US 12,133,635 B2
Endoscope processor, training device, information processing method, training method and program
Toshio Tachibana, Tokyo (JP)
Assigned to HOYA CORPORATION, Tokyo (JP)
Appl. No. 17/636,199
Filed by HOYA CORPORATION, Tokyo (JP)
PCT Filed Sep. 20, 2019, PCT No. PCT/JP2019/036940
§ 371(c)(1), (2) Date Feb. 17, 2022,
PCT Pub. No. WO2021/053808, PCT Pub. Date Mar. 25, 2021.
Prior Publication US 2022/0202284 A1, Jun. 30, 2022
Int. Cl. A61B 1/045 (2006.01); A61B 1/00 (2006.01); A61B 1/273 (2006.01)
CPC A61B 1/045 (2013.01) [A61B 1/000096 (2022.02); A61B 1/2736 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A processor for an endoscope comprising:
an image sensor that acquires an endoscope image;
a processor that inputs the endoscope image acquired by the image sensor to a first learning model that outputs a target region corresponding to a predetermined region to be photographed when the endoscope image is input to acquire the target region; and
a display that displays the endoscope image acquired by the image sensor and an index indicating the target region acquired by the processor with the endoscope image and the index superimposed,
wherein the processor outputs a guide for increasing the similarity between the endoscope image acquired by the image sensor and a reference image associated with a region to be photographed with the guide superimposed on the endoscope image.