Method and system for assessing fibrosis in a tissue sample

1. A computer-implemented method of assessing fibrosis in a tissue sample using at least one processor, the method comprising:

obtaining a stained image of a stained tissue sample, the stained tissue sample being stained in relation to collagen therein;

producing a plurality of different types of collagen images based on the stained image, the plurality of different types of collagen images corresponding to a plurality of different types of collagen, respectively;

determining a plurality of different types of collagen parameters based on the plurality of different types of collagen images using a deep neural network; and

determining a degree of fibrosis in the stained tissue sample based on the plurality of different types of collagen parameters.

2. The method of claim 1 , wherein said producing a plurality of different types of collagen images comprises:

producing a first image corresponding to tissue in the stained image; and

producing a second image corresponding to collagen in the stained image.

3. The method of claim 2 , wherein said producing a plurality of different types of collagen images further comprises:

producing a third image corresponding to portal tracts and central veins in the first image.

4. The method of claim 3 , wherein said producing a plurality of different types of collagen images further comprises:

producing a first binarized image based on the second image;

producing a second binarized image based on the third image; and

producing the plurality of different types of collagen images based on the first and second binarized images.

5. The method of claim 4 , wherein the first and second images are produced based on K-mean clustering.

6. The method of claim 4 , wherein the plurality of different types of collagen images comprises a first type, a second type, and a third type of collagen images, and said producing the plurality of different types of collagen images based on the first and second binarized images comprises:

producing the first type of collagen image based on collagen in the first binarized image satisfying a predetermined size condition;

producing the second type of collagen image based on collagen in the first binarized image satisfying a predetermined distance condition with respect to a boundary of the portal tracts and the central veins in the second binarized image; and

producing the third type of collagen image based on collagen in the first binarized image that does not satisfy the predetermined size condition and the predetermined distance condition.

7. The method of claim 1 , wherein the plurality of different types of collagen comprises portal collagen, fibrillar collagen and septal collagen.

8. The method of claim 1 , wherein the plurality of different types of collagen parameters each comprises a quantitative fibrosis value in relation to the corresponding type of collagen of the plurality of different types of collagen in the stained tissue sample.

9. The method of claim 1 , wherein the degree of fibrosis in the tissue sample is determined based on the different types of collagen parameters using a multinomial logistic regression.

10. The method of claim 1 , wherein the deep neural network comprises a plurality of deep neural sub-networks corresponding to the plurality of different types of collagen respectively, wherein each deep neural sub-network of the plurality of deep neural sub-networks is configured to output a quantitative fibrosis value in relation to a respective type of collagen.

11. A system for assessing fibrosis in a tissue sample, the system comprising:

a memory; and

at least one processor communicatively coupled to the memory and configured to:

obtain a stained image of a stained tissue sample, the stained tissue sample being stained in relation to collagen therein;

produce a plurality of different types of collagen images based on the stained image, the plurality of different types of collagen images corresponding to a plurality of different types of collagen, respectively;

determine a plurality of different types of collagen parameters based on the plurality of different types of collagen images using a deep neural network; and

determine a degree of fibrosis in the stained tissue sample based on the plurality of different types of collagen parameters.

12. The system according to claim 11 , wherein said produce a plurality of different types of collagen images comprises:

producing a first image corresponding to tissue in the stained image; and

producing a second image corresponding to collagen in the stained image.

13. The system according to claim 12 , wherein said produce a plurality of different types of collagen images further comprises:

producing a third image corresponding to portal tracts and central veins in the first image.

14. The system according to claim 13 , wherein said produce a plurality of different types of collagen images further comprises:

producing a first binarized image based on the second image;

producing a second binarized image based on the third image; and

producing the plurality of different types of collagen images based on the first and second binarized images.

15. The system according to claim 14 , wherein the first and second images are produced based on K-mean clustering.

16. The system according to claim 14 , wherein the plurality of different types of collagen images comprises a first type, a second type, and a third type of collagen images, and said produce the plurality of different types of collagen images based on the first and second binarized images comprises:

producing the first type of collagen image based on collagen in the first binarized image satisfying a predetermined size condition;

producing the second type of collagen image based on collagen in the first binarized image satisfying a predetermined distance condition with respect to a boundary of the portal tract and/or the central vein in the second binarized image; and

producing the third type of collagen image based on collagen in the first binarized image that does not satisfy the predetermined size condition and the predetermined distance condition.

17. The system according to claim 11 , wherein the plurality of different types of collagen comprises portal collagen, fibrillar collagen and septal collagen.

18. The system according to claim 11 , wherein the plurality of different types of collagen parameters each comprises a quantitative fibrosis value in relation to the corresponding type of collagen of the plurality of different types of collagen in the stained tissue sample.

19. The system according to claim 11 , wherein the degree of fibrosis in the tissue sample is determined based on the different types of collagen parameters using a multinomial logistic regression.

20. A computer program product, embodied in one or more non-transitory computer-readable storage mediums, comprising instructions executable by at least one processor to perform a method of assessing fibrosis in a tissue sample, the method comprising:

obtaining a stained image of a stained tissue sample, the stained tissue sample being stained in relation to collagen therein;

producing a plurality of different types of collagen images based on the stained image, the plurality of different types of collagen images corresponding to a plurality of different types of collagen, respectively;

determining a plurality of different types of collagen parameters based on the plurality of different types of collagen images using a deep neural network; and

determining a degree of fibrosis in the stained tissue sample based on the plurality of different types of collagen parameters.