Comparison of 10 brain tissue segmentation methods using revisited IBSR annotations
作者： Sergi Valverde , Arnau Oliver , Mariano Cabezas , Eloy Roura , Xavier Lladó
DOI: 10.1002/JMRI.24517
关键词:
摘要: Purpose Ground-truth annotations from the well-known Internet Brain Segmentation Repository (IBSR) datasets consider Sulcal cerebrospinal fluid (SCSF) voxels as gray matter. This can lead to bias when evaluating performance of tissue segmentation methods. In this work we compare accuracy 10 brain methods analyzing effects SCSF ground-truth on estimations. Materials and Methods The set is composed by FAST, SPM5, SPM8, GAMIXTURE, ANN, FCM, KNN, SVPASEG, FANTASM, PVC. Methods are evaluated using original IBSR ranked means their pairwise comparisons permutation tests. Afterward, evaluation repeated without considering SCSF. Results The Dice coefficient all affected changes in annotations, especially SPM8 FAST. When not voxels, SVPASEG (0.90 ± 0.01) (0.91 ± 0.01) our study that appear more suitable for matter segmentation, while FAST (0.89 ± 0.02) best tool segmenting white tissue. Conclusion The images vary notably voxels. The fact three most common (FAST, SPM8) report an important change suggest these differences labeling new comparative studies. J. Magn. Reson. Imaging 2014. © 2014 Wiley Periodicals, Inc. 2015;41:93–101.
sci-hub.se 参考文章(26)
Ayelet Akselrod-Ballin, Meirav Galun, Moshe John Gomori, Ronen Basri, Achi Brandt, Atlas Guided Identification of Brain Structures by Combining 3D Segmentation and SVM Classification Medical Image Computing and Computer-Assisted Intervention – MICCAI 2006. ,vol. 9, pp. 209- 216 ,(2006) , 10.1007/11866763_26
Benoît Caldairou, François Rousseau, Nicolas Passat, Piotr Habas, Colin Studholme, Christian Heinrich, A Non-Local Fuzzy Segmentation Method: Application to Brain MRI Computer Analysis of Images and Patterns. ,vol. 5702, pp. 606- 613 ,(2009) , 10.1007/978-3-642-03767-2_74
P. A. Filipek, C. Richelme, D. N. Kennedy, V. S. Caviness, The Young Adult Human Brain: An MRI-based Morphometric Analysis Cerebral Cortex. ,vol. 4, pp. 344- 360 ,(1994) , 10.1093/CERCOR/4.4.344
Lee R. Dice, Measures of the Amount of Ecologic Association Between Species Ecology. ,vol. 26, pp. 297- 302 ,(1945) , 10.2307/1932409
Michael Wels, Yefeng Zheng, Martin Huber, Joachim Hornegger, Dorin Comaniciu, A discriminative model-constrained EM approach to 3D MRI brain tissue classification and intensity non-uniformity correction Physics in Medicine and Biology. ,vol. 56, pp. 3269- 3300 ,(2011) , 10.1088/0031-9155/56/11/007
Andrés Ortiz, JM Górriz, Javier Ramírez, Diego Salas-Gonzalez, José M Llamas-Elvira, None, Two fully-unsupervised methods for MR brain image segmentation using SOM-based strategies soft computing. ,vol. 13, pp. 2668- 2682 ,(2013) , 10.1016/J.ASOC.2012.11.020
Renske de Boer, Henri A. Vrooman, Fedde van der Lijn, Meike W. Vernooij, M. Arfan Ikram, Aad van der Lugt, Monique M.B. Breteler, Wiro J. Niessen, White matter lesion extension to automatic brain tissue segmentation on MRI NeuroImage. ,vol. 45, pp. 1151- 1161 ,(2009) , 10.1016/J.NEUROIMAGE.2009.01.011
Dzung L. Pham, Spatial Models for Fuzzy Clustering Computer Vision and Image Understanding. ,vol. 84, pp. 285- 297 ,(2001) , 10.1006/CVIU.2001.0951
Navid Shiee, Pierre-Louis Bazin, Arzu Ozturk, Daniel S. Reich, Peter A. Calabresi, Dzung L. Pham, A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions. NeuroImage. ,vol. 49, pp. 1524- 1535 ,(2010) , 10.1016/J.NEUROIMAGE.2009.09.005
Henri A. Vrooman, Chris A. Cocosco, Fedde van der Lijn, Rik Stokking, M. Arfan Ikram, Meike W. Vernooij, Monique M.B. Breteler, Wiro J. Niessen, Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification. NeuroImage. ,vol. 37, pp. 71- 81 ,(2007) , 10.1016/J.NEUROIMAGE.2007.05.018