The purpose of this study is to reveal how the performance of lung nodule segmentation algorithm impacts the performance of lung nodule detection, and to provide guidelines for choosing an appropriate segmentation algorithm with appropriate parameters in a computer-aided detection (CAD) scheme.
The database consisted of 85 CT scans with 111 nodules of 3 mm or larger in diameter from the standard CT lung nodule database created by the Lung Image Database Consortium. The initial nodule candidates were identified as those with strong response to a selective nodule enhancement filter. A uniform viewpoint reformation technique was applied to a three-dimensional nodule candidate to generate 24 two-dimensional (2D) reformatted images, which would be used to effectively distinguish between true nodules and false positives. Six different algorithms were employed to segment the initial nodule candidates in the 2D reformatted images. Finally, 2D features from the segmented areas in the 24 reformatted images were determined, selected, and classified for removal of false positives. Therefore, there were six similar CAD schemes, in which only the segmentation algorithms were different. The six segmentation algorithms included the fixed thresholding (FT), Otsu thresholding (OTSU), fuzzy C-means (FCM), Gaussian mixture model (GMM), Chan and Vese model (CV), and local binary fitting (LBF). The mean Jaccard index and the mean absolute distance (Dmean) were employed to evaluate the performance of segmentation algorithms, and the number of false positives at a fixed sensitivity was employed to evaluate the performance of the CAD schemes.
For the segmentation algorithms of FT, OTSU, FCM, GMM, CV, and LBF, the highest mean Jaccard index between the segmented nodule and the ground truth were 0.601, 0.586, 0.588, 0.563, 0.543, and 0.553, respectively, and the corresponding Dmean were 1.74, 1.80, 2.32, 2.80, 3.48, and 3.18 pixels, respectively. With these segmentation results of the six segmentation algorithms, the six CAD schemes reported 4.4, 8.8, 3.4, 9.2, 13.6, and 10.4 false positives per CT scan at a sensitivity of 80%.
When multiple algorithms are available for segmenting nodule candidates in a CAD scheme, the “optimal” segmentation algorithm did not necessarily lead to the “optimal” CAD detection performance.
This work was supported in part by USPHS Grant No. R01 CA113870, and W.G. is supported in part by Shenyang Science and Technology Foundation No. F13-316-1-35, the Ph.D. startup Fund of National Science Foundation of Liaoning Province No. 20131086, the Ph.D. startup Fund of SAU (No. 13YB16), National Aerospace science Foundation (No. 2103ZE54025), and National Natural Science Foundation of China (Nos. 61373088 and 61300233). CAD technologies developed by Qiang Li and his colleagues have been licensed to companies including Hologic, Inc., Riverain Medical Group, Median Technology, Mitsubishi Space Software Co., General Electric Corporation, and Toshiba Corporation.
III.A. Fixed thresholding
III.B. Otsu thresholding
III.C. Fuzzy C-mean algorithm
III.D. Gaussian mixture model
III.E. Chan and Vese model
III.F. Local binary fitting
III.G. Statistical analysis
IV.A. Segmentation results by use of different segmentation algorithms
IV.B. Performances of segmentation and detection by use of different segmentation algorithms
IV.C. Performances of segmentation and detection by use of different parameters of the same segmentation algorithm
- Medical image segmentation
- Computed tomography
- Three dimensional image processing
Data & Media loading...
Article metrics loading...
Full text loading...