Advertisement

3D variational brain tumor segmentation using Dirichlet priors on a clustered feature set

  • Karteek PopuriEmail author
  • Dana Cobzas
  • Albert Murtha
  • Martin Jägersand
Original Article

Abstract

Purpose

Brain tumor segmentation is a required step before any radiation treatment or surgery. When performed manually, segmentation is time consuming and prone to human errors. Therefore, there have been significant efforts to automate the process. But, automatic tumor segmentation from MRI data is a particularly challenging task. Tumors have a large diversity in shape and appearance with intensities overlapping the normal brain tissues. In addition, an expanding tumor can also deflect and deform nearby tissue. In our work, we propose an automatic brain tumor segmentation method that addresses these last two difficult problems.

Methods

We use the available MRI modalities (T1, T1c, T2) and their texture characteristics to construct a multidimensional feature set. Then, we extract clusters which provide a compact representation of the essential information in these features. The main idea in this work is to incorporate these clustered features into the 3D variational segmentation framework. In contrast to previous variational approaches, we propose a segmentation method that evolves the contour in a supervised fashion. The segmentation boundary is driven by the learned region statistics in the cluster space. We incorporate prior knowledge about the normal brain tissue appearance during the estimation of these region statistics. In particular, we use a Dirichlet prior that discourages the clusters from the normal brain region to be in the tumor region. This leads to a better disambiguation of the tumor from brain tissue.

Results

We evaluated the performance of our automatic segmentation method on 15 real MRI scans of brain tumor patients, with tumors that are inhomogeneous in appearance, small in size and in proximity to the major structures in the brain. Validation with the expert segmentation labels yielded encouraging results: Jaccard (58%), Precision (81%), Recall (67%), Hausdorff distance (24 mm).

Conclusions

Using priors on the brain/tumor appearance, our proposed automatic 3D variational segmentation method was able to better disambiguate the tumor from the surrounding tissue.

Keywords

MRI segmentation Variational methods Clustering methods Tumors Edema 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Archip N, Jolesz F, Warfield S (2007) A validation framework for brain tumor segmentation. Acad Radiol 14(10): 1242–1251PubMedCrossRefGoogle Scholar
  2. 2.
    Batista J, Kitney R (1995) Extraction of tumors from MR images of the brain by texture and clustering. In: Proceedings of the 8th international conference on image analysis and processing (ICIAP ’95). Springer, London, pp 235–240Google Scholar
  3. 3.
    Capelle AS, Alata O, Fernandez-Maloigne C, Ferrié JC (2000) Unsupervised segmentation for automatic detection of brain tumors in MRI. In: IEEE international conference on image processing, ICIP 2000, Vancouver, CanadaGoogle Scholar
  4. 4.
    Chan T, Vese L (2001) Active contours without edges. IEEE Trans Image Process 10(2): 266–277PubMedCrossRefGoogle Scholar
  5. 5.
    Chan T, Sandberg B, Vese L (2000) Active contours without edges for vector-valued images. J Vis Commun Image Represent 11(2): 130–141CrossRefGoogle Scholar
  6. 6.
    Cobzas D, Birkbeck N, Schmidt M, Jagersand M, Murtha A (2007) 3d variational brain tumor segmentation using a high dimensional feature set. In: IEEE 11th international conference on computer vision, pp 1–8Google Scholar
  7. 7.
    Corso J, 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
  8. 8.
    Cremers D, Rousson M, Deriche R (2007) A review of statistical approaches to level set segmentation: integrating color, texture, motion and shape. Int J Comput Vis 72(2): 195–215CrossRefGoogle Scholar
  9. 9.
    Droske M, Bernhard M, Martin R, Carlo S (2001) An adaptive level set method for medical image segmentation. In: IPMI ’01: Proceedings of the 17th international conference on information processing in medical imaging, Springer, London, pp 416–422Google Scholar
  10. 10.
    Fletcher-Heath L, Hall L, Goldgof D, Murtagh F (2001) Automatic segmentation of non-enhancing brain tumors in magnetic resonance images. Artif Intell Med 21(1-3): 43–63PubMedCrossRefGoogle Scholar
  11. 11.
    Gibbs P, Buckley D, Blackb S, Horsman A (1996) Tumour volume determination from MR images by morphological segmentation. Phys Med Biol 41: 2437–2446PubMedCrossRefGoogle Scholar
  12. 12.
    Kaus M, Warfield S, Nabavi A, Black P, Jolesz F, Kikinis R (1999) Adaptive template moderated brain tumor segmentation in MRI. Bildverarbeitung fur die Medizin. Springer, Berlin, pp 102–106Google Scholar
  13. 13.
    Kaus M, Warfield S, Nabavi A, Simon K, Chatzidakis E, Black P, Jolesz F, Kikinis R (1999) Segmentation of meningiomas and low grade gliomas in MRI. In: MICCAI ’99: Proceedings of the second international conference on medical image computing and computer-assisted intervention, Springer, London, pp 1–10Google Scholar
  14. 14.
    Khotanlou H, Atif J, Colliot O, Bloch I (2006) 3D brain tumor segmentation using fuzzy classification and deformable models. Fuzzy logic and applications. Springer, New York, pp 312–318Google Scholar
  15. 15.
    Koller D, Friedman N (2005) Structured probabilistic models, (unpublished manuscript)Google Scholar
  16. 16.
    Lee C, Greiner R, Schmidt M (2005) Support vector random fields for spatial classification. Lect Notes Comput Sci 3721: 121CrossRefGoogle Scholar
  17. 17.
    Lee C, Greiner R, Zaiane O (2006) Efficient spatial classification using decoupled conditional random fields. Lect Notes Comput Sci 4213: 272CrossRefGoogle Scholar
  18. 18.
    Liu J, Chelberg D, Smith C, Chebrolu H (2007) Distribution-based level set segmentation for medical images. In: 18th British machine vision conference (BMVC’07). Warwick, UK, 10–13 Sept, 2007Google Scholar
  19. 19.
    Macqueen JB (1967) Some methods of classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematics, statistics and probability, pp 281–297Google Scholar
  20. 20.
    Malik J, Belongie S, Leung T, Shi J (2001) Contour and texture analysis for image segmentation. IJCV 43(1): 29–44CrossRefGoogle Scholar
  21. 21.
    Mazzara G, Velthuizen R, Pearlman J, Greenberg H, Wagner H (2004) Brain tumor target volume determination for radiation treatment planning through automated MRI segmentation. Int J Radiat Oncol Biol Phys 59(1): 300–312PubMedCrossRefGoogle Scholar
  22. 22.
    Popuri K, Cobzas D, Jagersand M, Shah S, Murtha A (2009) 3D variational brain tumor segmentation on a clustered feature set. In: Society of photo-optical instrumentation Engineers (SPIE) conference seriesGoogle Scholar
  23. 23.
    Prastawa M, Bullitt E, Moon N, Leemput K, Gerig G (2003) Automatic brain tumor segmentation by subject specific modification of atlas priors. Acad Radiol 10(12): 1341–1348PubMedCrossRefGoogle Scholar
  24. 24.
    Roth S, Black M (2005) Fields of experts: a framework for learning image priors. In: IEEE computer society conference on computer vision and pattern recognition, IEEE Computer Society, 1999, vol 2, p 860Google Scholar
  25. 25.
    Rousson M, Deriche R (2002) A variational framework for active and adaptative segmentation of vector valued images. In: IEEE workshop on motion and video comp, pp 56–61Google Scholar
  26. 26.
    Rousson M, Brox T, Deriche R (2003) Active unsupervised texture segmentation on a diffusion based feature space. In: Computer vision and pattern recognition, 2003. Proceedings. 2003 IEEE computer society conference on, vol 2, pp 699–704Google Scholar
  27. 27.
    Schmidt M, Levner I, Greiner R, Murtha A, Bistritz A (2005) Segmenting brain tumors using alignment-based features. In: Proceedings fourth international conference on machine learning and applications, 2005. pp 215–220Google Scholar
  28. 28.
    Sean H, Elizabeth B, Guido G (2002) Level set evolution with region competition: automatic 3-d segmentation of brain tumors. In: Proceedings of the 16th international conference on pattern recognition. IEEE Computer Society, pp 532–535Google Scholar
  29. 29.
    Shi J, Malik J (2000) Normalized cuts and image segmentation. IEEE Trans Pattern Anal Mach Intell 22: 888–905CrossRefGoogle Scholar
  30. 30.
    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
  31. 31.
    Smith S, Brady J (1997) Susan a new approach to low level image processing. Int J Comput Vision 23(1): 45–78CrossRefGoogle Scholar
  32. 32.
    Vaidyanathan M, Clarke L, Velthuizen R, Phuphanich S, Bensaid A, Hall L, Bezdek J, Greenberg H, Trotti A, Silbiger M (1995) Comparison of supervised MRI segmentation methods for tumor volume determination during therapy. Magn Reson Imaging 13(5): 719–728PubMedCrossRefGoogle Scholar
  33. 33.
    Varma M, Zisserman A (2005) A statistical approach to texture classification from single images. Int J Comput Vis V62(1): 61–81Google Scholar
  34. 34.
    Velthuizen R (1995) Validity guided clustering for brain tumor segmentation [treatment planning]. In: IEEE 17th annual conference engineering in medicine and biology society, 1995, vol 1, pp 413–414Google Scholar
  35. 35.
    Vinitski S, Gonzalez C, Knobler R, Andrews D, Iwanaga T, Curtis M (1999) Fast tissue segmentation based on a 4D feature map in characterization of intracranial lesions. J Magn Reson Imaging 9(6): 768–776PubMedCrossRefGoogle Scholar
  36. 36.
    Xie K, Yang J, Zhang Z, Zhu Y (2005) Semi-automated brain tumor and edema segmentation using MRI. Eur J Radiol 56(1): 12–19PubMedCrossRefGoogle Scholar
  37. 37.
    Yazdan-Shahmorad A, Jahanian H, Patel S, Soltanian-Zadeh H (2007) Automatic brain tumor segmentation using tissue diffisivity characteristics. In: ISBI 2007 4th IEEE international symposium on biomedical imaging from nano to macro, 2007, pp 780–783Google Scholar
  38. 38.
    Zhang J, Ma K, Er M, Chong V (2004) Tumor segmentation from magnetic resonance imaging by learning via one-class support vector machine. In: International workshop on advanced image technology, pp 207–211Google Scholar
  39. 39.
    Zuiderveld K (1994) Contrast limited adaptive histogram equalization. In: Graphics gems IV, Academic Press, Waltham, pp 474–485Google Scholar

Copyright information

© CARS 2011

Authors and Affiliations

  • Karteek Popuri
    • 1
    Email author
  • Dana Cobzas
    • 1
  • Albert Murtha
    • 2
  • Martin Jägersand
    • 1
  1. 1.Department of Computing ScienceUniversity of AlbertaEdmontonCanada
  2. 2.Department of OncologyUniversity of AlbertaEdmontonCanada

Personalised recommendations