Large residual multiple view 3D CNN for false positive reduction in pulmonary nodule detection
Source of Publication
2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2017
© 2017 IEEE. Pulmonary nodules detection play a significant role in the early detection and treatment of lung cancer. False positive reduction is the one of the major parts of pulmonary nodules detection systems. In this study a novel method aimed at recognizing real pulmonary nodule among a large group of candidates was proposed. The method consists of three steps: appropriate receptive field selection, feature extraction and a strategy for high level feature fusion and classification. The dataset consists of 888 patient's chest volume low dose computer tomography (LDCT) scans, selected from publicly available LIDC-IDRI dataset. This dataset was marked by LUNA16 challenge organizers resulting in 1186 nodules. Trivial data augmentation and dropout were applied in order to avoid overfitting. Our method achieved high competition performance metric (CPM) of 0.735 and sensitivities of 78.8% and 83.9% at 1 and 4 false positives per scan, respectively. This study is also accompanied by detailed descriptions and results overview in comparison with the state of the art solutions.
Institute of Electrical and Electronics Engineers Inc.
3D convolution neural networks, deep learning, false positive reduction, lung cancer, pulmonary nodule detection, residual learning
Dobrenkii, Anton; Kuleev, Ramil; Khan, Adil; Rivera, Adin Ramirez; and Khattak, Asad Masood, "Large residual multiple view 3D CNN for false positive reduction in pulmonary nodule detection" (2017). All Works. 2215.
Indexed in Scopus