Method and system for predicting expression of biomarker from medical image

1. A method comprising:

obtaining a medical image created by capturing at least one part of a patient's body without tissue collection; and

using at least one processor:

inputting the medical image to a machine learning model;

outputting information related to a biomarker expression for each of a plurality of lesions in the medical image by using the machine learning model, wherein the plurality of lesions are detected in the medical image; and

determining information associated with tissue collection for the plurality of lesions in the medical image based on the information related to the biomarker expression.

2. The method according to claim 1 , wherein the outputting the information related to the biomarker expression comprises:

extracting regions containing at least one of the plurality of lesions from the medical image; and

cropping the regions to generate partial images.

3. The method according to claim 2 , wherein the outputting the information related to the biomarker expression further comprises inputting the partial images to the machine learning model to output the information related to the biomarker expression.

4. The method according to claim 2 , wherein the outputting the information related to the biomarker expression further comprises inputting the medical image and the partial images to the machine learning model to output the information related to the biomarker expression.

5. The method according to claim 2 , further comprising:

determining segmentation information of each of the plurality of lesions,

wherein the outputting the information related to the biomarker expression comprises inputting the segmentation information and the partial images to the machine learning model to output the information related to the biomarker expression.

6. The method according to claim 2 , further comprising:

acquiring different information related to biomarker expression for a different lesion from the plurality of lesions,

wherein the outputting the information related to the biomarker expression comprises inputting the different information related to the biomarker expression of the different lesion and the partial images to the machine learning model to output the information related to the biomarker expression.

7. The method according to claim 1 ,

wherein the obtaining the medical image comprises obtaining a first medical image of at least one part of the patient's body and a second medical image of at least one part of the patient's body captured at different time points, and

wherein the outputting the information related to the biomarker expression comprises:

extracting regions for the plurality of lesions from each of the first medical image and the second medical image; and

inputting the regions extracted from the first medical image and the regions extracted from the second medical image to the machine learning model to output the information related to the biomarker expression.

8. The method according to claim 1 , wherein the information associated with the tissue collection includes at least one of: information on a method of the tissue collection, information on a location of the tissue collection, or a priority of the tissue collection.

9. The method according to claim 1 , further comprising:

outputting information on priorities of the tissue collection for each of the plurality of lesions.

10. The method according to claim 9 , further comprising:

acquiring reference information on the tissue collection associated with the medical image,

wherein the outputting the information on the priorities of the tissue collection for each of the plurality of lesions comprises determining the priorities of the tissue collection for each of the plurality of lesions based on the information related to the biomarker expression and the reference information.

11. An information processing system comprising:

at least one memory storing one or more instructions; and

at least one processor connected to the at least one memory and configured to execute the one or more instructions to:

obtain a medical image created by capturing at least one part of a patient's body without tissue collection,

input the medical image to a machine learning model,

output information related to a biomarker expression for each of a plurality of lesions by using the machine learning model, wherein the plurality of lesions are detected in the medical image, and

determine information associated with tissue collection for the plurality of lesions in the medical image based on the information related to the biomarker expression.

12. The information processing system according to claim 11 , wherein the at least one processor is further configured to execute the one or more instructions to:

extract regions containing at least one of the plurality of lesions from the medical image; and

crop the regions to generate partial images.

13. The information processing system according to claim 12 , wherein the at least one processor is further configured to execute the one or more instructions to:

input the partial images to the machine learning model to output the information related to the biomarker expression.

14. The information processing system according to claim 12 , wherein the at least one processor is further configured to execute the one or more instructions to:

input the medical image and the partial images to the machine learning model to output the information related to the biomarker expression.

15. The information processing system according to claim 12 , wherein the at least one processor is further configured to execute the one or more instructions to:

determine segmentation information of each of the plurality of lesions; and

input the segmentation information and the partial images to the machine learning model to output the information related to the biomarker expression.

16. The information processing system according to claim 12 , wherein the at least one processor is further configured to execute the one or more instructions to:

acquire different information related to biomarker expression for a different lesion from the plurality of lesions; and

input the different information related to the biomarker expression of the different lesion and the partial images to the machine learning model to output the information related to the biomarker expression.

17. The information processing system according to claim 11 , wherein the at least one processor is further configured to execute the one or more instructions to:

receive a first medical image of the patient's body and a second medical image of the patient's body captured at different time points;

extract regions for the plurality of lesions from each of the first medical image and the second medical image; and

input the regions extracted from the first medical image and the regions extracted from the second medical image to the machine learning model to output the information related to the biomarker expression.

18. The information processing system according to claim 11 , wherein the information associated with the tissue collection includes at least one of: information on a method of the tissue collection, information on a location of the tissue collection, or a priority of the tissue collection.

19. The information processing system according to claim 11 , wherein the at least one processor is further configured to execute the one or more instructions to:

output information on priorities of the tissue collection for each of the plurality of lesions.

20. The information processing system according to claim 19 , wherein the at least one processor is further configured to execute the one or more instructions to:

acquire reference information on the tissue collection associated with the medical image; and

determine the priorities of the tissue collection for each of the plurality of lesions based on the information related to the biomarker expression and the reference information.