• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学 ›› 2020, Vol. 42 ›› Issue (10高性能专刊): 1827-1832.

• 高性能计算机系统应用 • 上一篇    下一篇

基于多尺度卷积神经网络的胶囊内窥镜出血点快速识别

谢雪娇1,陆枫2,李书展2,周到3   

  1. (1.华中科技大学同济医学院附属同济医院,湖北 武汉 430030;

    (2.华中科技大学计算机学院大数据技术与系统国家工程研究中心,湖北 武汉 430074;

    3.中南民族大学生物医学工程学院认知科学国家民委重点实验室,湖北 武汉 430074)

  • 收稿日期:2020-04-30 修回日期:2020-07-15 接受日期:2020-10-25 出版日期:2020-10-25 发布日期:2020-10-23
  • 基金资助:
    中南民族大学中央高校科研基本业务费(CZY20039,CZQ18013)

Quick bleeding point detection in WCE image based on multi-scale convolutional neural network

XIE Xue-jiao1,LU Feng2,LI Shu-zhan2,ZHOU Dao3   

  1. (1.Tongji Hospital,Tongji Medical College,Huazhong University of Science and Technology,Wuhan 430030;

    2.National Engineering Research Center for Big Data Technology and System,

    School of Computer Science and Technology,Huazhong University of Science and Technology,Wuhan 430074;

    3.Key Laboratory of Cognitive Science,School of Biomedical Engineering,

    South-Central University for Nationalities,Wuhan 430074,China)

  • Received:2020-04-30 Revised:2020-07-15 Accepted:2020-10-25 Online:2020-10-25 Published:2020-10-23

摘要: 无线胶囊内窥镜技术WCE已广泛应用于胃肠道疾病辨识中,然而随之产生的海量影像学数据为医生阅片带来了沉重负担。针对WCE图像出血点自动识别中存在的颜色和纹理特征不明显、易与正常器官混淆,细节特征模糊与病灶尺寸大小不一,以及含有较多杂质等问题,提出残差多尺度全卷积神经网络对含出血点的WCE图像进行快速分类辨识。通过引入残差学习网络中跳跃连接以及Inception网络中多尺度卷积核的思想,使简洁的网络结构能够有效提取图像的各类病灶细节特征。从实验结果看,网络的灵敏度达到98.05%,特异度达到97.67%,准确率达到97.84%,优于ResNet50和Inception-v4网络,识别效率高,且收敛速度更快,计算性能有所提升。总之,该网络兼顾出血点识别效率和性能,实用性较强。

关键词: 深度学习, 无线胶囊内窥镜, 卷积神经网络, 残差网络, 多卷积核

Abstract: With the full application of Wireless Capsule Endoscopy (WCE) in the detection of gastrointestinal diseases, screening out a small number of lesion images from the massive imaging data brings a heavy burden to doctors. To solve the problems existing in the automatic detection of WCE images, such as inconspicuous colour and texture features, ease of being confused with healthy organs, fuzzy detail features and different sizes of lesions, and high impurities, we propose a residual-based multi-scale fully convolutional neural network to classify and detect lesions in WCE image. By introducing the concepts of skip connection in residual learning network and multi-scale convolution kernel in the inception network, the model can effectively extract the detailed features of various lesions in the image. The experimental results show that the sensitivity of the model reaches 98.05%, the specificity reaches 97.67%, and the accuracy reaches 97.84%. It is better than the classical deep residual network ResNet50 and the standard width multi-scale Inception-v4 algorithm. The model has high recognition rate, fast convergence speed, and improved computing performance. In short, the algorithm model takes into account the efficiency and performance of bleeding  point detection, and has strong practicability.



Key words: deep learning, wireless capsule endoscopy, convolutional neural network, residual network, multiple convolution kernels