Advertisement

Brain tumor detection and segmentation in a CRF (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features

  • Wei WuEmail author
  • Albert Y. C. Chen
  • Liang Zhao
  • Jason J. Corso
Original Article

Abstract

Purpose

Detection and segmentation of a brain tumor such as glioblastoma multiforme (GBM) in magnetic resonance (MR) images are often challenging due to its intrinsically heterogeneous signal characteristics. A robust segmentation method for brain tumor MRI scans was developed and tested.

Methods

Simple thresholds and statistical methods are unable to adequately segment the various elements of the GBM, such as local contrast enhancement, necrosis, and edema. Most voxel-based methods cannot achieve satisfactory results in larger data sets, and the methods based on generative or discriminative models have intrinsic limitations during application, such as small sample set learning and transfer. A new method was developed to overcome these challenges. Multimodal MR images are segmented into superpixels using algorithms to alleviate the sampling issue and to improve the sample representativeness. Next, features were extracted from the superpixels using multi-level Gabor wavelet filters. Based on the features, a support vector machine (SVM) model and an affinity metric model for tumors were trained to overcome the limitations of previous generative models. Based on the output of the SVM and spatial affinity models, conditional random fields theory was applied to segment the tumor in a maximum a posteriori fashion given the smoothness prior defined by our affinity model. Finally, labeling noise was removed using “structural knowledge” such as the symmetrical and continuous characteristics of the tumor in spatial domain.

Results

The system was evaluated with 20 GBM cases and the BraTS challenge data set. Dice coefficients were computed, and the results were highly consistent with those reported by Zikic et al. (MICCAI 2012, Lecture notes in computer science. vol 7512, pp 369–376, 2012).

Conclusion

A brain tumor segmentation method using model-aware affinity demonstrates comparable performance with other state-of-the art algorithms.

Keywords

Brain tumor segmentation Model-aware affinity SVM CRF Superpixels 

Notes

Acknowledgments

This work was partially supported by the Chinese National Science Foundation (61273241) and the NSF CAREER grant IIS-0845282. Conflict of Interest   The authors have declared that no conflict of interest exists.

References

  1. 1.
    Liu J, Udupa JK, Odhner D, Hackney D, Moonis G (2005) A system for brain tumor volume estimation via MR imaging and fuzzy connectedness. Comput Med Imaging Graphics 29(1):21–34Google Scholar
  2. 2.
    Sled JG, Zijdenbos AP, Evans AC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging 17(1):87–97PubMedCrossRefGoogle Scholar
  3. 3.
    Belaroussi B, Milles J, Carme S, Zhu YM, Benoit-Cattin H (2006) Intensity non-uniformity correction in MRI: existing methods and their validation. Med Image Anal 10(2):234PubMedCrossRefGoogle Scholar
  4. 4.
    Madabhushi A, Udupa JK (2005) Interplay between intensity standardization and inhomogeneity correction in MR image processing. IEEE Trans Med Imaging 24(5):561–576PubMedCrossRefGoogle Scholar
  5. 5.
    Patel MR, Tse V (2004) Diagnosis and staging of brain tumors. Semin Roentgenol 39(3):347–360Google Scholar
  6. 6.
    Prastawa M, Bullitt E, Ho S, Gerig G (2004) A brain tumor segmentation framework based on outlier detection. Med Image Anal 8(3):275–283PubMedCrossRefGoogle Scholar
  7. 7.
    Phillips W, Velthuizen R, Phuphanich S, Hall L, Clarke L, Silbiger M (1995) Application of fuzzy c-means segmentation technique for tissue differentiation in MR images of a hemorrhagic glioblastoma multiforme. Magn Reson Imaging 13(2):277–290PubMedCrossRefGoogle Scholar
  8. 8.
    Clark MC, Hall LO, Goldgof DB, Velthuizen R, Murtagh FR, Silbiger MS (1998) Automatic tumor segmentation using knowledge-based techniques. IEEE Trans Med Imaging 17(2):187–201PubMedCrossRefGoogle Scholar
  9. 9.
    Fletcher-Heath LM, Hall LO, Goldgof DB, Murtagh FR (2001) Automatic segmentation of non-enhancing brain tumors in magnetic resonance images. Artif Intell Med 21(1–3):43–63PubMedCrossRefGoogle Scholar
  10. 10.
    Warfield SK, Kaus M, Jolesz FA, Kikinis R (2000) Adaptive, template moderated, spatially varying statistical classification. Med Image Anal 4(1):43–55PubMedCrossRefGoogle Scholar
  11. 11.
    Kaus MR, Warfield SK, Nabavi A, Black PM, Jolesz FA, Kikinis R (2001) Automated segmentation of MR images of Brain Tumors1. Radiology 218(2):586–591PubMedCrossRefGoogle Scholar
  12. 12.
    Prastawa M, Bullitt E, Moon N, Van Leemput K, Gerig G (2003) Automatic brain tumor segmentation by subject specific modification of atlas priors. Acad Radiol 10(12):1341–1348PubMedCentralPubMedCrossRefGoogle Scholar
  13. 13.
    Wells W III, Grimson WEL, Kikinis R, Jolesz FA (1996) Adaptive segmentation of MRI data. IEEE Trans Med Imaging 15(4):429–442PubMedCrossRefGoogle Scholar
  14. 14.
    Guillemaud R, Brady M (1997) Estimating the bias field of MR images. IEEE Trans Med Imaging 16(3):238–251PubMedCrossRefGoogle Scholar
  15. 15.
    Corso JJ, Sharon E, Dube S, El-Saden S, Sinha U, Yuille A (2008) Efficient multilevel brain tumor segmentation with integrated bayesian model classification. IEEE Trans Med Imaging 27(5):629–640PubMedCrossRefGoogle Scholar
  16. 16.
    Zhou J, Chan K, Chong V, Krishnan S (2006) Extraction of brain tumor from MR images using one-class support vector machine. In: 27th annual international conference of the engineering in medicine and biology society, 2005. IEEE-EMBS 2005. pp 6411–6414Google Scholar
  17. 17.
    Xuan X, Liao Q (2008) Automated MRI brain rumor segmentation based on feature extraction. Comput Eng 9:070Google Scholar
  18. 18.
    Corso J, Yuille A, Sicotte N, Toga A (2007) Detection and segmentation of pathological structures by the extended graph-shifts algorithm. In: Medical Image Computing and Computer-Assisted Intervention—MICCAI. pp 985–993Google Scholar
  19. 19.
    Schapire RE, Freund Y, Bartlett P, Lee WS (1998) Boosting the margin: a new explanation for the effectiveness of voting methods. Ann Stat 26(5):1651–1686CrossRefGoogle Scholar
  20. 20.
    Dettling M (2004) BagBoosting for tumor classification with gene expression data. Bioinformatics 20(18):3583–3593PubMedCrossRefGoogle Scholar
  21. 21.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32CrossRefGoogle Scholar
  22. 22.
    Zikic D, Glocker B, Konukoglu E, Criminisi A, Demiralp C, Shotton J, Thomas O, Das T, Jena R, Price S (2012) Decision forests for tissue-specific segmentation of high-grade gliomas in multi-channel MR. In: Medical Image Computing and Computer-Assisted Intervention—MICCAI. Lecture notes in computer science, vol 7512. pp 369–376Google Scholar
  23. 23.
    Liu H, Motoda H, Yu L (2004) A selective sampling approach to active feature selection. Artif Intell 159(1):49–74CrossRefGoogle Scholar
  24. 24.
    Fernández A, García S, Herrera F (2011) Addressing the classification with imbalanced data: open problems and new challenges on class distribution. In: Hybrid artificial intelligent systems. Lecture notes in computer science, vol 6678. pp 1–10Google Scholar
  25. 25.
    Li SZ (1995) Markov random field modeling in computer vision. Springer, New YorkCrossRefGoogle Scholar
  26. 26.
    Zhang Y, Brady M, Smith S (2001) Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans Med Imaging 20(1):45–57PubMedCrossRefGoogle Scholar
  27. 27.
    Lee CH, Schmidt M, Murtha A, Bistritz A, Sander J, Greiner R (2005) Segmenting brain tumors with conditional random fields and support vector machines. In: Computer vision for biomedical, image applications. Lecture notes in computer science, vol 3765. pp 469–478Google Scholar
  28. 28.
    Felzenszwalb PF, Huttenlocher DP (2004) Efficient graph-based image segmentation. Int J Comput Vis 59(2):167–181CrossRefGoogle Scholar
  29. 29.
    Xu C, Corso JJ (2002) Evaluation of super-voxel methods for early video processing. In: IEEE conference on computer vision and pattern recognition (CVPR) 2012, pp 1202–1209Google Scholar
  30. 30.
    Bauer S, Nolte L-P, Reyes M (2011) Fully automatic segmentation of brain tumor images using support vector machine classification in combination with hierarchical conditional random field regularization. In: Medical Image Computing and Computer-Assisted Intervention—MICCAI 2011. Springer, pp 354–361Google Scholar
  31. 31.
    Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Class 10(3):61–74Google Scholar
  32. 32.
    Ren X, Malik J (2003) Learning a classification model for segmentation. In: Proceedings of the ninth IEEE international conference on computer vision, 2003. pp 10–17Google Scholar
  33. 33.
    Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell 18(8):837–842Google Scholar
  34. 34.
    Lee TS (1996) Image representation using 2D Gabor wavelets. IEEE Trans Pattern Anal Mach Intell 18(10):959–971 Google Scholar
  35. 35.
    Boykov Y, Veksler O, Zabih R (2001) Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell 23(11):1222–1239Google Scholar
  36. 36.
    Boykov Y, Kolmogorov V (2004) An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans Pattern Anal Mach Intell 26(9):1124–1137PubMedCrossRefGoogle Scholar
  37. 37.
    Kolmogorov V, Zabin R (2004) What energy functions can be minimized via graph cuts? IEEE Trans Pattern Anal Mach Intell 26(2):147–159PubMedCrossRefGoogle Scholar
  38. 38.
    Zabih RD, Veksler O, Boykov Y (2004) System and method for fast approximate energy minimization via graph cuts. U. S. Patent 6,744, 923 [p]. 1 June 2004Google Scholar
  39. 39.
    Delong A, Osokin A, Isack HN, Boykov Y (2012) Fast approximate energy minimization with label costs. Int J Comput Vis 96(1):1–27CrossRefGoogle Scholar
  40. 40.
    Singh SK, Hawkins C, Clarke ID, Squire JA, Bayani J, Hide T, Henkelman RM, Cusimano MD, Dirks PB (2004) Identification of human brain tumour initiating cells. Nature 432(7015):396–401PubMedCrossRefGoogle Scholar
  41. 41.
    Zikic D, Glocker B, Konukoglu E, Shotton J, Criminisi A, Ye DH, Demiralp C, Thomas OM, Das T, Jena R, Price SJ (2012) Context-sensitive classification forests for segmentation of brain tumor tissues. In: Proceedings of MICCAI-BRATS (2012)Google Scholar

Copyright information

© CARS 2013

Authors and Affiliations

  • Wei Wu
    • 1
    • 2
    • 3
    Email author
  • Albert Y. C. Chen
    • 1
  • Liang Zhao
    • 1
  • Jason J. Corso
    • 1
  1. 1.Department of Computer Science and EngineeringSUNY at BuffaloBuffaloUSA
  2. 2.School of Information EngineeringWuhan University of TechnologyWuhanChina
  3. 3.Key Laboratory of Fiber Optic Sensing Technology and Information ProcessingWuhan University of TechnologyWuhanChina

Personalised recommendations