Jump to ContentJump to Main Navigation
Show Summary Details
More options …

Biomedical Engineering / Biomedizinische Technik

Editor-in-Chief: Dössel, Olaf

Editorial Board Member: Augat, Peter / Haueisen, Jens / Jockenhoevel, Stefan / Lenarz, Thomas / Leonhardt, Steffen / Plank, Gernot / Radermacher, Klaus M. / Schkommodau, Erik / Stieglitz, Thomas / Boenick, Ulrich / Jaramaz, Branislav / Kraft, Marc / Lenthe, Harry / Lo, Benny / Mainardi, Luca / Micera, Silvestro / Penzel, Thomas / Robitzki, Andrea A. / Schaeffter, Tobias / Snedeker, Jess G. / Sörnmo, Leif / Sugano, Nobuhiko / Werner, Jürgen /

6 Issues per year

IMPACT FACTOR 2016: 0.915
5-year IMPACT FACTOR: 1.263

See all formats and pricing
More options …
Volume 61, Issue 4 (Aug 2016)


Volume 57 (2012)

Brain tumor classification and segmentation using sparse coding and dictionary learning

Saif Dawood Salman Al-Shaikhli
  • Corresponding author
  • Institute for Information Processing, Leibniz University Hannover, Appelstr. 9A, 30167 Hannover, Germany
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Michael Ying Yang / Bodo Rosenhahn
  • Institute for Information Processing, Leibniz University Hannover, Appelstr. 9A, 30167 Hannover, Germany
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
Published Online: 2015-08-06 | DOI: https://doi.org/10.1515/bmt-2015-0071


This paper presents a novel fully automatic framework for multi-class brain tumor classification and segmentation using a sparse coding and dictionary learning method. The proposed framework consists of two steps: classification and segmentation. The classification of the brain tumors is based on brain topology and texture. The segmentation is based on voxel values of the image data. Using K-SVD, two types of dictionaries are learned from the training data and their associated ground truth segmentation: feature dictionary and voxel-wise coupled dictionaries. The feature dictionary consists of global image features (topological and texture features). The coupled dictionaries consist of coupled information: gray scale voxel values of the training image data and their associated label voxel values of the ground truth segmentation of the training data. For quantitative evaluation, the proposed framework is evaluated using different metrics. The segmentation results of the brain tumor segmentation (MICCAI-BraTS-2013) database are evaluated using five different metric scores, which are computed using the online evaluation tool provided by the BraTS-2013 challenge organizers. Experimental results demonstrate that the proposed approach achieves an accurate brain tumor classification and segmentation and outperforms the state-of-the-art methods.

Keywords: brain tumor; classification; dictionary learning; segmentation; sparse coding; texture; topology


  • [1]

    Aharon M, Elad M, Bruckstein A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE T Signal Proces 2006; 54: 4311–4322.Google Scholar

  • [2]

    Al-Shaikhli SDS, Yang MY, Rosenhahn B. Brain tumor classification using sparse coding and dictionary learning. IEEE Int Conf Image Process 2014: 2752–2756.Google Scholar

  • [3]

    Al-Shaikhli SDS, Yang MY, Rosenhahn B. Coupled dictionary learning for automatic multi-label brain tumor segmentation in flair MRI images. Int Symp Vis Comput Adv Vis Comput Part I LNCS 2014; 8887: 489–500.Google Scholar

  • [4]

    Al-Shaikhli SDS, Yang MY, Rosenhahn B. Multi-region labeling and segmentation using a graph topology prior and atlas information in brain images. Comput Med Imag Grap J 2014; 38: 725–734.Google Scholar

  • [5]

    Angelini ED, Clatz O, Mandonnet E, Konukoglu E, Capelle L, Duffau H. Glioma dynamics and computational models: a review of segmentation, registration, and in silico growth algorithms and their clinical applications. Curr Medl Imaging Rev 2007; 3: 262–276.Web of ScienceGoogle Scholar

  • [6]

    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. MICCAI 2011; 14: 354–361.Google Scholar

  • [7]

    Bauer S, Wiest R, Nolte LP, Reyes M. A survey of MRI based medical image analysis for brain tumor studies. Phys Med Biol 2013; 58: R97–R129.Web of ScienceGoogle Scholar

  • [8]

    Brain Tumor Segmentation Database (BraTS-MICCAI). http://hal.inria.fr/hal-00935640. Accessed on November 2014.

  • [9]

    BraTS-MICCAI Website. http://martinos.org/qtim/miccai2013/results. Accessed on November 2014.

  • [10]

    Cao T, Jojic V, Modla S, Powell D, Czymmek K, Niethammer M. Robust multimodal dictionary learning. MICCAI Proc 2013; 16: 259–266.Google Scholar

  • [11]

    Cocosco CA, Zijdenbos AP, Evans AC. A fully automatic and robust brain MRI tissue classification method. Med Image Anal 2003; 7: 513–527.Google Scholar

  • [12]

    Cordier N, Menze B, Delingette H, Ayache N. Patch-based segmentation of brain tissues. Proc NCI-MICCAI BRATS 2013: 6–17.Google Scholar

  • [13]

    Delong A, Osokin A, Isack HN, Boykov Y. Fast approximate energy minimization with label costs. Int J Comput Vision 2012; 96: 1–27.Web of ScienceGoogle Scholar

  • [14]

    Duarte-Carvajalino JM, Sapiro G. Learning to sense sparse signals: simultaneous sensing matrix and sparsifying dictionary optimization. IEEE T Image Proc 2009; 18: 1395–1408.Web of ScienceGoogle Scholar

  • [15]

    Festa J, Pereira S, Mariz JA, Sousa N, Silva CA. Automatic brain tumor segmentation of multi-sequence MR images using random decision forests. Proc NCI-MICCAI BRATS 2013: 23–26.Google Scholar

  • [16]

    Fischl B, Salat DH, Busa E, et al. Whole brain segmentation: neurotechnique automated labeling of neuroanatomical structures in the human brain. Neuron 2002; 33: 341–355.Google Scholar

  • [17]

    Gladis Pushpa Rathi VP, Palani S. Linear discriminant analysis for brain tumor classification using feature selection. Int J Commun Eng 2012; 5: 130–134.Google Scholar

  • [18]

    Gooya A, Pohl KM, Bilello M, Biros G, Davatzikos C. Joint segmentation and deformable registration of brain scans guided by a tumor growth model. MICCAI Proc LNCS 2011; 6892: 532–540.Google Scholar

  • [19]

    Gooya A, Pohl KM, Bilello M, et al. GLISTR: glioma image segmentation and registration. IEEE T Med Imaging 2012; 31: 1941–1954.Web of ScienceGoogle Scholar

  • [20]

    Gordillo N, Montseny E, Sobrevilla P. State of the art survey on MRI brain tumor segmentation. Magn Reson Imaging 2013; 31: 1426–1438.Google Scholar

  • [21]

    Han J, Chang H, Loss L, et al. Comparison of sparse coding and kernel methods for histopathological classification of glioblastoma multiforme. ISBI 2011; 9: 711–714.Google Scholar

  • [22]

    Haralick RM, Shanmugam K, Dinstein I. Texture feature for image classification. IEEE T Syst Man Cyb 1973; SMC-3: 610–621.CrossrefGoogle Scholar

  • [23]

    Huang X, Dione DP, Compas CB, et al. Contour tracking in echocardiographic sequences via sparse representation and dictionary learning. Med Image Anal 2014; 18: 253–271.Web of ScienceGoogle Scholar

  • [24]

    Jenkinson M, Pechaud M, Smith S. BET2: MR-based estimation of brain, skull and scalp surfaces. In: Eleventh annual meeting of the organization for human brain mapping, vol. 17: 2005. http://www.humanbrainmapping.org/i4a/pages/index.cfm?pageid=1.

  • [25]

    Jiang S,Wu Y, Huang M, Yang W, Chen W, Feng Q. 3D brain tumor segmentation in multimodal MR images based on learning population- and patient-specific feature sets. Comput Med Imag Grap 2013; 37: 512–521.Web of ScienceGoogle Scholar

  • [26]

    Kaus M, Warfield SK, Nabavi A, Black PM, Jolesz FA, Kikinis R. Automated segmentation of MRI of brain tumors. Radiology 2001; 218: 586–591.Google Scholar

  • [27]

    Konukoglu E, Wells WM, Novellas S, et al. Monitoring slowly evolving tumors. ISBI 2008: 812–815.Google Scholar

  • [28]

    Meier R, Bauer S, Slotboom J, Wiest R, Reyes M. A hybrid model for multimodal brain tumor segmentation. Proc NCI-MICCAI BRATS 2013: 31–37.Google Scholar

  • [29]

    Menze B, Jakab A, Bauer S, et al. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE T Med Imaging 2014: 33. DOI: .CrossrefWeb of ScienceGoogle Scholar

  • [30]

    Moon N, Bullitt E, Leemput KV, Gerig G. Automatic brain and tumor segmentation. MICCAI Proc LNCS 2002; 2488: 372–379.Google Scholar

  • [31]

    National Institutes of Health. Image processing, analysis, and visualization. Center for Information Technology. http://mipav.cit.nih.gov/. Accessed on November 2014.

  • [32]

    Otsu N. A threshold selection method from gray-level histograms. IEEE T Syst Man Cyb 1979; 9: 62–66.Google Scholar

  • [33]

    Reza S, Iftekharuddin KM. Multi-class abnormal brain tissue segmentation using texture features. Proc NCI-MICCAI BRATS 2013: 38–42.Google Scholar

  • [34]

    Sachdeva J, Kumar V, Gupta I, Khandelwal N, Ahuja CK. Segmentation, feature extraction, multiclass brain tumor classification. J Digit Imaging 2013; 26: 1141–1150.Web of ScienceGoogle Scholar

  • [35]

    Selvaraj H, Thamarai S, Selvathi D, Gewali L. Brain MRI slices classification using least squares support vector machine. Int J Intell Comput Med Sci Image Proc 2007; 1: 21–33.Google Scholar

  • [36]

    Smith SM. Fast robust automated brain extraction. Hum Brain Mapp 2002; 17: 143–155.Google Scholar

  • [37]

    Sokolova M, Lapalme G. A systematic analysis of performance measures for classification tasks. Inform Process Manag 2009; 45: 427–437.Google Scholar

  • [38]

    The Internet Brain Segmentation Repository. http://www.nitrc.org/projects/ibsr/. Accessed on November 2014.

  • [39]

    Thiagarajan JJ, Ramamurthy KN, Rajan D, Spanias A. Kernel sparse models for automatic tumor segmentation. Int J Artif Intell Tools 2013; 12: 1–12.Google Scholar

  • [40]

    Tong T, Wolz R, Coupé P, Hajnal JV, Rueckert D. Segmentation of MR images via discriminative dictionary learning and sparse coding: application to hippocampus labeling. NeuroImage 2013; 76: 11–23.Google Scholar

  • [41]

    Tsai YF, Chiang IJ, Lee YC, Liao CC, Wang KL. Automatic MRI meningioma segmentation using estimation maximization. Proc IEEE Eng Med Biol Soc 2005; 3: 3074–3077.Google Scholar

  • [42]

    Tustison N, Wintermark M, Durst C, Avants B. ANTs and Arboles. Proc NCI-MICCAI BRATS 2013: 47–50.Google Scholar

  • [43]

    Warfield SK, Kaus M, Jolesz FA, Kikinis R. Adaptive, template moderated, spatially varying statistical classification. Med Image Anal 2000; 4: 43–55.Google Scholar

  • [44]

    Weiss N, Rueckert D, Rao A. Multiple sclerosis lesion segmentation using dictionary learning and sparse coding. MICCAI 2013: 735–742.Google Scholar

  • [45]

    Weizman L, Ben Sira L, Joskowicz L, et al. Automatic segmentation, internal classification, and follow-up of optic pathway gliomas in MRI. Med Image Anal 2012; 16: 177–188.Web of ScienceGoogle Scholar

  • [46]

    Whole brain atlas database. http://www.med.harvard.edu/aanlib/home.html. Accessed on November 2014.

  • [47]

    Wu P, Xie K, Zheng Y, Wu C. Brain tumors classification based on 3D shape. Adv Intell Soft Comput 2012; 160: 277–283.Google Scholar

  • [48]

    Zhao L, Sarikaya D, Corso JJ. Automatic brain tumor segmentation with MRF on supervoxels. Proc NCI-MICCAI BRATS 2013: 51–54.Google Scholar

  • [49]

    Zhao L, Wu W, Corso JJ. Semi-automatic brain tumor segmentation by constrained MRFs using structural trajectories. MICCAI 2013; 16: 567–575.Google Scholar

About the article

Corresponding author: Saif Dawood Salman Al-Shaikhli, Institute for Information Processing, Leibniz University Hannover, Appelstr. 9A, 30167 Hannover, Germany, Phone: +49 511 762-5319, E-mail:

Received: 2015-04-15

Accepted: 2015-07-10

Published Online: 2015-08-06

Published in Print: 2016-08-01

Citation Information: Biomedical Engineering / Biomedizinische Technik, ISSN (Online) 1862-278X, ISSN (Print) 0013-5585, DOI: https://doi.org/10.1515/bmt-2015-0071.

Export Citation

©2016 Walter de Gruyter GmbH, Berlin/Boston. Copyright Clearance Center

Comments (0)

Please log in or register to comment.
Log in