US 12,169,963 B2
Processing system, image processing method, learning method, and processing device
Satoshi Ohara, Hachioji (JP)
Assigned to OLYMPUS CORPORATION, Tokyo (JP)
Filed by OLYMPUS CORPORATION, Tokyo (JP)
Filed on Sep. 8, 2022, as Appl. No. 17/940,224.
Application 17/940,224 is a continuation of application No. PCT/JP2020/010541, filed on Mar. 11, 2020.
Prior Publication US 2023/0005247 A1, Jan. 5, 2023
Int. Cl. G06T 7/00 (2017.01); A61B 1/00 (2006.01); A61B 1/06 (2006.01); G06T 7/73 (2017.01); G06V 10/25 (2022.01); G06V 10/70 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); H04N 23/60 (2023.01); H04N 23/61 (2023.01); G06V 10/141 (2022.01); H04N 23/50 (2023.01)
CPC G06V 10/776 (2022.01) [A61B 1/00006 (2013.01); A61B 1/0655 (2022.02); G06V 10/25 (2022.01); G06V 10/774 (2022.01); G06V 10/87 (2022.01); H04N 23/61 (2023.01); H04N 23/64 (2023.01); G06V 10/141 (2022.01); H04N 23/555 (2023.01)] 21 Claims
OG exemplary drawing
 
1. A processing system comprising:
a processor including hardware, wherein the processor is configured to:
acquire a first detection target image captured by an endoscope apparatus based on control using first control information;
detect a region of interest included in the first detection target image;
calculate estimated probability information, the estimated probability information representing a probability of the detected region of interest in the first detection target image, based on the first detection target image and a trained model acquired by machine learning;
identify second control information for improving the estimated probability information related to the region of interest in the first detection target image; and
control the endoscope apparatus based on the second control information.