a recurrence of measurable prostate-specific antigen (PSA) in the patient'"'"'s blood.

7. The method of claim 1, wherein the second stain is cluster of differentiation 163 (CD163).

8. The method of claim 1, wherein the first stain is a double stain comprising cluster of differentiation 68 (CD68) and cluster of differentiation 163 (CD163).

9. The method of claim 1, wherein the predetermined distance is 150 microns or more.

10. The method of claim 1, wherein the first and second objects are macrophages.

11. A method involving a system for predicting a risk of cancer recurrence in a patient, the method comprising:

(a) performing image analysis on a digital image of a tissue sample removed from the patient, wherein the tissue sample was immunohistochemically stained with a first stain marking M1 macrophages with a first color so that the digital image includes first color information, and with a second stain marking M2 macrophages a second color so that the digital image includes second color information;

(b) identifying a non-intact region of non-intact gland cells of the tissue sample in the digital image;

(c) identifying a stroma region of stroma cells of the tissue sample in the digital image;

(d) detecting first and second objects in the digital image, wherein the detecting involves using the first color information, the second color information, a predefined object size lower threshold, and a predefined object size upper threshold;

(e) counting those first objects that are disposed in the stroma region within a predetermined distance of the non-intact region, wherein the counting of (e) results in a first object count;

(f) counting those second objects that are disposed in the stroma region within the predetermined distance of the non-intact region, wherein the counting of (f) results in a second object count; and

(g) computing a score using the first object count and using the second object count, wherein the score predicts the risk of cancer recurrence in the patient, and wherein (a) through (g) are performed by the system.

12. The method of claim 11, further comprising:

(h) identifying an intact region of intact gland cells, wherein the counting of (e) involves counting first objects that are located in intact regions as well as those first objects that are disposed in stroma regions within a predetermined distance of non-intact regions, and wherein the counting of (f) involves counting second objects that are located in intact regions as well as those second objects that are disposed in stroma regions within the predetermined distance of non-intact regions.

13. The method of claim 11, wherein the score predicts that the patient will likely have a recurrence of measurable prostate-specific antigen (PSA) in the patient'"'"'s blood.

14. The method of claim 11, wherein the second stain is cluster of differentiation 163 (CD163).

15. The method of claim 11, wherein the first stain is a double stain comprising cluster of differentiation 68 (CD68) and cluster of differentiation 163 (CD163).

16. The method of claim 11, wherein the predetermined distance is 150 microns or more.

17. The method of claim 11, wherein the first and second objects are macrophages.

18. The method of claim 11, further comprising:

(h) storing the score to a storage device of the system.

19. The method of claim 11, further comprising:

(h) displaying the score on a display device of the system.