US 12,285,151 B2
Target part identification among human-body internal images
Masahiro Saikou, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Filed by NEC Corporation, Tokyo (JP)
Filed on Mar. 13, 2024, as Appl. No. 18/603,473.
Application 18/603,473 is a continuation of application No. 17/258,296, granted, now 11,969,143, previously published as PCT/JP2018/025871, filed on Jul. 9, 2018.
Prior Publication US 2024/0215801 A1, Jul. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 1/00 (2006.01); A61B 5/00 (2006.01); A61B 34/10 (2016.01); G06T 7/73 (2017.01)
CPC A61B 1/000094 (2022.02) [A61B 1/000096 (2022.02); A61B 5/4887 (2013.01); A61B 5/7221 (2013.01); A61B 34/10 (2016.02); G06T 7/73 (2017.01); A61B 2034/107 (2016.02); G06T 2207/10048 (2013.01); G06T 2207/10068 (2013.01); G06T 2207/30096 (2013.01)] 9 Claims
OG exemplary drawing
 
6. A surgery assistance method comprising:
calculating, from a human-body internal image captured using an endoscope, feature extraction information, region information, confidence information, and heatmap information of a target part image corresponding to a target part, the feature extraction information indicating features of the target part image extracted from the human-body internal image, the region information indicating a position and a size of a window region with which a part or an entirety of an image corresponding to the target part is detected from the feature extraction information, the confidence information indicating probability of the image in the window region being an image corresponding to the target part, and the heatmap information being calculated using the feature extraction information;
calculating a similarity degree of the confidence information between different human-body internal images, including the human-body image;
calculating a similarity degree of the region information between the different human-body internal images based on determining whether the similarity degree of the confidence information is greater than or equal to a predetermined confidence value;
calculating a similarity degree of the feature extraction information based on determining whether the similarity degree of the region information is greater than or equal to a predetermined region value;
calculating a similarity degree of the heatmap information based on determining whether the similarity degree of the feature extraction information is greater than or equal to a predetermined feature extraction value; and
identifying the target part image in each of the different human-body internal images based on determining whether the similarity degree of the heatmap information is greater than or equal to a predetermined heatmap value.