Document Type : Full Research Paper


1 M.Sc., Control and Intelligent Processing Center of Excellence, School of Electrical and computer Engineering, College of Engineering, University of Tehran

2 Profeesor, school of electrical and computer engineering, control and intelligent processing center of Excellence (CIPCE), university of Tehran



Segmentation of tumors in magnetic resonance images is an important task. However, it is quite time consuming and has low accuracy and reproducibility when performed manually. Automating the process is challenging, due to high diversity in appearance of tumor tissue in different patients and in many cases, similarity between tumor and normal tissues. This paper presents semi-automatic approach for analysis of multi-parametric magnetic resonance images (MRI) to segment a highly malignant brain tumor called Glioblastoma multiform (GBM). MRI studies of 12 patients with GBM tumors are used. To show that the proposed method identifies Gd-enhanced tumor pixels from T1-post contrast images minimal user interactions. They are also used to illustrate that the segmentation results obtained by the proposed approach are close to those of an expert, by showing excellent correlations among them (R2=0.97). In order to evaluate the proposed method in practical applications, effects of treatment of GBM brain tumors using Bevacizumab are predicted. Bevacizumab is a recent therapy for stopping tumor growth and even shrinking tumor through inhibition of vascular development (angiogenesis). To this end, two image series of 12 patients before and after treatment and relative changes in the volumes of the Gd-enhanced regions in T1-post contrast images are used as measure of response. The proposed method applies signal decomposition with KNN classifier to minimize user interactions and increase reproducibility of the results. Then histogram analysis is applied to extract statistical features from Gd-enhanced regions of tumor and quantify its micro structural characteristics. Predictive models developed in this work have large regression coefficients (maximum R2=0.91) indicating their capability to predict response to therapy. The results obtained by the proposed approach are compared with those of previous work where excellent correlations are obtained.


Main Subjects

[1]     M. C. Clark, O. Hall, B. Goldgof, R. Velthuizen, Murtagh, F. R. Murtagh, S. Silbiger, “Automatic tumor-segmentation using knowledgebased techniques,” IEEE transaction on medical imaging, 1998, vol. 117, pp. 187-201.
[2]     L. M. Fletcher-Health, L. O. Hall, D. B. Goldgof, F.R. Murtagh, “Automatic segmentation of non-enhancing brain tumors in 282 M.Prastawa et al,” Medical image analysis, Artificial intelligence in medicine 21, 2004, pp. 275-283.
[3]     M.B. Cuadra, J. Gomez, P. Hagmann, C. Pollo, J. G. Villemure, B. M. Dawant, J. Ph. Thiran, “Atlas-based segmentation of pathological brains using a model of tumor growth,” Medical image computing and computer-Assisted intervention MICCAI, Springer, 2002, pp. 380-387.
[4]     L. Schad, S. Bluml, I. Zuna, “MR tissue characterization of intracnial tumors by means of texture analysis,” Elsevier, 1993, Vol. 11, pp. 889-896.
[5]     Glioblastoma Multiform (GBM):, retrieved on july 3rd, 2009.
[6]     E. C. Holland, “Glioblastoma Multiform: The Terminator,” in proc. Natl. Acad. Sci. USA. 2000, Vol. 97, no. 12, pp.6242-6244.
[7]     C. Nieder, M. P. Mehta, R. Jalali, Combined Radio and Chemotherapy of Brain Tumors in Adult Patients, Clin Oncol (2009), doi: 10.1016/ j. Clon. 2009.5.003. (Article in Press).
[8]     S. Mueller, S.Chang, “Pediatric Brain Tumors: Current Treatment Strategies and Future Therapeutic Approaches,” Journal of Neurotherapeutics, 2009, vol. 6 (3), pp. 570- 586.
[9]     R. K. Jain, E. Tomaso, “Angiogenesis in Brain tumors,” 2007,vol. 8, pp. 610- 622.
[10] A. D. Norden, G. S. Young, K. Stayesh, A. Muzikansky, R. Klufas, G. L. Ross, A. S. Ciampa, L. G. Ebbeling, B. Levy, J. Drappatz, S. Kesari, P. Y. Wen, “Bevacizumab for Recurrent Malignant Gliomas: Efficacy, toxicity, and patterns of recurrence,” Journal of Neurology, 2008, vol. 70, pp. 779- 787.       
[11] S. Sathornsumetee, Y. Cao, J. E. Marcello, J. E. Herndon II, R. E. Mclendon, A. Desjardins, H. S. Fridman, M. W. Dewirst, J.J. Vredenburgh, J. N. Rich, “Tumor Angiogenic and Hypoxic Profiles Predict Rdiolographic Response and Survival in Malignant Astrocytoma patients Treated with Bevacizumab and Irinotecan,” Journal of Cilinical Oncology, 2008, vol. 26, no. 2, pp. 271-278.
[12] M. Najafi, H. Soltanian-Zadeh, K. Jafari-khouzani, L. Scarpace, T. Mikkelsen, “Prediction of Glioblastoma multiform response to Bevacizumab treatment using multi-parametric MRI,” Journal of Plos one, 2012, vol. 7.
[13] J. D. Christensen, “ Normalization of Brain Magnetic Resonance Images using Histogram Even- order Derivative Analysis,” Magnetic Resonance Imaging, 2003, vol. 21, no. 7, pp. 817- 820.
[14] Y. Zhang, M. Brady, S. Smith, “Segmentation of Brain Images through a Hidden Random Field Model and the Expectation Maximization Algorithm,” IEEE Trans Med Image, 2001, vol.20, pp. 45-57.
[15] L. G. Nyul, JK. Udupa, “On Standardizing the MR Intensity Scale,” 1999, vol. 42, pp. 1072- 1081.
[16] P. Schroeter, JM. Vesin, T. Langenberger, R. Meuli, “Robust Parameter Estimation of  Intensity Distribution for Brain Magnetic Resonance Images,” IEEE Trans Med Image, 1998, vol. 17, pp. 172- 186.
[17] M. C. Clark, B. Goldgof, R. Veltuizen, FR. Murtagh, MS. Silbiger, “Automatic Tumor Segmentation Using Knowledge- based Techniques,” IEEE Trans Med, 1998, vol. 17, pp. 187-201.
[18] K. Somasundaram, T. Kalaiselvi, “Fully Automatic Brain Extraction Algorithm for Axial T2-Weighted Magnetic Resonance Images,” Computers in Biology and Medicine, Elsevier, 2010, vol. 40, pp. 811-822.
[19] S. M. Smith, “Fast Robust Automated Brain Extraction,” Human Brain Mapping, 2002, vol. 17, pp. 143-155.
[20] D. W. Shattuck, S. R. Sandor-Leahy, K. A. Schaper, D. A. Rottenberg, R. M. Leahy, “Magnetic Resonance Image Tissue Classification Using a Partial Volume Model,” Neuroimage, 2001, no. 5, vol. 13, pp. 856- 876.
[21] J. Ashburmer, K. J. Friston, “Voxel Based Morphometry: the Methods,” Neuroimage, 2000, vol. 11, pp. 805-821.
[22] M. S. Atkins, B. T. Mackiewich, “Fully Automatic Segmentation of the Brain in MRI,” IEEE Transaction on Mdical Imaging, 1998, no. 17, vol. 1, pp. 89- 107.
[23] A. H. Zhuang, D. J. Valentino, A.W. Toga, “Skull-stripping Magnetic Resonance Brain Images Using a Model based Level Set,” Neuroimage, 2006, no. 1, vol. 32, pp. 79-92.
[24] S.W. Hartley, A. I. Scher, E. S. C. Korf, L. R. White, L. J. Launer, “Analysis and Validation of Automated Skull Stripping Tools: a Validation Study Based on 296 MR Images from the Honolulu Asia aging Study,” Neuroimage, 2006, vol. 30, pp. 1179-1186.
[25] M. Lee, J. H. Kim, I. Y. Kim, J. S. Kwon, S. I. Kim, “Evaluation of Automated and Semi-stripping Algorithm: Similarity Index and Segmentation Error,” Computers in Biology and Medicine, 2003, no. 6, vol. 33, pp. 495-507.
[26] M. Sonka, V. Hlavac, R. Boyle, “In Image Processing: Analysis and Machine Vision,” Second Edition, books/ Cole Publishing Company, 1999.
[27] S. Taheri, S. H. Ong, V. F. H. Chong, “Level-set Segmentation of Brain Tumors Using a Threshold- based Speed Function,” Image and Vision Computing, 2010, vol. 28, pp. 26-37.
[28] H. Soltanian-ZADEH, J. P. Windham, A. E. Yagle, “Optional Transformation for Correcting Partial Volume Averaging Effects in Magnetic Resonance Imaging,” IEEE Transaction on Nuclear Science, Aug 1993,vol. 40, no. 4, pp. 1204- 1212.
[29] H. Soltanin- Zadeh, J. P. Windham, D. J. Peck, “Optimal Linear Transformation for MRI Feature Extraction,” IEEE Transaction on Medical Imaging, 1996, vol. 15, no. 6, pp. 749-767.
[30] H. Soltanin- Zadeh, J. P. Windham, D. J. Peck, T. Mikkelsen, “Feature Space Analysis of MRI,” Magnetic Resonance In Medicine, 1998, vol. 40, no. 3, pp. 443-453.
[31] A. Rajendran, R. Dhanasekaran, “A  Hybrid Method Based on Fuzzy Clustering and Active Contour using GGVF for Brain Tumor Segmentation on MRI Images,” European Journal of Scientific Research, 2011, vol. 16, pp. 305-313.
[32] D. Selvathi, H. Selvaraj, S. Thamara Selvi, “Hybrid Approach for Brain Tumor Segmentation in Magnetic Resonance Images Using Cellular Neural Networks and Optimization Techniques,” International Journal of Computational Intelligence  and Applications, 2011, vol. 9, no. 1, pp. 17-31.
[33] W. Dou, S. Ruan, Y. Chen, D. Bloyet, J. M. Constans, “ A Framework of Fuzzy Information Fusion For Segmentation of Brain Tumor Tissues on MR images,” Image and Vision Computing, 2007, vol. 25, pp. 164-171.
[34] N. Behzadfar, H. Soltanin- Zadeh, “Reproducibility study of brain tumors response to bevacizumab treatment”, International Conference on Medical Information and Bioengineering, pp. 106-110, 2011