文献类型：期刊文献

英文题名：Colorectal polyp region extraction using saliency detection network with neutrosophic enhancement

作者：Hu, Keli[1,2];Zhao, Liping[2];Feng, Sheng[2];Zhang, Shengdong[2];Zhou, Qianwei[3];Gao, Xiaozhi[4];Guo, Yanhui[5]

机构：[1]Hangzhou Med Coll, Dept Gastroenterol, Zhejiang Prov Peoples Hosp, Affiliated Peoples Hosp,Canc Ctr, Hangzhou 310014, Peoples R China;[2]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[3]Zhejiang Univ Technol, Coll Comp Sci & Technol, Hangzhou 310023, Peoples R China;[4]Univ Eastern Finland, Joensuu 80101, Finland;[5]Univ Illinois, One Univ Plaza, Springfield, IL 62703 USA

年份：2022

卷号：147

外文期刊名：COMPUTERS IN BIOLOGY AND MEDICINE

收录：SCI-EXPANDED(收录号：WOS:000861569700004)、、EI(收录号：20222712331190)、Scopus(收录号：2-s2.0-85133456777)、WOS

基金：This work was supported in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LY20F020011, the Social Sciences and Humanities Youth Foundation of Ministry of Education under Grant 21YJCZH039, the Zhejiang Provincial Natural Science Foundation of China under Grant LTY22F020003, LY19F020015, the National Natural Science Foundation of China under Grant 61603258, 61871289, 61802347, 62002227, and in part by the Key scientific research project of Shaoxing University under Grant 2020LG1004.

语种：英文

外文关键词：Colorectal polyp; Polyp recognition; Polyp segmentation; Saliency detection; Short connection

外文摘要：Colorectal polyp recognition is crucial for early colorectal cancer detection and treatment. Colonoscopy is always employed for colorectal polyp scanning. However, one out of four polyps may be ignored, due to the similarity of polyp and normal tissue. In this paper, we present a novel method called NeutSS-PLP for polyp region extraction in colonoscopy images using a short connected saliency detection network with neutrosophic enhancement. We first utilize the neutrosophic theory to enhance the quality of specular reflections detection in the colonoscopy images. We develop the local and global threshold criteria in the single-valued neutrosophic set (SVNS) domain and define the corresponding T (Truth), I (Indeterminacy), and F (Falsity) functions for each criterion. The well-built neutrosophic images are processed and employed for specular reflection detection and suppressing. Next, we introduce two-level short connections into the saliency detection network, aiming to take advantage of the multi-level and multi-scale features extracted from different stages of the network. Experimental results conducted on two public colorectal polyp datasets achieve 0.877 and 0.9135 mIoU for polyp extraction respectively, and our method performs better compared with several state-of-the-art saliency networks and semantic segmentation networks, which demonstrate the effectiveness of applying the saliency detection mechanism for colorectal polyp region extraction.