基于深度学习的肺结核检测综述  

Review on tuberculosis detection using deep learning

作　　者：谢浩杰 鲁明丽[2] 张陈 周理想 滕诣迪 王明明 XIE Haojie;LU Mingi;ZHANG Chen;ZHOU Lixiang;TENG Yidi;WANG Mingming(School of Electrical Engineering,Yancheng Institute of Technology,Yancheng 221051,China;School of Electrical and Automation Engineering,Changshu Institute of Technology,Changshu 215500,China;School of Mechanical and Electrical Engineering,Soochow University,Suzhou 215031,China;School of Electronic and Information Engineering,Changshu Institute of Technology,Changshu 215500,China)

机构地区：[1]盐城工学院电气工程学院,江苏盐城221051 [2]常熟理工学院电气与自动化工程学院,江苏常熟215500 [3]苏州大学机电工程学院,江苏苏州215031 [4]常熟理工学院电子信息工程学院,江苏常熟215500

出　　处：《中国医学物理学杂志》2024年第7期918-924,共7页Chinese Journal of Medical Physics

基　　金：苏州市科技计划项目(SYG202129)。

摘　　要：基于医学影像的肺结核病灶自动检测技术成为医学图像处理领域的研究热点。本研究围绕深度学习在肺结核病灶检测方面的相关研究与应用展开综述,首先阐述用于肺结核检测的实验基准,涵盖肺部医学影像的相关公开数据库和肺结核检测与分类竞赛的相关研究进展,然后提出肺结核检测领域中深度学习方法与应用的发展趋势,最后分析深度学习在肺结核诊断中面临的挑战。本研究从技术特性、性能优势、应用前景等方面对这些技术的研究进展以及面临的挑战进行总结和展望。The automatic detection of tuberculosis lesions based on medical imaging has become a research hotspot in medical image processing.A comprehensive review of relevant researches and applications pertaining to deep learning in tuberculosis lesion detection is provided,which elucidates the experimental benchmarks in tuberculosis analysis,covering public datasets of pulmonary medical images and recent research advancements in tuberculosis detection and classification competitions,introduces emerging trends in deep learning methods and applications in tuberculosis detection,and analyzes the challenges existing in tuberculosis diagnosis using deep learning.The review summarizes and provides insights into the research advances and challenges of these technologies from the aspects of technical characteristics,performance advantages,and application prospects.

关 键 词：肺结核 医学影像 自动检测 深度学习 综述 

分 类 号：R318[医药卫生—生物医学工程] TP391.7[医药卫生—基础医学]