A CADe system for nodule detection in thoracic CT images based on artificial neural network  

作　　者：Xinglong LIU Fei HOU Hong QIN Aimin HAO 

机构地区：[1]State Key Laboratory of Virtual Reality Technology and Systems, Beihang University [2]School of Computer Science and Engineering, Nanyang Technological University [3]Department of Computer Science, Stony Brook University

出　　处：《Science China(Information Sciences)》2017年第7期173-187,共15页中国科学（信息科学）（英文版）

基　　金：supported in part by National Natural Science Foundation of China (Grant Nos. 61190120, 61190121, 61190125, 61532002, 61300068, 61300067, 61672149, 61672077);National Science Foundation of USA (Grant Nos. IIS-0949467, IIS-1047715, IIS-1049448);Postdoctoral Science Foundation of China (Grant No. 2013M530512);China Scholarship Council (Grant No. 201506020035)

摘　　要：Lung cancer has been the leading cause of cancer-related deaths in 2015 in United States. Early detection of lung nodules will undoubtedly increase the five-year survival rate for lung cancer according to prior studies. In this paper, we propose a novel rating method based on geometrical and statistical features to extract initial nodule candidates and an artificial neural network approach to the detection of lung nodules. The novel method is solely based on 3D distribution of neighboring voxels instead of user-specified features. During initial candidates detection, we combine organized region properties calculated from connected component analysis with corresponding voxel value distributions from statistical analysis to reduce false positives while retaining true nodules. Then we devise multiple artificial neural networks（ANNs） trained from massive voxel neighbor sampling of different types of nodules and organize the outputs using a 3D scoring method to identify final nodules. The experiments on 107 CT cases with 252 nodules in LIDC-IDRI data sets have shown that our new method achieves sensitivity of 89.4% while reducing the false positives to 2.0 per case. Our comprehensive experiments have demonstrated our system would be of great assistance for diagnosis of lung nodules in clinical treatments.Lung cancer has been the leading cause of cancer-related deaths in 2015 in United States. Early detection of lung nodules will undoubtedly increase the five-year survival rate for lung cancer according to prior studies. In this paper, we propose a novel rating method based on geometrical and statistical features to extract initial nodule candidates and an artificial neural network approach to the detection of lung nodules. The novel method is solely based on 3D distribution of neighboring voxels instead of user-specified features. During initial candidates detection, we combine organized region properties calculated from connected component analysis with corresponding voxel value distributions from statistical analysis to reduce false positives while retaining true nodules. Then we devise multiple artificial neural networks（ANNs） trained from massive voxel neighbor sampling of different types of nodules and organize the outputs using a 3D scoring method to identify final nodules. The experiments on 107 CT cases with 252 nodules in LIDC-IDRI data sets have shown that our new method achieves sensitivity of 89.4% while reducing the false positives to 2.0 per case. Our comprehensive experiments have demonstrated our system would be of great assistance for diagnosis of lung nodules in clinical treatments.

关 键 词：artificial neutral network Lung nodule computed tomography computer aided detection nodule detection 

分 类 号：R734.2[医药卫生—肿瘤] TP183[医药卫生—临床医学] TP391.7[自动化与计算机技术—控制理论与控制工程]