Hongsheng Jin1, Zongyao Li2, Ruofeng Tong1, Lanfen Lin1. 1. State Key Lab of CAD & CG, Zhejiang University, Hangzhou, 310027, China. 2. The School of Aeronautics and Astronautics, Zhejiang University, Hangzhou, 310027, China.
Abstract
PURPOSE: The automatic detection of pulmonary nodules using CT scans improves the efficiency of lung cancer diagnosis, and false-positive reduction plays a significant role in the detection. In this paper, we focus on the false-positive reduction task and propose an effective method for this task. METHODS: We construct a deep 3D residual CNN (convolution neural network) to reduce false-positive nodules from candidate nodules. The proposed network is much deeper than the traditional 3D CNNs used in medical image processing. Specifically, in the network, we design a spatial pooling and cropping (SPC) layer to extract multilevel contextual information of CT data. Moreover, we employ an online hard sample selection strategy in the training process to make the network better fit hard samples (e.g., nodules with irregular shapes). RESULTS: Our method is evaluated on 888 CT scans from the dataset of the LUNA16 Challenge. The free-response receiver operating characteristic (FROC) curve shows that the proposed method achieves a high detection performance. CONCLUSIONS: Our experiments confirm that our method is robust and that the SPC layer helps increase the prediction accuracy. Additionally, the proposed method can easily be extended to other 3D object detection tasks in medical image processing.
PURPOSE: The automatic detection of pulmonary nodules using CT scans improves the efficiency of lung cancer diagnosis, and false-positive reduction plays a significant role in the detection. In this paper, we focus on the false-positive reduction task and propose an effective method for this task. METHODS: We construct a deep 3D residual CNN (convolution neural network) to reduce false-positive nodules from candidate nodules. The proposed network is much deeper than the traditional 3D CNNs used in medical image processing. Specifically, in the network, we design a spatial pooling and cropping (SPC) layer to extract multilevel contextual information of CT data. Moreover, we employ an online hard sample selection strategy in the training process to make the network better fit hard samples (e.g., nodules with irregular shapes). RESULTS: Our method is evaluated on 888 CT scans from the dataset of the LUNA16 Challenge. The free-response receiver operating characteristic (FROC) curve shows that the proposed method achieves a high detection performance. CONCLUSIONS: Our experiments confirm that our method is robust and that the SPC layer helps increase the prediction accuracy. Additionally, the proposed method can easily be extended to other 3D object detection tasks in medical image processing.
Authors: Ke Nie; Hania Al-Hallaq; X Allen Li; Stanley H Benedict; Jason W Sohn; Jean M Moran; Yong Fan; Mi Huang; Michael V Knopp; Jeff M Michalski; James Monroe; Ceferino Obcemea; Christina I Tsien; Timothy Solberg; Jackie Wu; Ping Xia; Ying Xiao; Issam El Naqa Journal: Int J Radiat Oncol Biol Phys Date: 2019-01-31 Impact factor: 7.038
Authors: Alireza Mehrtash; Mohsen Ghafoorian; Guillaume Pernelle; Alireza Ziaei; Friso G Heslinga; Kemal Tuncali; Andriy Fedorov; Ron Kikinis; Clare M Tempany; William M Wells; Purang Abolmaesumi; Tina Kapur Journal: IEEE Trans Med Imaging Date: 2018-10-18 Impact factor: 10.048