US 12,437,509 B2
Medical image processing apparatus, method, and storage medium
Fuyue Wang, Beijing (CN); Yanhua Wang, Beijing (CN); and Qilin Xiao, Beijing (CN)
Assigned to CANON MEDICAL SYSTEMS CORPORATION, Tochigi (JP)
Filed by CANON MEDICAL SYSTEMS CORPORATION, Tochigi (JP)
Filed on Dec. 14, 2022, as Appl. No. 18/065,718.
Claims priority of application No. 202111534705.8 (CN), filed on Dec. 15, 2021; and application No. 2022-175338 (JP), filed on Nov. 1, 2022.
Prior Publication US 2023/0186603 A1, Jun. 15, 2023
Int. Cl. G06V 10/764 (2022.01); G06V 10/26 (2022.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/764 (2022.01) [G06V 10/267 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01); G06V 2201/031 (2022.01)] 9 Claims
OG exemplary drawing
 
1. A medical image processing apparatus comprising:
processing circuitry configured to
receive a medical image of a target region,
generate an image pair including a local image having local features of the target region and a global image having global features of the target region on the basis of the received medical image,
perform segmentation using a first neural network to locate the target region in the local image,
perform classification using a second neural network to classify the target region in the global image by type, the classification for the global image being a rough classification that roughly classifies the type of target region, and
input a segmentation result and a classification result into a third neural network to generate a classified image of the target region, the classified image of the target region being an image in which the type of target region is precisely classified.