US 11,869,190 B2
System, program, and method for determining hypermutated tumor
Toshifumi Wakai, Niigata (JP); Shujiro Okuda, Niigata (JP); Yoshifumi Shimada, Niigata (JP); Hiroshi Izutsu, Tokyo (JP); and Keisuke Kodama, Tokyo (JP)
Assigned to Niigata University, Niigata (JP); and Denka Company Limited, Tokyo (JP)
Filed by Niigata University, Niigata (JP); and Denka Company Limited, Tokyo (JP)
Filed on Apr. 4, 2022, as Appl. No. 17/713,026.
Application 17/713,026 is a division of application No. 16/964,550, granted, now 11,295,447, previously published as PCT/JP2019/004499, filed on Feb. 7, 2019.
Claims priority of application No. 2018-024784 (JP), filed on Feb. 15, 2018.
Prior Publication US 2022/0301167 A1, Sep. 22, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06T 7/00 (2017.01); G01N 1/30 (2006.01); G01N 33/483 (2006.01)
CPC G06T 7/0014 (2013.01) [G01N 1/30 (2013.01); G01N 33/4833 (2013.01); G01N 2001/302 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30028 (2013.01); G06T 2207/30096 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer system for determining hypermutated cancer comprising one or more computers programmed to perform steps comprising:
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;
holding a first image data and a second image data;
performing a Z value conversion process of the first image data, the second image data and the third 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 and the third 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 converted by the Z value conversion process and held as training data; and
determining whether the third image data represents an image of hypermutated cancer or not, by inputting the third image data converted by the Z value conversion process into the determination model.