System, program, and method for determining hypermutated tumor
A method, a program, and a method determining hypermutated type cancer with higher accuracy than before is provided. Provided is a system for determining hypermutated cancer comprising, an input unit configured to be capable of inputting a plurality of first image data, a plurality of second image data and a plurality of third image data, wherein the first image data represents an image of a pathological section of stained hypermutated cancer, the second image data represents an image of a pathological section of cancer which is not hypermutated, and is stained same as the pathological section of the first image data, and the third image data represents an image of a pathological section of cancer which is newly determined whether hypermutated or not, and is stained same as the pathological section of the first image data, a holding unit configured to be capable of holding a first image data and a second image data, a machine learning execution unit configured to be capable of generating a determination model determining whether a cancer is hypermutated or not, using the first image data and the second image data held by the holding unit as training data, and a determining unit configured to be capable of determining whether the third image data represents an image of hypermutated cancer or not, by inputting the third image data into the determination model.
1. A system for determining hypermutated cancer comprising:
an input unit configured to be capable of inputting a plurality of first image data, a plurality of second image data and a plurality of third image data, wherein
the first image data represents an image of a pathological section of stained hypermutated cancer,
the second image data represents an image of a pathological section of cancer which is not hypermutated, and is stained same as the pathological section of the first image data, and
the third image data represents an image of a pathological section of cancer which is newly determined whether hypermutated or not, and is stained same as the pathological section of the first image data;
a holding unit configured to be capable of holding a first image data and a second image data;
a machine learning execution unit configured to be capable of generating a determination model determining whether a cancer is hypermutated or not, using the first image data and the second image data held by the holding unit as training data; and
a determining unit configured to be capable of determining whether the third image data represents an image of hypermutated cancer or not, by inputting the third image data into the determination model.
2. The system of claim 1 , wherein
a method of staining the pathological section is hematoxylin eosin staining.
3. The system of claim 1 ,
the input unit is configured to be capable of further inputting non-cancer image data,
the non-cancer image data represents an image which is not a pathological section of cancer,
the holding unit is configured to be capable of further holding the non-cancer image data,
the machine learning execution unit is configured to be capable of further generating a determination model determining whether an image represents a pathological section of cancer or not, using the non-cancer image data held by the holding unit as training data,
the determining unit is configured to be capable of further determining whether the third image data represents an image of cancer or not.
4. The system of claim 1 , further comprising:
an image processing unit configured to be capable of performing a Z value conversion process for at least one of the first image data, the second image data and the non-cancer image data, converting each RGB color in each pixel into Z value in the CIE color system based on the entire color distribution of the first image data, the second image data or the non-cancer image data.
5. The system of claim 4 , wherein
the image processing unit is configured to be capable of performing a division process dividing at least one of the first image data, the second image data, and the non-cancer image data input into the input unit.
6. The system of claim 5 , wherein
the image processing unit performs the division process such that a part of the regions in a divided image overlaps each other.
7. The system of claim 5 ,
the image processing unit is configured to be further capable of performing a division process dividing the third image data input into the input unit.
8. The system of claim 3 , wherein
the determining unit determines whether the third image data represents an image of a pathological section of cancer or not, and further determines whether the image data determined as a cancer image data represents an image of hypermutated cancer or not.
9. The system of claim 8 , wherein
the determining unit determines whether a cancer image data represents an image of hypermutated cancer or not, based on the ratio of the image data determined as an image of hypermutated cancer in the cancer image data.
10. A non-transitory computer-readable storage medium storing a program for causing a computer to perform a process comprising:
inputting a plurality of first image data and a plurality of second image data, wherein
the first image data represents an image of a pathological section of stained hypermutated cancer and
the second image data represents an image of a pathological section of cancer which is not hypermutated, and is stained same as the pathological section of the first image data;
holding a first image data and a second image data; and
generating a determination model determining whether a cancer is hypermutated or not, using the first image data and the second image data held by the holding unit as training data.
11. The method of determining hypermutated cancer performed by the system of claim 1 .
12. The method of determining hypermutated cancer performed by the program stored in the storage medium of claim 10 .
13. The method of claim 11 including the process of determining the effectiveness of immune checkpoint inhibitors.