Research ArticlesNo Access

Classification of Diffusion Tensor Metrics for the Diagnosis of a Myelopathic Cord Using Machine Learning

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, P. R. China

Department of Orthopaedic Surgery, The University of Hong Kong, 12 Sandy Bay Road, Hong Kong, Duchess of Kent Children’s Hospital, Pokfulam, Hong Kong

E-mail Address: yhud@hku.hk

Corresponding author.

Search for more papers by this author

Yanyan Shen

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, P. R. China

Search for more papers by this author

, and

Hanxiong Li

Department of Systems Engineering and Engineering Management, City University of Hong Kong, Kowloon, Hong Kong

School of Mechanical and Electrical Engineering, Central South University, Changsha, P. R. China

Search for more papers by this author

https://doi.org/10.1142/S0129065717500368Cited by:48 (Source: Crossref)

Abstract

In this study, we propose an automated framework that combines diffusion tensor imaging (DTI) metrics with machine learning algorithms to accurately classify control groups and groups with cervical spondylotic myelopathy (CSM) in the spinal cord. The comparison between selected voxel-based classification and mean value-based classification were performed. A support vector machine (SVM) classifier using a selected voxel-based dataset produced an accuracy of 95.73%, sensitivity of 93.41% and specificity of 98.64%. The efficacy of each index of diffusion for classification was also evaluated. Using the proposed approach, myelopathic areas in CSM are detected to provide an accurate reference to assist spine surgeons in surgical planning in complicated cases.

Keywords:

References

1. H. Adeli and S. Ghosh-Dastidar , Automated EEG-based Diagnosis of Neurological Disorders Inventing the Future of Neurology (CRC Press, Taylor & Francis, Boca Raton, Florida, 2010). Google Scholar
2. L. O’Dwyer, F. Lamberto, A. L. W. Bokde, M. Ewers et al., Using support vector machines with multiple indices of diffusion for automated classification of mild cognitive impairment, PLoS ONE 7(2) (2012) e32441. Medline, Web of Science, Google Scholar
3. H. Adeli, S. Ghosh-Dastidar and N. Dadmehr , Alzheimer’s disease and models of computation: Imaging, Classification, and Neural Models, J. Alzheimers Dis. 7(3) (2005) 187–199. Medline, Web of Science, Google Scholar
4. S. Ghosh-Dastidar and H. Adeli , Improved spiking neural networks for EEG classification and epilepsy and seizure detection, Integr. Comput.-Aided Eng. 14(3) (2007) 187–212. Web of Science, Google Scholar
5. A. Ortiz, J. Munilla, J. M. Górriz et al., Ensembles of deep learning architectures for the early diagnosis of the Alzheimer’s disease, Int. J. Neural. Syst. 26(7) (2016) 1650025. Link, Web of Science, Google Scholar
6. H. Adeli and S. Ghosh-Dastidar , A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection, Neural Netw. 22(10) (2009) 1419–1431. Medline, Web of Science, Google Scholar
7. Z. Sankari and H. Adeli , Probabilistic neural networks for EEG-based diagnosis of Alzheimer’s disease using conventional and wavelet coherence, J. Neurosci. Methods 197(1) (2011) 165–170. Medline, Web of Science, Google Scholar
8. H. Adeli, S. Ghosh-Dastidar and N. Dadmehr , A spatio-temporal wavelet-chaos methodology for EEG-based diagnosis of Alzheimer’s disease, Neurosci. Lett. 444(2) (2008) 190–194. Medline, Web of Science, Google Scholar
9. B. Magnin, L. Mesrob, S. Kinkingne’ hun and M. Pe’ le ‘grini-Issac , Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI, Neuroradiology 51(2) (2009) 73–83. Medline, Web of Science, Google Scholar
10. T. Hirschauer, H. Adeli and T. Buford , Computer-Aided diagnosis of parkinson’s disease using an enhanced probabilistic neural network, J. Med. Syst. 39(11) (2015) 179. Medline, Web of Science, Google Scholar
11. M. Ahmadlou and H. Adeli , Enhanced probabilistic neural network with local decision circles: A robust classifier, Integr. Comput.-Aided Eng. 17(3) (2010) 197. Web of Science, Google Scholar
12. P. Sharma, Y. U. Khan, O. Farooq, M. Tripathi and H. Adeli , A wavelet-statistical features approach for non-convulsive seizure detection, Clin. EEG Neurosci. 45(4) (2014) 274–284. Medline, Web of Science, Google Scholar
13. C. Davatzikos, Y. Fan, X. Wu and D. Shen , Detection of prodromal Alzheimer’s disease via pattern classification of magnetic resonance imaging, Neurobiol. Aging. 29(4) (2008) 514–523. Medline, Web of Science, Google Scholar
14. W. R. Brain, D. Northfield and M. Wilkinson , The Neurological manifestations of cervical spondylosis, Brain 75(2) (1952) 187–225. Medline, Web of Science, Google Scholar
15. M. Grana, M. Termenon, A. Savio and A. Gonzalez-Pinto , Computer aided diagnosis system for alzheimer disease using brain diffusion tensor imaging features selected by Pearson’s correlation, Neurosci. Lett. 502(3) (2011) 225–229. Medline, Web of Science, Google Scholar
16. K. Herholz, E. Salmon, D. Perani, J. C. Baron et al., Discrimination between Alzheimer dementia and controls by automated analysis of multicenter FDG PET, Neuroimage 17 (1) (2002) 302–316. Medline, Web of Science, Google Scholar
17. Y. Zhang, W. Zhou and S. Yuan , Multifractal Analysis and Relevance Vector Machine-based Automatic Seizure Detection in Intracranial, Int. J. Neural. Syst. 25(6) (2015) 1550020. Link, Web of Science, Google Scholar
18. V. Jumutc, P. Zayakin and A. Borisov , Ranking-based kernels in applied biomedical diagnostics using a support vector machine, Int. J. Neural. Syst. 21(6) (2011) 459–473. Link, Web of Science, Google Scholar
19. P. Piaggi, D. Menicucci, C. Gentili, G. Handjaras, A. Gemignani and A. Landi , Singular spectrum analysis and adaptive filtering enhance the functional connectivity analysis of resting state fMRI data, Int. J. Neural. Syst. 24(3) (2014) 1450010. Link, Web of Science, Google Scholar
20. S. Ferdowsi, S. Sanei and V. Abolghasemi , A predictive modeling approach to analyze data in EEG-fMRI experiments, Int. J. Neural. Syst. 25(1) (2015) 1440008. Link, Web of Science, Google Scholar
21. M. Thurnher and M. Law , Diffusion-weighted imaging, diffusion-tensor imaging, and fiber tractography of the spinal cord, Magn. Reson. Imag. C. 17(2) (2009) 225–244. Medline, Web of Science, Google Scholar
22. A. Demir, M. Ries, C. T. Moonen and J. M. Vital , Diffusion-weighted MR imaging with apparent diffusion coefficient and apparent diffusion tensor maps in cervical spondylotic myelopathy, Radiology 229(1) (2003) 37–43. Medline, Web of Science, Google Scholar
23. J. L. Cui, C. Y. Wen, Y. Hu, T. H. Li and K. Luk , Entropy-based analysis for diffusion anisotropy mapping of healthy and myelopathic spinal cord, Neuroimage 54(3) (2011) 2125–2131. Medline, Web of Science, Google Scholar
24. D. Facon, A. Ozanne, P. Fillard and J. F. Lepeintre , MR diffusion tensor imaging and fiber tracking in spinal cord compression, Am. J. Neuroradiol. 26(6) (2005) 1587–1594. Medline, Web of Science, Google Scholar
25. T. Uda, T. Takami, N. Tsuyuguchi and S. Sakamoto , Assessment of cervical spondylotic myelopathy using diffusion tensor magnetic resonance imaging parameter at 3.0 tesla, Spine 38(5) (2013) 407–414. Medline, Web of Science, Google Scholar
26. S. Q. Wang, X. Li, J. L. Cui and H. X. Li et al., Prediction of Myelopathic level in the cervical spinal cord using DTI, J. Magn. Reson. Imag. 41(6) (2015) 1682–1688. Medline, Web of Science, Google Scholar
27. F. C. Garcia, M. Garcia-Torres, B. Melian and J. A. Moreno-Perez , Solving feature subset selection problem by a parallel scatter search, EJOR 169(2) (2006) 477–489. Web of Science, Google Scholar
28. P. Hagmann, L. Jonasson, P. Maeder and J. P. Thiran , Understanding diffusion MR imaging techniques: From scalar diffusion-weighted imaging to diffusion tensor imaging and beyond, Radiographics 26(1) (2006) 205–223. Web of Science, Google Scholar
29. D. Schwartz, J. Duda, J. S. Shumsky, E. T. Cooper et al., Spinal cord diffusion tensor imaging and fibber tracking can identify white matter tract disruption and glial scar orientation following lateral funiculotomy, J. Neurotrauma 22(12) (2005) 1388–1398. Medline, Web of Science, Google Scholar
30. B. M. Ellingson, S. N. Kurpad and B. D. Schmit , Functional correlates of diffusion tensor imaging in spinal cord injury, Biomed. Sci. Instrum. 44 (2008) 28–33. Medline, Google Scholar
31. K. Yonenobu, K. Abumi, K. Nagata and E. Taketomi , Interobserver and intraobserver reliability of the japanese orthopaedic association scoring system for evaluation of cervical compression myelopathy, Spine 26(17) (2001) 1890–1894. Medline, Web of Science, Google Scholar
32. T. C. Chuang, T. Y. Huang, F. H. Lin and F. N. Wang , PROPELLER-EPI with parallel imaging using a circularly symmetric phased-array RF coil at 3.0 T: Application to high-resolution diffusion tensor imaging, Magn. Reson. Med. 56(6) (2006) 1352–1358. Medline, Web of Science, Google Scholar
33. P. Morgan, R. Bowtell, D. McIntyre and B. Worthington , Correction of spatial distortion in EPI due to inhomogeneous static magnetic fields using the reversed gradient method, J. Magn. Reson. Imag. 19(4) (2004) 499–507. Medline, Web of Science, Google Scholar
34. J. Soares, P. Marques, V. Alves and N. Sousa , A hitchhiker’s guide to diffusion tensor imaging, Front. Neurosci. 7 (2013) 31. Medline, Web of Science, Google Scholar
35. C. F. Westin, S. E. Maier, H. Mamata and A. Nabavi , Processing and visualization of diffusion tensor MRI, Med. Image Anal. 6(2) (2002) 93–108. Medline, Web of Science, Google Scholar
36. C. Cortes and V. Vapnik , Support-vector networks, Mach Learn. 20(3) (1995) 273–297. Web of Science, Google Scholar
37. E. Castillo, D. Peteiro-Barral, B. G. Berdiñas and O. Fontenla-Romero , Distributed one-class support vector machine, Int. J. Neural. Syst. 25(7) (2015) 1550029. Link, Web of Science, Google Scholar
38. I. Kotsia, W. Guo and I. Patras , Higher rank support tensor machines for visual recognition, Pattern Recogn. 45(12) (2012) 4192–4203. Web of Science, Google Scholar
39. D. J. Hand and K. Yu , Idiot’s Bayes — not so stupid after all, Int. Stat. Rev. 69(3) (2001) 385–399. Web of Science, Google Scholar
40. G. Holmes, A. Donkin and I. H. Witten , Weka: A machine learning workbench, in Proc. 2nd ANZIIS (Brisbane, Australia, 1994), pp. 357–361. Google Scholar
41. M. Robnik-Sikonja and I. Kononenko , Theoretical and Empirical Analysis of ReliefF and RReliefF, Mach Learn. 53(suppl_1) (2003) 23–69. Web of Science, Google Scholar
42. Z. Zhao and H. Liu , Spectral feature selection for supervised and unsupervised learning, in Proc. 24th Int. Conf. Mach Learn (Corvalis, Oregon, 2007), pp. 1151–1157. Google Scholar
43. M. Stone , Asymptotics for and against cross-validation, Biometrika 64(1) (1977) 29–35. Web of Science, Google Scholar
44. J. L. Cui, C. Y. Wen, Y. Hu, K. C. Mark and K. D. Luk , Orientation entropy analysis of diffusion tensor in healthy and myelopathic spinal cord, Neuroimage 258 (2011) 1028–1033. Web of Science, Google Scholar
45. A. Vedantam, M. B. Jirjis, B. D. Schmit, M. C. Wang et al., Diffusion tensor imaging of the spinal cord: Insights from animal and human studies, Neurosurgery 74(1) (2014) 1–8. Medline, Web of Science, Google Scholar
46. C. Wen, J. Cui, H. Liu, K. Mak et al., Is Diffusion Anisotropy a biomarker for disease severity and surgical prognosis of cervical Spondylotic Myelopathy, Radiology 270(1) (2013) 197–204. Medline, Web of Science, Google Scholar