Automated glioblastoma segmentation based on a multiparametric structured unsupervised classification

Javier Juan-Albarracín, Elies Fuster-Garcia, José V Manjón, Montserrat Robles, F Aparici, L Martí-Bonmatí, Juan M García-Gómez, Javier Juan-Albarracín, Elies Fuster-Garcia, José V Manjón, Montserrat Robles, F Aparici, L Martí-Bonmatí, Juan M García-Gómez

Abstract

Automatic brain tumour segmentation has become a key component for the future of brain tumour treatment. Currently, most of brain tumour segmentation approaches arise from the supervised learning standpoint, which requires a labelled training dataset from which to infer the models of the classes. The performance of these models is directly determined by the size and quality of the training corpus, whose retrieval becomes a tedious and time-consuming task. On the other hand, unsupervised approaches avoid these limitations but often do not reach comparable results than the supervised methods. In this sense, we propose an automated unsupervised method for brain tumour segmentation based on anatomical Magnetic Resonance (MR) images. Four unsupervised classification algorithms, grouped by their structured or non-structured condition, were evaluated within our pipeline. Considering the non-structured algorithms, we evaluated K-means, Fuzzy K-means and Gaussian Mixture Model (GMM), whereas as structured classification algorithms we evaluated Gaussian Hidden Markov Random Field (GHMRF). An automated postprocess based on a statistical approach supported by tissue probability maps is proposed to automatically identify the tumour classes after the segmentations. We evaluated our brain tumour segmentation method with the public BRAin Tumor Segmentation (BRATS) 2013 Test and Leaderboard datasets. Our approach based on the GMM model improves the results obtained by most of the supervised methods evaluated with the Leaderboard set and reaches the second position in the ranking. Our variant based on the GHMRF achieves the first position in the Test ranking of the unsupervised approaches and the seventh position in the general Test ranking, which confirms the method as a viable alternative for brain tumour segmentation.

Conflict of interest statement

Competing Interests: Veratech for Health S.L., a commercial company, provided support in the form of salaries for author EF-G, but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific roles of this author is articulated in the “author contributions” section. This does not alter the authors’ adherence to PLOS ONE policies on sharing data and materials.

Figures

Fig 1. Example of new skull stripping.
Fig 1. Example of new skull stripping.
From left to right column: original BRATS 2013 patient image, resultant image after the new skull stripping and the remaining residual.
Fig 2. Example of super resolution using…
Fig 2. Example of super resolution using Non-local Upsampling of a Flair sequence of the BRATS 2013 dataset.
Fig 3. Example of feature extraction and…
Fig 3. Example of feature extraction and dimensionality reduction from a patient of the BRATS 2013 dataset.
Fig 4. Patient tissue probability maps computation…
Fig 4. Patient tissue probability maps computation and lesion area correction.
Fig 5. Automatic tumour class isolation process.
Fig 5. Automatic tumour class isolation process.
Fig 6. Examples of final segmentations of…
Fig 6. Examples of final segmentations of 3 patients of BRATS 2013 dataset computed by the different unsupervised algorithms.

References

    1. Wen PY, Macdonald DR, Reardon DA, Cloughesy TF, Sorensen AG, Galanis E, et al. Updated response assessment criteria for high-grade gliomas: Response assessment in neuro-oncology working group. Journal of Clinical Oncology. 2010;28: 1963–1972. 10.1200/JCO.2009.26.3541
    1. Bauer S, Wiest R, Nolte LP, Reyes M. A survey of MRI-based medical image analysis for brain tumor studies. Physics in Medicine and Biology. 2013;58: R97–129. 10.1088/0031-9155/58/13/R97
    1. Dolecek TA, Propp JM, Stroup NE, Kruchko C. Cbtrus statistical report: Primary brain and central nervous system tumors diagnosed in the united states in 2005–2009. Neuro-Oncology. 2012;14: 1–49. 10.1093/neuonc/nos218
    1. von Deimling A. Gliomas (Recent Results in Cancer Research). Heidelberg: Springer; 2009.
    1. Gordillo N, Montseny E, Sobrevilla P. State of the art survey on MRI brain tumor segmentation. Magnetic Resonance Imaging. 2013;31: 1426–1438. 10.1016/j.mri.2013.05.002
    1. Verma R, Zacharaki EI, Ou Y, Cai H, Chawla S, Lee SK, et al. Multiparametric tissue characterization of brain neoplasms and their recurrence using pattern classification of MR images. Academic Radiology. 2008;15: 966–977. 10.1016/j.acra.2008.01.029
    1. Ruan S, Zhang N, Liao Q, Zhu Y. Image fusion for following-up brain tumor evolution. IEEE International Symposium on Biomedical Imaging: From Nano to Macro. 2011;1: 281–284.
    1. Jensen TR, Schmainda KM. Computer-aided detection of brain tumor invasion using multiparametric MRI. Journal of Magnetic Resonance Imaging. 2009;30: 481–489. 10.1002/jmri.21878
    1. Lee CH, Wang S, Murtha A, Brown M, Greiner R. Segmenting brain tumors using pseudo–conditional random fields. Medical Image Computing and Computer-Assisted Intervention. 2008;11: 359–366.
    1. Bauer S, Nolte LP, Reyes M. Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization. Medical Image Computing and Computer-Assisted Intervention. 2011;14: 354–361.
    1. Breiman L. Random forests. Machine Learning 2001;45: 5–32. 10.1023/A:1010933404324
    1. Meier R, Bauer S, Slotboom J, Wiest R, Reyes M. A hybrid model for multimodal brain tumor segmentation. Proceedings of NCI-MICCAI BRATS. 2013;1: 31–37.
    1. Festa J, Pereira S, Mariz JA, Sousa N, Silva CA. Automatic brain tumor segmentation of multi-sequence mr images using random decision forests. Proceedings of NCI-MICCAI BRATS. 2013;1: 23–26.
    1. Reza S, Iftekharuddin K. Multi-class abnormal brain tissue segmentation using texture features. Proceedings of NCI-MICCAI BRATS. 2013;1: 38–42.
    1. Tustison N, Wintermark M, Durst C, Avants B. ANTs and árboles. Proceedings of NCI-MICCAI BRATS. 2013;1: 47–50.
    1. Wagstaff KL. Intelligent Clustering with instance-level constraints. PhD Thesis, Cornell University. 2002.
    1. Duda R, Hart P, Stork D. Pattern classification. 2nd ed. New York: Wiley-Interscience; 2000.
    1. Fletcher-Heath LM, Hall LO, Goldgof DB, Murtagh F. Automatic segmentation of non-enhancing brain tumors in magnetic resonance images. Artificial Intelligence in Medicine. 2001;21: 43–63. 10.1016/S0933-3657(00)00073-7
    1. Nie J, Xue Z, Liu T, Young GS, Setayesh K, Guo L, et al. Automated brain tumor segmentation using spatial accuracy-weighted hidden Markov random field. Computerized Medical Imaging and Graphics. 2009;33: 431–441. 10.1016/j.compmedimag.2009.04.006
    1. Zhu Y, Young GS, Xue Z, Huang RY, You H, Setayesh K, et al. Semi-automatic segmentation software for quantitative clinical brain glioblastoma evaluation. Academic Radiology. 2012;19: 977–985. 10.1016/j.acra.2012.03.026
    1. Zhang Y, Brady M, Smith S. Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Transactions on Medical Imaging. 2001;20: 45–57. 10.1109/42.906424
    1. Vijayakumar C, Damayanti G, Pant R, Sreedhar C. Segmentation and grading of brain tumors on apparent diffusion coefficient images using self-organizing maps. Computerized Medical Imaging and Graphics. 2007;31: 473–484. 10.1016/j.compmedimag.2007.04.004
    1. Prastawa M, Bullit E, Moon N, Leemput K, Gerig G. Automatic brain tumor segmentation by subject specific modification of atlas priors. Academic Radiology. 2003;10: 1341–1348. 10.1016/S1076-6332(03)00506-3
    1. Doyle S, Vasseur F, Dojat M, Forbes F. Fully automatic brain tumor segmentation from multiple MR sequences using hidden Markov fields and variational EM. Proceedings of NCI-MICCAI BRATS. 2013;1: 18–22.
    1. Menze Bjoern, Jakab Andras, Bauer Stefan, Kalpathy-Cramer Jayashree, Farahani Keyvan, Kirby Justin, et al. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Transactions on Medical Imaging. 2014; 1–33. 10.1109/TMI.2014.2377694
    1. Gudbjartsson H, Patz S. The rician distribution of noisy MRI data. Magnetic Resonance in Medicine. 1995;34: 910–914. 10.1002/mrm.1910340618
    1. Diaz I, Boulanger P, Greiner R, Murtha A. A critical review of the effects of de-noising algorithms on MRI brain tumor segmentation. Proceedings of Engineering in Medicine and Biology Society. 2011;1: 3934–3937.
    1. Buades A, Coll B, Morel JM. A review of image denoising algorithms, with a new one. Multiscale Model & Simulation. 2005;4: 490–530. 10.1137/040616024
    1. Manjón JV, Coupé P, Martí-Bonmatí L, Collins DL, Robles M. Adaptive non-local means denoising of MR images with spatially varying noise levels. Journal of Magnetic Resonance Imaging. 2010;31: 192–203. 10.1002/jmri.22003
    1. Sled J, Zijdenbos A, Evans A. A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Transactions on Medical Imaging. 1998;17: 87–97. 10.1109/42.668698
    1. Tustison N, Avants B, Cook P, Zheng Y, Egan A, Yushkevich PA, et al. N4ITK: Improved N3 bias correction. IEEE Transactions on Medical Imaging. 2010;29: 1310–1320. 10.1109/TMI.2010.2046908
    1. Plenge E, Poot D, Niessen W, Meijering E. Super-resolution reconstruction using cross-scale self-similarity in multi-slice MRI. Medical Image Computing and Computer-Assisted Intervention. 2013;16: 123–130.
    1. Manjón JV, Coupé P, Buades A, Collins DL, Robles M. MRI superresolution using self similarity and image priors. International Journal of Biomedical Imaging. 2010;17: 1–12.
    1. Rousseau F. A non-local approach for image super-resolution using intermodality priors. Medical Image Analysis. 2010;14: 594–605. 10.1016/j.media.2010.04.005
    1. Protter M, Elad M, Takeda H, Milanfar P. Generalizing the Non Local-Means to super-resolution reconstruction. IEEE Transactions on Image Processing. 2009;18: 36–51. 10.1109/TIP.2008.2008067
    1. Manjón JV, Coupé P, Buades A, Fonov V, Collins DL, Robles M. Non-local MRI upsampling. Medical Image Analysis. 2010;14: 784–792. 10.1016/j.media.2010.05.010
    1. Kassner A, Thornhill R. Texture analysis: A review of neurologic MR imaging applications. American Journal of Neuroradiology. 2010;31: 809–816. 10.3174/ajnr.A2061
    1. Ahmed S, Iftekharuddin KM, Vossough A. Efficacy of texture, shape, and intensity feature fusion for posterior-fossa tumor segmentation in MRI. IEE Transaction on Information Technology in Biomedicine. 2011;15: 206–213. 10.1109/TITB.2011.2104376
    1. Lloyd S. Least squares quantization in PCM. IEEE Transactions on Information Theory. 1982;28: 129–137. 10.1109/TIT.1982.1056489
    1. MacQueen J. Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. 1967;1: 281–297.
    1. Dempster AP, Laird NM, Rubin DB. Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society. 1977;39: 1–38.
    1. Bishop C. Neural Networks for Pattern Recognition. New York: Oxford University Press, Inc; 1995.
    1. Dunn JC. A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters. Journal of Cybernetics. 1973;3: 32–57. 10.1080/01969727308546046
    1. Bezdek JC. Pattern Recognition with Fuzzy Objective Function Algorithms. Norwell: Kluwer Academic Publishers; 1981.
    1. Hammersley, JM, Clifford, P. Markov fields on finite graphs and lattices. 1971.
    1. Komodakis N, Tziritas G. Approximate labeling via graph cuts based on linear programming. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2007;29: 1436–1453. 10.1109/TPAMI.2007.1061
    1. Komodakis N, Tziritas G, Paragios N. Performance vs computational efficiency for optimizing single and dynamic MRFs: Setting the state of the art with primal-dual strategies. Computer Vision and Image Understanding. 2008;112: 14–29. 10.1016/j.cviu.2008.06.007
    1. Arthur D, Vassilvitskii S. K-means++: The advantages of careful seeding. Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms. 2007;1: 1027–1035.
    1. Fonov VS, Evans AC, Botteron K, Almli CR, McKinstry RC, Collins DL, et al. Unbiased average age-appropriate atlases for pediatric studies. NeuroImage. 2011;54: 313–327 10.1016/j.neuroimage.2010.07.033
    1. Fonov VS, Evans AC, McKinstry RC, Almli CR, Collins DL. Unbiased nonlinear average age-appropriate brain templates from birth to adulthood. NeuroImage. 2009;47: S102 10.1016/S1053-8119(09)70884-5
    1. Klein A, Andersson J, Ardekani BA, Ashburner J, Avants B, Chiang MC, et al. Evaluation of 14 nonlinear deformation algorithms applied to human brain MRI registration. NeuroImage. 2009;46: 786–802. 10.1016/j.neuroimage.2008.12.037
    1. Avants B, Epstein C, Grossman M, Gee J. Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain. Medical Image Analysis. 2008;12: 26–41. 10.1016/j.media.2007.06.004
    1. Saez C, Robles M, Garcia-Gomez JM. Stability metrics for multi-source biomedical data based on simplicial projections from probability distribution distances. Statistical Methods in Medical Research 2014; In press.

Source: PubMed

Sponsorer og samarbeidspartnere

Medisinsk tilstand

Legemiddelintervensjoner

3
Abonnere