Abstract: A method for detection and pathological classification of polyps via colonoscopy based on an anchor-free technique includes: performing feature extraction on a color endoscopic image that is pretreated, enhancing and extending the extracted features, decoding the feature information of the enhanced feature and the extended feature through an anchor-free detection algorithm to acquire a polyp prediction box and a prospect prediction mask, then respectively extracting global and local feature vectors from the extended feature and the prospect prediction mask, and combining the global feature vector with the local feature vector, so as to predict the type of polyps through a full-connection layer. Through the present application, the type of polyps can be correctly predicted, and the detection rate of polyps and the accuracy rate of pathological classification are improved.
Type:
Grant
Filed:
April 8, 2022
Date of Patent:
April 9, 2024
Assignee:
HIGHWISE CO, LTD.
Inventors:
Yu Cao, Xinzi Sun, Qilei Chen, Benyuan Liu
Abstract: A method for detection and pathological classification of polyps via colonoscopy based on an anchor-free technique includes: performing feature extraction on a color endoscopic image that is pretreated, enhancing and extending the extracted features, decoding the feature information of the enhanced feature and the extended feature through an anchor-free detection algorithm to acquire a polyp prediction box and a prospect prediction mask, then respectively extracting global and local feature vectors from the extended feature and the prospect prediction mask, and combining the global feature vector with the local feature vector, so as to predict the type of polyps through a full-connection layer. Through the present application, the type of polyps can be correctly predicted, and the detection rate of polyps and the accuracy rate of pathological classification are improved.
Type:
Application
Filed:
April 8, 2022
Publication date:
February 8, 2024
Applicant:
HIGHWISE CO, LTD.
Inventors:
Yu CAO, Xinzi SUN, Qilei CHEN, Benyuan LIU