Osteoporotic Vertebral Fracture Classification in X-rays Based on a Multi-modal Semantic Consistency Network

作     者：Yuzhao Wang Tian Bai Tong Li Lan Huang Yuzhao Wang;Tian Bai;Tong Li;Lan Huang

作者机构：College of Computer Science and TechnologyJilin UniversityChangchun130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun130012China Department of OrthopedicsThe Second Hospital of Jilin UniversityChangchun130012China 

出 版 物：《Journal of Bionic Engineering》 (仿生工程学报（英文版）)

年 卷 期：2022年第19卷第6期

页      面：1816-1829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] 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：National Natural Science Foundation of China(U21A20390) National Key Research and Development Program of China(2018YFC2001302) Development Project of Jilin Province of China(nos.20200801033GH,20200403172SF,YDZJ202101ZYTS128) Jilin Provincial Key Laboratory of Big Data Intelligent Computing(no.20180622002JC) The Fundamental Research Funds for the Central University,JLU 

主　　题：Osteoporotic vertebral fracture classification Cross-modality Unsupervised domain adaptation Transfer learning Convolutional neural network Computer-aided diagnosis 

摘      要：Osteoporotic Vertebral Fracture(OVFs)is a common lumbar spine disorder that severely affects the health of *** a clear bone blocks boundary,CT images have gained obvious advantages in OVFs *** with CT images,X-rays are faster and more inexpensive but often leads to misdiagnosis and miss-diagnosis because of the overlapping *** how to transfer CT imaging advantages to achieve OVFs classification in X-rays is *** this purpose,we propose a multi-modal semantic consistency network which could do well X-ray OVFs classification by transferring CT semantic consistency *** from existing methods,we introduce a feature-level mix-up module to get the domain soft labels which helps the network reduce the domain offsets between CT and *** the meanwhile,the network uses a self-rotation pretext task on both CT and X-ray domains to enhance learning the high-level semantic invariant *** employ five evaluation metrics to compare the proposed method with the state-of-the-art *** final results show that our method improves the best value of AUC from 86.32 to 92.16%.The results indicate that multi-modal semantic consistency method could use CT imaging features to improve osteoporotic vertebral fracture classification in X-rays effectively.