US 11,676,361 B2
Computer-readable recording medium having stored therein training program, training method, and information processing apparatus
Akira Sakai, Kawasaki (JP); Masaaki Komatsu, Wako (JP); and Ai Dozen, Chuo (JP)
Assigned to FUJITSU LIMITED, Kawasaki (JP); RIKEN, Wako (JP); and NATIONAL CANCER CENTER, Tokyo (JP)
Filed by FUJITSU LIMITED, Kawasaki (JP); RIKEN, Wako (JP); and NATIONAL CANCER CENTER, Tokyo (JP)
Filed on Jan. 8, 2021, as Appl. No. 17/144,157.
Claims priority of application No. JP2020-014105 (JP), filed on Jan. 30, 2020.
Prior Publication US 2021/0241460 A1, Aug. 5, 2021
Int. Cl. G06T 7/11 (2017.01); G06N 3/04 (2023.01); G06V 10/30 (2022.01); G06T 5/50 (2006.01); G06T 7/00 (2017.01); G06F 18/214 (2023.01)
CPC G06V 10/30 (2022.01) [G06F 18/214 (2023.01); G06N 3/04 (2013.01); G06T 5/50 (2013.01); G06T 7/0012 (2013.01); G06T 7/11 (2017.01); G06T 2207/10132 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable recording medium having stored therein a training program that causes a computer to execute a process comprising:
acquiring training data including moving image data obtained by photographing a target and a plurality of annotation images each indicative of a region of the target in each of a plurality of frame images included in the moving image data; and
executing a training process using the training data,
wherein the training process comprises:
detecting the target included in the plurality of frame images;
inputting a combined image to an auto-encoder, the combined image being obtained by combining a plurality of partial images, each of the plurality of partial images including the target and a peripheral region of the target, the plurality of partial images being detected in a given number of preceding and succeeding second frame images in a time series of the moving image data of a first frame image from among the plurality of frame images;
inputting a partial image, in the plurality of partial images, corresponding to the first frame image to a neural network that performs a segmentation process for an image; and
performing parameter update of the auto-encoder and the neural network, based on a difference between a combination output image obtained by combining an output image from the auto-encoder and an output image from the neural network and a partial image of the annotation image indicative of a region of the target in the first frame image.