LIDC/IDRI影像数据库在肺结节计算机辅助诊断中的研究进展  

Lung Image Database Consortium and Image Database Resource Initiative: reviewing progresses toward improved computer-aided diagnosis of pulmonary nodule

作　　者：林岚[1] 吴玉超 宋爽 吴水才[1] LIN Lan;WU Yu-chao;SONG Shuang;WU Shui-cai(College of Life Science and Bioengineering,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学生命科学与生物工程学院,北京100124

出　　处：《医疗卫生装备》2018年第10期95-99,共5页Chinese Medical Equipment Journal

基　　金：北京市教委科技计划一般项目(KM201810005033);国家科技支撑计划课题(2015BAI02B03)

摘　　要：介绍了用于开发肺部CT图像计算机辅助诊断(computer aided diagnosis,CAD)系统的LIDC/IDRI(Lung Image Database Consortium/Image Database Resource Initiative)影像数据库的发展历史、文件格式、组织构架及基本应用,分析了基于该影像数据库的肺结节分割与诊断的研究进展。指出了LIDC/IDRI影像数据库与CAD系统之间的关系,并指明了基于LIDC/IDRI影像数据库的新的人工智能方案,如深层强化学习和迁移学习等,是肺结节CAD系统未来的发展方向。Lung hnage Database Consortium （LIDC） / Image Database Resource Initiative （IDRI） image database had its history, file format, organizational structure and application introduced when used for developing a lung CT image computer- aided diagnosis （CAD） system. The research progress of pulmonary nodule segmentation and diagnosis based on the image database was analyzed, and the relationship between LIDC/IDRI image database and CAD system was indicated. It＇s pointed out that new AI schedules based on LIDC/IDRI image database, such as deep reinforcement learning and transfer learning, would contribute to the development of puhnonary nodule CAD system.

关 键 词：肺结节 LIDC/IDRI影像数据库 计算机辅助诊断 结节分割 结节分类 结节诊断 深度学习 

分 类 号：R318[医药卫生—生物医学工程] R445.2[医药卫生—基础医学]