Mobile QR Code QR CODE : The Transactions of the Korean Institute of Electrical Engineers
Title Computer-aided Diagnosis System for Abnormalities Classification in Gastric Endoscopy Images using Machine Learning
Authors 이신애(Sin-ae Lee) ; 조현진(HyunChin Cho) ; 조현종(Hyun-chong Cho)
DOI https://doi.org/10.5370/KIEE.2020.69.1.107
Page pp.107-113
ISSN 1975-8359
Keywords CADx; Gastric Endoscopy; Image Feature Extraction; LS-SVM
Abstract Gastric cancer is the most common cancer and has been the number one incidence since 1999 in Korea(as of 2016). Gastrointestinal symptoms and functional gastrointestinal disorders comprise a large proportion of primary care and gastroenterology practice. We propose a Computer-aided Diagnosis (CADx) system that analyzing the traditional gastroscope images and help the medical experts improve the accuracy of medical diagnosis. The data set we used consists of 400 normal images and 285 abnormal images from 103 volunteers. We also extracted four color features and two texture features from each image. The Least Square Support Vector Machine(LS-SVM) classifier was used for normal and abnormal classification. LS-SVM finds the solution by solving a set of linear equations instead of a convex quadratic programming problem for classical SVMs. The AUC value was 0.85, which is 0.02 higher than that of normal SVM.