中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中国科学院分子影像重点实验室
热门
Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation

文献类型：期刊论文

作者Wang, Shuo1,3; Zhou, Mu2; Liu, Zaiyi4; Liu, Zhenyu1; Gu, Dongsheng1,3; Zang, Yali1,3; Dong, Di1,3; Gevaert, Olivier2; Tian, Jie1,3,5
刊名MEDICAL IMAGE ANALYSIS
出版日期2017-08-01
卷号40期号:40页码:172-183
关键词Lung Nodule Segmentation Convolutional Neural Networks Deep Learning Computer-aided Diagnosis
DOI10.1016/j.media.2017.06.014
文献子类Article
英文摘要Accurate lung nodule segmentation from computed tomography (CT) images is of great importance for image-driven lung cancer analysis. However, the heterogeneity of lung nodules and the presence of similar visual characteristics between nodules and their surroundings make it difficult for robust nodule segmentation. In this study, we propose a data-driven model, termed the Central Focused Convolutional Neural Networks (CF-CNN), to segment lung nodules from heterogeneous CT images. Our approach combines two key insights: 1) the proposed model captures a diverse set of nodule-sensitive features from both 3-D and 2-D CT images simultaneously; 2) when classifying an image voxel, the effects of its neighbor voxels can vary according to their spatial locations. We describe this phenomenon by proposing a novel central pooling layer retaining much information on voxel patch center, followed by a multi-scale patch learning strategy. Moreover, we design a weighted sampling to facilitate the model training, where training samples are selected according to their degree of segmentation difficulty. The proposed method has been extensively evaluated on the public LIDC dataset including 893 nodules and an independent dataset with 74 nodules from Guangdong General Hospital (GDGH). We showed that CF-CNN achieved superior segmentation performance with average dice scores of 82.15% and 80.02% for the two datasets respectively. Moreover, we compared our results with the inter-radiologists consistency on LIDC dataset, showing a difference in average dice score of only 1.98%. (C) 2017 Published by Elsevier B.V.
WOS关键词THORACIC CT SCANS ; MR BRAIN IMAGES ; PULMONARY NODULES ; AUTOMATIC SEGMENTATION ; CONSORTIUM ; LESIONS
WOS研究方向Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging
语种英语
WOS记录号WOS:000407538000011
资助机构National Natural Science Foundation of China(81227901 ; Science and Technology Service Network Initiative of the Chinese Academy of Sciences(KFJ-SW-STS-160) ; special program for science and technology development from the Ministry of science and technology, China(2017YFA0205200 ; National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health(R01EB020527) ; Instrument Developing Project of the Chinese Academy of Sciences(YZ201502) ; Beijing Municipal Science and Technology Commission([Z161100002616022) ; Youth Innovation Promotion Association CAS ; 61231004 ; 2017YFC1308701 ; 81501616 ; 2017YFC1309100 ; 81671851 ; 2016CZYD0001) ; 81527805 ; 81501549)
源URL[http://ir.ia.ac.cn/handle/173211/20306]  
专题自动化研究所_中国科学院分子影像重点实验室
作者单位1.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
2.Stanford Univ, Dept Med, Stanford Ctr Biomed Informat Res BMIR, Stanford, CA 94305 USA
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Guangdong Gen Hosp, Guangzhou 510080, Guangdong, Peoples R China
5.Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Shuo,Zhou, Mu,Liu, Zaiyi,et al. Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation[J]. MEDICAL IMAGE ANALYSIS,2017,40(40):172-183.
APA Wang, Shuo.,Zhou, Mu.,Liu, Zaiyi.,Liu, Zhenyu.,Gu, Dongsheng.,...&Tian, Jie.(2017).Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation.MEDICAL IMAGE ANALYSIS,40(40),172-183.
MLA Wang, Shuo,et al."Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation".MEDICAL IMAGE ANALYSIS 40.40(2017):172-183.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。