Acta Optica Sinica, Volume. 39, Issue 6, 0615006(2019)
Pulmonary Nodule Recognition Based on Three-Dimensional Convolution Neural Network
Figures & Tables(7)
Fig. 5. Recognition results of candidate nodules. (a) Prediction probability of true nodule; (b) prediction probability of pseudopositive nodule
Table 1. Comparison of pulmonary nodule recognition performance by different network structures on LUNA16 dataset
View tableTable 1. Comparison of pulmonary nodule recognition performance by different network structures on LUNA16 dataset
Method False positives per scan CPM 1/8 1/4 1/2 1 2 4 8 Model_1 0.629 0.735 0.807 0.865 0.901 0.917 0.928 0.826 Model_2 0.734 0.812 0.869 0.901 0.918 0.927 0.929 0.870 Model_3 0.754 0.821 0.888 0.913 0.930 0.933 0.937 0.883 Proposed 0.807 0.843 0.877 0.911 0.925 0.934 0.939 0.891
Table 2. Pulmonary nodule recognition performance by different algorithms on LUNA16
View tableTable 2. Pulmonary nodule recognition performance by different algorithms on LUNA16
Algorithm False positives per scan CPM 0.125 0.25 0.5 1 2 4 8 Ref. [6] 0.678 0.738 0.816 0.848 0.879 0.907 0.922 0.827 Ref. [5] 0.692 0.710 0.809 0.863 0.895 0.914 0.923 0.838 Ref. [18] 0.760 0.794 0.833 0.860 0.876 0.893 0.906 0.846 Ref. [7] 0.802 0.847 0.886 0.909 0.925 0.936 0.941 0.892 Proposed 0.807 0.843 0.877 0.911 0.925 0.934 0.939 0.891
Tools
Get Citation
Copy Citation Text
Yu Feng, Benshun Yi, Chenyue Wu, Yungang Zhang. Pulmonary Nodule Recognition Based on Three-Dimensional Convolution Neural Network[J]. Acta Optica Sinica, 2019, 39(6): 0615006
Paper Information
Category: Machine Vision
Received: Jan. 22, 2019
Accepted: Mar. 11, 2019
Published Online: Jun. 17, 2019
The Author Email: Yi Benshun (yibs@whu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20