Deep Learning in CT Images: Automated Pulmonary Nodule Detection for Subsequent Management Using Convolutional Neural Network

Yi-Ming Xu,1 Teng Zhang,1 Hai Xu,1 Liang Qi,1 Wei Zhang,1 Yu-Dong Zhang,1 Da-Shan Gao,2 Mei Yuan,1 Tong-Fu Yu1 1Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, People’s Republic of China; 2 12sigma Technologies, San Diego, California, USACorrespondence: Mei Yuan; Tong-Fu YuDepartment of Radiology, The First Affiliated Hospital of Nanjing Medical University, 300, Guangzhou Road, Nanjing, Jiangsu Province, People’s Republic of China, 210009 Tel +86-13405835354; +86-13813810516Fax +86-02568136861Email yuanmeijiangsu@163.com; njmu_ytf@163.comPurpose: Thepurposeofthisstudyisto compare the detection performance of the 3-dimensional convolutional neural network (3D CNN)-based computer-aided detection (CAD) models with radiologists of different levels of experience in detecting pulmonary nodules on thin-section computed tomography (CT).Patients and Methods: We retrospectively reviewed 1109 consecutive patients who underwent follow-up thin-section CT at our institution. The 3D CNN model for nodule detection was re-trained and complemented by expert augmentation. The annotations of a consensus panel consisting of two expert radiologists determined the ground truth. The detection performance of the re-trained CAD model and three other radiologists at different levels of experience were tested using a free-response receiver operating characteristic (FROC) analysis in the test group.Results: The detection performance of the re-trained CAD model was significantly better than that of the pre-trained network (sensitivity: 93.09% vs 38.44%). The re-trained CAD model had a significantly better detection performance than radiologists (average sensitivity: 93.09% vs 50.22%), without significantly increasing the number of false positives per scan (1.64 vs 0.68). In the training set, 922 nodules less than 3 mm in size in 211 patients at high risk were recommended for follow-up CT according to the Fleischner Society Guidelines. Fifteen of 101 solid nodules were confirmed to be lung cancer.Conclusion: The re-trained 3D CNN-based CAD model, complemented by expert augmentation, was an accurate and efficient tool in identifying incidental pulmonary nodules for subsequent management.Keywords: computer-aided detection, computed tomography, pulmonary nodules, convolutional neural network