Abstract

Info

Title:: Image classification of gastric precancerous lesions based on convolutional neural network

Author(s):: ZHANG Yu; ZHAO Yifeng; SU Zhuobin; YANG Yongjiang; Department of Gastrointestinal Tumor Surgery, the First Affiliated Hospital of Hebei North University, Zhangjiakou 075000, China

Keywords:: Keywords: gastric carcinoma erosion polyp ulcer precancerous lesion convolutional neural network image classification

Abstract:: Abstract: By building a model that can classify gastric precancerous lesions in a systematic and intelligent way, doctors can find sensitive points and precancerous polyps. An improved AlexNet architecture and techniques such as data enhancement, Gaussian noise, L2 weight decay and ReLU are used for training the convolutional neural network model and the performance of the proposed model is evaluated by analyzing its precision, loss value and confusion matrix. The proposed model is tested on 3 677 images of gastric diseases such as erosion, polyps and ulcers, and the results show that the classification accuracy of the proposed model reaches 89%.