US 11,756,190 B2
Cell image evaluation device, method, and program
Kenta Matsubara, Ashigarakami-gun (JP); and Takashi Wakui, Ashigarakami-gun (JP)
Assigned to FUJIFILM Corporation, Tokyo (JP)
Filed by FUJIFILM Corporation, Tokyo (JP)
Filed on Aug. 16, 2019, as Appl. No. 16/543,301.
Application 16/543,301 is a continuation of application No. PCT/JP2018/008085, filed on Mar. 2, 2018.
Claims priority of application No. 2017-067954 (JP), filed on Mar. 30, 2017.
Prior Publication US 2019/0370967 A1, Dec. 5, 2019
Int. Cl. G06T 7/00 (2017.01)
CPC G06T 7/0012 (2013.01) [G06T 2207/10056 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30024 (2013.01); G06T 2207/30168 (2013.01)] 12 Claims
OG exemplary drawing
 
1. A cell image evaluation device comprising:
a processor configured to:
receive a plurality of captured images obtained by capturing divided regions each corresponding to a part to be observed inside a container that contains a cell;
for each of the plurality of captured images:
determine whether or not the captured image is deteriorated;
after it is determined whether or not the captured image is deteriorated, evaluate a state of the cell included in the captured image by applying, to the entire captured image, an evaluation method using a feature value indicating the state of the cell included in the captured image in a case where it is determined that the captured image is not deteriorated, and evaluate the state of the cell included in the captured image by applying, to the entire captured image, an evaluation method using an image feature value in a case where it is determined that the captured image is deteriorated; and
integrate all of evaluation results of the plurality of the captured images obtained by capturing the container, and calculate an evaluation result for the entire container, the calculation including adding different weights to the evaluation result of the captured image determined to be deteriorated and the evaluation result of the captured image determined not to be deteriorated,
wherein the image feature value is at least one of entropy of the captured image or a spatial frequency distribution of the captured image.