Optimized transfer learning for polyp detection

ECTI Transactions on Computer and Information Technology

article

Noppakun Boonsim¹  Saranya Kanjaruek¹ 

[1] Khon Kaen University

关键词: Polyp detection;    Transfer learning;    InceptionRestnetV2;   

DOI  :  10.37936/ecti-cit.2023171.250910

学科分类：医学（综合）

来源: Electrical Engineering/Electronics, Computer, Communications and Information Technology Association

【 摘 要 】

Early diagnosis of colorectal cancer focuses on detecting polyps in the colon as early as possible so that patients can have the best chances for success- ful treatment. This research presents the optimized parameters for polyp detection using a deep learning technique. Polyp and non-polyp images are trained on the InceptionResnetV2 model by the Faster Region Con- volutional Neural Networks (Faster R-CNN) framework to identify polyps within the colon images. The proposed method revealed more remarkable results than previous works, precision: 92.9 %, recall: 82.3%, F1-Measure: 87.3%, and F2-Measure: 54.6% on public ETIS-LARIB data set. This detection technique can reduce the chances of missing polyps during a pro- longed clinical inspection and can improve the chances of detecting multiple polyps in colon images.

【 授权许可】

CC BY-NC-ND