光学精密工程2018，Vol.26Issue(5)：1211-1218,8.DOI:10.3788/OPE.20182605.1211
基于三维卷积神经网络的低剂量CT肺结节检测
Detection of low dose CT pulmonary nodules based on 3D convolution neural network
摘要
Abstract
To improve the detection rate of pulmonary nodules in early lung cancer screening ,a low-dose CT pulmonary nodule detection algorithm based on 3D convolution neural network was presented . First ,the multi-directional morphological filtering algorithm was used to preprocess low-dose sequence CT image .The improved 3D region growth algorithm combined with the convex hull algorithm was used for lung parenchymal segmentation .Then the 3D candidate nodules were routed and illuminated in order to solve the convolution neural network on the sample imbalance sensitive issues . Finally , in situations of different network parameters ,four groups of experiments were performed on the 50 sequences of low-dose lung cancer screening data in ELCAP database .The results showed that accuracy ,sensitivity ,specificity and ROC curve of the AUC values were 84.6％ ,88.89％ ,80.32％ and 0.9244 respectively by the constant optimization of network parameters .The proposed algorithm can correctly detect low-dose lung nodules ,with the the accuracy ,sensitivity ,and specificity increased by 5.37％ ,5.6％ and 10.42％ ,respectively ,w hich is more comprehensive and can provide effective help for lung cancer screening compared with conventional lung nodule detection algorithm .关键词
肺癌筛查/3D卷积神经网络/ELCAP/肺结节/平衡Key words
lung cancer screening/three dimensional convolution neural network/ELCAP/lung nodule/imbalance分类
信息技术与安全科学引用本文复制引用
吕晓琪,吴凉,谷宇,张文莉,李菁..基于三维卷积神经网络的低剂量CT肺结节检测[J].光学精密工程,2018,26(5):1211-1218,8.基金项目
国家自然科学基金资助项目(No .61771266 ,61179019 ) （No .61771266 ,61179019 ）
内蒙古自治区自然科学基金资助项目(No.2015MS0604) （No.2015MS0604）
内蒙古自治区高等学校科学研究项目(No.NJZY145) （No.NJZY145）
包头市科技计划项目(No.2015C2006-14) （No.2015C2006-14）
