Voxel Based Treatment Prediction Using Diffusion Anisotropy Indices and Spatial Information in Glioblastoma Multiform Tumor

Sabahi, Hadi; Soltanian Zadeh, Hamid; Scarpace, Lisa; Mikkelsen, Tom

doi:10.22041/ijbme.2012.13166

Document Type : Full Research Paper

Authors

¹ Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University of Tehran

² 1Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University of Tehran

³ Hermelin Brain Tumor Research Center, Neurosurgery Department, Henry Ford Health System, Detroit, MI 48202, USA

10.22041/ijbme.2012.13166

Abstract

In this paper, we propose a method to predict the outcome of Bevacizumab therapy on Glioblastoma Multiform (GBM) tumors. The method uses diffusion anisotropy indices (DAI) and spatial information to predict the treatment response of each tumor voxel. These DAIs are Fractional Anisotropy, Mean Diffusivity, Relative Anisotropy, and Volume Ratio, extracted from Diffusion Tensor Imaging (DTI) data before treatment. The spatial information is considered as the distance of each tumor voxel from the tumor center, extracted from pre-treatment post-contrast T1-weighted Magnetic Resonance Images (pc-T1-MRI). DAIs and spatial information of each tumor voxel are considered as feature vector. DTI and pc-T1-MRI are gathered before and after the treatment of seven GBM patients. First, DAIs of all brain voxels and the distance of each tumor voxel from the tumor center are calculated. Second, the method registers pretreatment DAI maps and post-treatment pc-T1-MRI to pre-treatment pc-T1-MRI. Next, the tumor is segmented using thresholding technique from pc-T1-MRI. Then, Gd-enhanced voxels of the pre- and posttreatment pc-T1-MRI are compared to label the feature vectors. Three classifiers were evaluated, including Support Vector Machine, K-Nearest Neighbor, and Artificial Neural Network. Classification results show a preference for K-Nearest Neighbor based on well-established performance measures.

Keywords

Main Subjects

Biomedical Image Processing / Medical Image Processing

References

[1] Zimring D G, Mewes A U, Maddah M, Warfield S K; Diffusion tensor magnetic resonance imaging in multiple sclerosis; American Society of Neuroimaging 2005; 15: 68-81.

[2] Bammer R, Acar B, Moseley M E; In vivo MR tractography using diffusion imaging; European Journal of Radiology 2003; 45: 223 234.

[3] Besser P J and Jones D K; Diffusion-tensor MRI: theory, experimental design and data analysis –a technical review; NMR in Biomedicine 2002; 15: 456- 467.

[4] Hasan K M, Alexander A L, Narayana P A; Does Fractional Anisotropy Have Better Noise Immunity Characteristics Than Relative Anisotropy in Diffusion Tensor MRI? An Analytical Approach; Magnetic Resonance in Medicine 2004; 51: 413–417.

[5] Alexander A, Hasan K, Kindlmann G, Parker D, Tsuruda J; A geometric analysis of diffusion tensor measurements of the human brain; MagnReson Med 2000; 44: 291-283.

[6] Monahan WG and Kingsley PB; Contrast-to-noise ratios of diffusion anisotropy indices; MagnReson Med 2005; 53: 911-918.

[7] Wang J J, Chao T C, Wai Y Y, Hsu Y Y; Novel diffusion anisotropy indices: an evaluation; J MagnReson Imaging, 2006; 24: 211 217.

[8] Xu D, Cui J, Bansal R, Hao X, Liu J; The ellipsoidal area ratio: an alternative anisotropy index for diffusion tensor imaging; Magnetic Resonance Imaging 2009; 27: 311-323.

[9] Afzali M and Soltanian-Zadeh H; Comparison of Voxel-Based Morphometry (VBM) and Tractography of Diffusion Tensor MRI (DT-MRI) in Temporal Lobe Epilepsy; Int. Conf. on Electrical Engineering (ICEE) 2010; 18-23.

[10] Kang X, Herron T J, Woods D L; Validation of the anisotropy index ellipsoidal area ratio in diffusion tensor imaging; Magnetic Resonance Imaging 2010; 28: 546-556.

[11] Norden A D, Young G S, Setayesh K, Muzikansky A, Klufas R; Bevacizumab for recurrent malignant gliomas: Efficacy, toxicity, and patterns of recurrence; Journal of Neurology 2008; 70: 779-787.

[12] Sathornsumetee S, Cao Y, Marcello J E, Herndon II J E, McLendon R E; Tumor Angiogenic and Hypoxic Profiles Predict Radiographic Response and Survival in Malignant Astrocytoma Patients Treated with Bevacizumab and Irinotecan; Journal of Clinical Oncology 2008; 26: 271-278.

[13] Lipsitz D, Higgins R J, Kortz D G; Glioblastoma Multiforme: Clinical Findings, Magnetic Resonance Imaging, and Pathology in Five Dogs; Vet Pathol 2003; 40: 659-669.

[14] Bishop C; Pattern Recognition and Machine Learning; USA, New York; 1th ed; 2006;.

[15] Wang P and Verma R; On classifying disease-induced patterns in the brain using diffusion tensor images; Med Image ComputComput Assist Interv 2008; 11: 908- 916.

[16] Ingalhalikar M, Kanterakis S, Gur R, Roberts T P L, Verma R; DTI based Diagnostic Prediction of a Disease via Pattern Classification; Med Image Comput Comput Assist Interv 2010; 13: 558-568.

[17] Bihan D L, Mangin J F, Poupon C, Clark C A, Pappata S; Diffusion Tensor Imaging: Concepts and Applications; J MagnReson Imaging 2001; 13: 534- 546.

[18] Xu D, Cui J, Bansal R, Hao X, Liu J; The ellipsoidal area ratio:an alternative anisotropy index for diffusion tensor imaging; Magnetic Resonance Imaging 2009; 27: 311-323.

[19] Glass G V and Hopkins K D; Statistical Methods in Education and Psychology; Allyn& Bacon, 3th ed. 1995;.

[20] Selvaraj H, Selvi S T, Selvathi D, Gewali L; Brain MRI Slices Classification Using Least Squares Support Vector Machine; IC MED 2007; 1: 21-33.

[21] Nishikawa R M, Giger M L, Doi K, Vyborny C J, Schmidt R A; Computer Aided Detection of Clustered Microcalcifications in Digital Mammograms; Med. Biol. Eng. Comp. 1995; 33: 174-178.

[22] Koutroumbas S and Theodoridis K; Pattern Recognition; San Diego, Academic Press; 1999;.

[23] Reiser B and Faraggiand D; Estimation of the area under the ROC curve; Statistics in Medicine 2002; 21: 3093–3106.

Iranian Journal of Biomedical Engineering

Voxel Based Treatment Prediction Using Diffusion Anisotropy Indices and Spatial Information in Glioblastoma Multiform Tumor

References

References

Volume 5, Issue 4 - Serial Number 4
June 2011
Pages 289-295

Voxel Based Treatment Prediction Using Diffusion Anisotropy Indices and Spatial Information in Glioblastoma Multiform Tumor

References

References

Volume 5, Issue 4 - Serial Number 4June 2011Pages 289-295

Volume 5, Issue 4 - Serial Number 4
June 2011
Pages 289-295