Texture branch network for chronic kidney disease screening based on ultrasound images

作     者：Peng-yi HAO Zhen-yu XU Shu-yuan TIAN Fu-li WU Wei CHEN Jian WU Xiao-nan LUO Peng-yi HAO;Zhen-yu XU;Shu-vuan TIAN;Fu-li WU;Wei CHEN;Jian WU;Xiao-nan LUO

作者机构：College of Computer Science and TechnologyZhejiang University of TechnologyHangzhou 310023China Tongde Hospital of Zhejiang ProvinceHangzhou 310012China The First Affiliated HospitalZhejiang UniversityHangzhou 310003China College of Computer Science and TechnologyZhejiang UniversityHangzhou 310027China Real Doctor AI Research CenterZhejiang UniversityHangzhou 310027China Institute of Artificial IntelligenceGuilin University of Electronic TechnologyGuilin 541004China 

出 版 物：《Frontiers of Information Technology & Electronic Engineering》 (信息与电子工程前沿（英文版）)

年 卷 期：2020年第21卷第8期

页      面：1161-1170页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the Zhejiang Provincial Natural Science Foundation of China (No. LY18F020034) the Zhejiang Provincial Medical Health Science and Technology Project China(No. 2014KYB320) the National Natural Science Foundation of China (Nos. 61801428 and 61672543) the Zhejiang University Education Foundation China (Nos. K18-511120-004 and K17-511120-017) the Major Scientific Project of Zhejiang Lab China (No. 2018DG0ZX01) 

主　　题：Chronic kidney disease Ultrasound Texture branch network Transfer learning 

摘      要：Chronic kidney disease(CKD) is a widespread renal disease throughout the world. Once it develops to the advanced stage, serious complications and high risk of death will follow. Hence, early screening is crucial for the treatment of CKD. Since ultrasonography has no side effects and enables radiologists to dynamically observe the morphology and pathological features of the kidney, it is commonly used for kidney examination. In this study,we propose a novel convolutional neural network(CNN) framework named the texture branch network to screen CKD based on ultrasound images. This introduces a texture branch into a typical CNN to extract and optimize texture features. The model can automatically generate texture features and deep features from input images, and use the fused information as the basis of classification. Furthermore, we train the base part of the network by means of transfer learning, and conduct experiments on a dataset with 226 ultrasound images. Experimental results demonstrate the effectiveness of the proposed approach, achieving an accuracy of 96.01% and a sensitivity of 99.44%.