基于全卷积网络迁移学习的左心室内膜分割  

Segmentation of Left Ventricle Endocardium Based on Transfer Learning of Fully Convolutional Networks

作　　者：齐林[1] 吕旭阳 杨本强[2] 徐礼胜[1,3] QI Lin;LYU Xu-yang;YANG Ben-qiang;XU Li-sheng(School of Sino-Dutch Biomedical&Information Engineering,Northeastern University,Shenyang 110169,China;Department of Radiology,General Hospital of Shenyang Military Region,Shenyang 110016,China;Key Laboratory of Medical Image Computing,Ministry of Education,Northeastern University,Shenyang 110169,China)

机构地区：[1]东北大学中荷生物医学与信息工程学院,辽宁沈阳110169 [2]沈阳军区总医院放射科,辽宁沈阳110016 [3]东北大学教育部医学影像计算重点实验室,辽宁沈阳110169

出　　处：《东北大学学报（自然科学版）》2018年第11期1577-1581,1592,共6页Journal of Northeastern University(Natural Science)

基　　金：国家自然科学基金资助项目(61773110;61374015;61202258);中央高校基本科研业务费专项资金资助项目(N161904002;N130404016;N171904009);辽宁省博士启动基金资助项目(20170520180)

摘　　要：为了避免过拟合现象,提出了基于全卷积网络迁移学习的左心室内膜分割方法.该方法在已用自然图像训练好的VGGNet模型的基础上对参数进行微调;其次,利用了心室内膜位于MRI图像中心处的先验信息作为选取准则来优化分割结果.将该方法对2009 MICCAI数据集的45个病例进行测试,其DICE指数、APD距离和GC率分别为0. 91,1. 73 mm和97. 81%.测试结果表明该方法对于心脏M RI图像的左心室内膜的分割结果较好,当引入一定的先验信息后可以优化测试结果.To avoid the over-fitting phenomenon,a segmentation method of left ventricle endocardium based on transfer learning of FCN was proposed.The VGG network which had been trained through the natural images was fine-tuned.In addition,some segmentation criteria were employed to optimizing the results based on the priori information that the left ventricle endocardium was in the center of the MRI(magnetic resonance imaging).In the end,45 cases taken from the 2009 MICCAI dataset was tested by this mothod.The computed DICE index,APD and GC ratio were 0.91,1.73 mm and 97.81%,respectively.Better results in segmentation of left ventricle endocardium were achieved through the transfer learning of fully convolutional networks and the priori information can improve the automatic segmentation results.

关 键 词：左心室内膜分割 深度学习 全卷积网络 迁移学习 核磁共振成像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]