基于深度学习的器官自动分割研究进展  

Research progress of automatic organ image segmentation based on deep learning

作　　者：郭雯 鞠忠建[2] 吴青南 全红[1] 戴相昆[2] GUO Wen;JU Zhong-jian;WU Qing-nan;QUAN Hong;DAI Xiang-kun(School of Physics Science and Technology,Wuhan University,Wuhan 430072,China;Department of Radiation Oncology,the First Medical Center,Chinese PLA General Hospital,Beijing 100853,China;Peking University International Hospital,Beijing 102206,China)

机构地区：[1]武汉大学物理科学与技术学院,武汉430072 [2]解放军总医院第一医学中心放疗科,北京100853 [3]北京大学国际医院,北京102206

出　　处：《医疗卫生装备》2020年第1期85-94,共10页Chinese Medical Equipment Journal

基　　金：国家自然科学基金(61671204);解放军总医院临床科研扶持基金(2017FC-TSYS-3027)

摘　　要：介绍了使用率较高的深度学习基础网络的结构模型及常用改进方法,阐述了使用深度学习神经网络对MRI及CT图像中的脑部、肺部、肝脏、胰腺、前列腺等器官进行自动分割的研究进展。指出了未来应更多关注3D图像分割和少样本训练,开发更适用的网络结构,以提高器官分割准确性和分割效率。The structure model and common improvement methods of deep learning neural network were introduced and the research progress of automatic segmentation of brain,lung,liver,pancreas,prostate and other organs in MRI and CT images by using deep learning neural network were described.It's pointed out more attention had to be paid to 3D image segmentation and less sample training in the future to develop applicable network structure and improve the accuracy and efficiency of organ segmentation.

关 键 词：深度学习 医学图像 自动分割 卷积神经网络 危及器官 

分 类 号：R318[医药卫生—生物医学工程] R319[医药卫生—基础医学]