Gastric Section Correlation Network for Gastric Precancerous Lesion Diagnosis

Jyun Yao Jhang, Yu Ching Tsai, Tzu Chun Hsu, Chun Rong Huang, Hsiu Chi Cheng, Bor Shyang Sheu

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

&#x00A0; <italic>Goal:</italic> Diagnosing the corpus-predominant gastritis index (CGI) which is an early precancerous lesion in the stomach has been shown its effectiveness in identifying high gastric cancer risk patients for preventive healthcare. However, invasive biopsies and time-consuming pathological analysis are required for the CGI diagnosis. <italic>Methods:</italic> We propose a novel gastric section correlation network (GSCNet) for the CGI diagnosis from endoscopic images of three dominant gastric sections, antrum, body and cardia. The proposed network consists of two dominant modules including the scaling feature fusion module and section correlation module. The front one aims to extract scaling fusion features which can effectively represent the mucosa under variant viewing angles and scale changes for each gastric section. The latter one aims to apply the medical prior knowledge with three section correlation losses to model the correlations of different gastric sections for the CGI diagnosis. <italic>Results:</italic> The proposed method outperforms competing deep learning methods and achieves high testing accuracy, sensitivity, and specificity of 0.957, 0.938 and 0.962, respectively. <italic>Conclusions:</italic> The proposed method is the first method to identify high gastric cancer risk patients with CGI from endoscopic images without invasive biopsies and time-consuming pathological analysis.

Original languageEnglish
Pages (from-to)1-9
Number of pages9
JournalIEEE Open Journal of Engineering in Medicine and Biology
DOIs
Publication statusAccepted/In press - 2023

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Fingerprint

Dive into the research topics of 'Gastric Section Correlation Network for Gastric Precancerous Lesion Diagnosis'. Together they form a unique fingerprint.

Cite this