基于CNN的胶囊内窥镜图像胃肠道疾病预测分析

Analysis of Prediction of Gastrointestinal Diseases in Capsule Endoscopy Images Based on CNN

阐述一种利用卷积神经网络结构来网络检测WCE图像疾病的学习方法。并且在深度学习检测WCE图像的过程中尝试了众多解决数据匮乏的方法。其中包括数据扩充、迁移学习、少数据学习和无监督学习。实验结果表明,即使在数据量较少的情况下,该方法可以实现一个高效、准确的WCE疾病检测深度学习模型,能够达到86.7%的准确率。

This paper expounds a learning method using convolutional neural network structure to detect WCE image diseases.And in the process of deep learning to detect WCE images,many methods have been tried to solve the problem of data shortage.It includes data expansion,transfer learning,little data learning and unsupervised learning.The experimental results show that this method can achieve an efficient and accurate WCE disease detection depth learning model even when the amount of data is small,and the accuracy can reach 86.7%.