Optimization of Multi-Atlas Segmentation with Joint Label Fusion Algorithm for Automatic Segmentation in Prostate MR Imaging
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF’s parameters (rpxy, rpz, rsxy, rsz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of rpxy = 10, rpz = 1, rsxy = 3, rsz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.
Abstract
Purpose: Joint label fusion (JLF) is a popular multi-atlas-based segmentation algorithm, which compensates for dependent errors that may exist between atlases. However, in order to get good segmentation results, it is very important to set the several free parameters of the algorithm to optimal values. In this study, we first investigate the feasibility of a JLF algorithm for prostate segmentation in MR images, and then suggest the optimal set of parameters for the automatic prostate segmentation by validating the results of each parameter combination. Materials and Methods: We acquired T2-weighted prostate MR images from 20 normal heathy volunteers and did a series of cross validations for every set of parameters of JLF. In each case, the atlases were rigidly registered for the target image. Then, we calculated their voting weights for label fusion from each combination of JLF’s parameters (rpxy, rpz, rsxy, rsz, β). We evaluated the segmentation performances by five validation metrics of the Prostate MR Image Segmentation challenge. Results: As the number of voxels participating in the voting weight calculation and the number of referenced atlases is increased, the overall segmentation performance is gradually improved. The JLF algorithm showed the best results for dice similarity coefficient, 0.8495 ± 0.0392; relative volume difference, 15.2353 ± 17.2350; absolute relative volume difference, 18.8710 ± 13.1546; 95% Hausdorff distance, 7.2366 ± 1.8502; and average boundary distance, 2.2107 ± 0.4972; in parameters of rpxy = 10, rpz = 1, rsxy = 3, rsz = 1, and β = 3. Conclusion: The evaluated results showed the feasibility of the JLF algorithm for automatic segmentation of prostate MRI. This empirical analysis of segmentation results by label fusion allows for the appropriate setting of parameters.
참고문헌 (15)
- Siegel RL, "Cancer Statistics, 2017", CA Cancer J Clin, 67, pp.7~30 (2017)
- Rosenkrantz AB, "Prostate Imaging Reporting and Data System (PI-RADS), version 2: a critical look", AJR Am J Roentgenol, 206, pp.1179~1183 (2016)
- Weinreb JC, "PI-RADS Prostate Imaging - Reporting and Data System: 2015, version 2", Eur Urol, 69, pp.16~40 (2016)
- 윤지민, "Dynamic Contrast-Enhanced MRI of the Prostate: Can Auto-Generated Wash-in Color Map Be Useful in Detecting Focal Lesion Enhancement?", Investigative Magnetic Resonance Imaging, 23(3), pp.220~227 (2019), 대한자기공명의과학회
- 최문형, "Multiparametric MRI of Prostate Cancer after Biopsy: Little Impact of Hemorrhage on Tumor Staging", Investigative Magnetic Resonance Imaging, 21(3), pp.139~147 (2017), 대한자기공명의과학회[DOI]
- Giannini V, "A fully automatic computer aided diagnosis system for peripheral zone prostate cancer detection using multi-parametric magnetic resonance imaging", Comput Med Imaging Graph, 46(Pt 2), pp.219~226 (2015)
- Gao Y, "A coupled global registration and segmentation framework with application to magnetic resonance prostate imagery", IEEE Trans Med Imaging, 29, pp.1781~1794 (2010)
- Ghose S, "A survey of prostate segmentation methodologies in ultrasound, magnetic resonance and computed tomography images", Comput Methods Programs Biomed, 108, pp.262~287 (2012)
- Tian Z, "Superpixel-based segmentation for 3D prostate MR images", IEEE Trans Med Imaging, 35, pp.791~801 (2016)
- Klein S, "Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information", Med Phys, 35, pp.1407~1417 (2008)
- Chandra SS, "Fast automated segmentation of multiple objects via spatially weighted shape learning", Phys Med Biol, 61, pp.8070~8084 (2016)
- Greenham S, "Evaluation of atlas-based auto-segmentation software in prostate cancer patients", J Med Radiat Sci, 61, pp.151~158 (2014)
- Litjens G, "Evaluation of prostate segmentation algorithms for MRI : the PROMISE12challenge", Med Image Anal, 18, pp.359~373 (2014)
- Wang H, "Multi-atlas segmentation with joint label fusion", IEEE Trans Pattern Anal Mach Intell, 35, pp.611~623 (2013)
- Smith SM, "Advances in functional and structural MR image analysis and implementation as FSL", Neuroimage, 23(Suppl 1), pp.S208~S219 (2004)