为了定位颞叶癫痫（TLE）患者脑白质微结构发生异常的重要脑区，本文设立了正常对照组（NC）与 TLE 组两组人群，采集了 50 位受试者（其中 NC 组 28 人，TLE 组 22 人）的脑部弥散张量成像（DTI）影像，分别计算其部分各向异性（FA）、平均扩散率（MD）、扩散系数（AD）、径向扩散系数（RD）等参数，并采用纤维束追踪空间统计方法（TBSS），获取组间差异的脑区，然后利用支持向量机（SVM），对 NC 组与 TLE 组进行分类，并与支持向量机-递归特征消除法（SVM-RFE）进行比较，最后对重要脑区及其分布进行分析与讨论。实验结果表明，TLE 患者的 FA 值存在明显降低的脑区主要有胼胝体、上纵束、放射冠、外囊、内囊、下额枕束、钩束、矢状层等，基本呈双侧分布，其中大部分脑区的 MD、RD 值明显增高，AD 值虽有增高，但差异无统计学意义。支持向量机-纤维束追踪空间统计法（SVM-TBSS）利用 FA、MD、RD 进行分类的准确率分别为 82%、76%、76%，特征融合后分类准确率为 80%；SVM-RFE 利用 FA、MD、RD 进行分类准确率分别为 90%、90% 和 92%，特征融合后分类准确率达到 100%，SVM-RFE 分类性能明显优于 SVM-TBSS，对分类有重要影响的特征主要分布于联络纤维和连合纤维脑区。研究结果表明，DTI 参数能有效地反映 TLE 患者的脑白质纤维异常改变，可用于阐明其病理机制、定位病灶及实现自动诊断
References
[1]
1. Ngugi A K, Bottomley C, Kleinschmidt I, et al. Estimation of the burden of active and life-time epilepsy: a meta-analytic approach. Epilepsia, 2010, 51(5): 883-890.
[2]
2. Kwan P, Brodie M J. Drug treatment of epilepsy: when does it fail and how to optimize its use? CNS Spectr, 2004, 9(2): 110-119.
[3]
4. Kemmotsu N, Girard H M, Bernhardt B C, et al. MRI analysis in temporal lobe epilepsy: cortical thinning and white matter disruptions are related to side of seizure onset. Epilepsia, 2011, 52(12): 2257-2266.
[4]
5. Mueller S G, Laxer K D, Cashdollar N, et al. Identification of abnormal neuronal metabolism outside the seizure focus in temporal lobe epilepsy. Epilepsia, 2004, 45(4): 355-366.
[5]
8. Song S K, Sun Shuwei, Ramsbottom M J, et al. Dysmyelination revealed through MRI as increased radial (but unchanged axial) diffusion of water. Neuroimage, 2002, 17(3): 1429-1436.
[6]
27. Arbabshirani M R, Plis S, Sui Jing, et al. Single subject prediction of brain disorders in neuroimaging: Promises and pitfalls. Neuroimage, 2017, 145(Pt B): 137-165.
[7]
3. Duncan J. The current status of neuroimaging for epilepsy. Curr Opin Neurol, 2009, 22(2): 179-184.
[8]
12. Mcmillan A B, Hermann B P, Johnson S C, et al. Voxel-based morphometry of unilateral temporal lobe epilepsy reveals abnormalities in cerebral white matter. Neuroimage, 2004, 23(1): 167-174.
[9]
13. Smith S M, Jenkinson M, Johansen-Berg H, et al. Tract-based spatial statistics: Voxelwise analysis of multi-subject diffusion data. Neuroimage, 2006, 31(4): 1487-1505.
[10]
14. Focke N K, Yogarajah M, Bonelli S B, et al. Voxel-based diffusion tensor imaging in patients with mesial temporal lobe epilepsy and hippocampal sclerosis. Neuroimage, 2008, 40(2): 728-737.
[11]
15. I？ik H, Sezer E. Diagnosis of epilepsy from electroencephalography signals using multilayer perceptron and Elman Artificial Neural Networks and Wavelet Transform. J Med Syst, 2012, 36(1): 1-13.
[12]
16. Kerr W T, Nguyen S T, Cho A Y, et al. Computer-Aided diagnosis and localization of lateralized temporal lobe epilepsy using interictal FDG-PET. Front Neurol, 2013, 4(31): 31-44.
[13]
17. Laufs H, Daunizeau J, Carmichael D W, et al. Recent advances in recording electrophysiological data simultaneously with magnetic resonance imaging. Neuroimage, 2008, 40(2): 515-528.
[14]
18. Bernhardt B C, Hong S J, Bernasconi A, et al. Magnetic resonance imaging pattern learning in temporal lobe epilepsy: classification and prognostics. Ann Neurol, 2015, 77(3): 436-446.
[15]
19. Memarian N, Kim S, Dewar S, et al. Multimodal data and machine learning for surgery outcome prediction in complicated cases of mesial temporal lobe epilepsy. Comput Biol Med, 2015, 64(2015): 67-78.
[16]
20. Cantor-Rivera D, Khan A R, Goubran M, et al. Detection of temporal lobe epilepsy using support vector machines in multi-parametric quantitative Mr imaging. Comput Med Imaging Graph, 2015, 41(2015): 14-28.
[17]
21. Focke N K, Yogarajah M, Symms M R, et al. Automated Mr image classification in temporal lobe epilepsy. Neuroimage, 2012, 59(1): 356-362.
[18]
22. An Jie, Fang Peng, Wang Wensheng, et al. Decreased white matter integrity in mesial temporal lobe epilepsy: a machine learning approach. Neuroreport, 2014, 25(10): 788-794.
[19]
23. Cui Zaixu, Zhong Suyu, Xu Pengfei, et al. PANDA: a pipeline toolbox for analyzing brain diffusion images. Front Hum Neurosci, 2013, 7(42): 42.
[20]
24. Le Bihan D, Mangin J F, Poupon C, et al. Diffusion tensor imaging: concepts and applications. Magn Reson Imaging, 2001, 13(4): 534-546.
[21]
25. Smith S M, Jenkinson M, Woolrich M W, et al. Advances in functional and structural Mr image analysis and implementation as FSL. Neuroimage, 2004, 23(Suppl 1): S208-S219.
[22]
26. Mori Susumu, Oishi K, Jiang Hangyi, et al. Stereotaxic white matter Atlas based on diffusion tensor imaging in an ICBM template. Neuroimage, 2008, 40(2): 570-582.
[23]
6. Govindan R M, Makki M I, Sundaram S K, et al. Diffusion tensor analysis of temporal and extra-temporal lobe tracts in temporal lobe epilepsy. Epilepsy Res, 2008, 80(1): 30-41.
[24]
7. Chiang S, Levin H S, Wilde E, et al. White matter structural connectivity changes correlate with epilepsy duration in temporal lobe epilepsy. Epilepsy Res, 2016, 120(2016): 37-46.
[25]
9. Campos B M, Coan A C, Beltramini G C, et al. White matter abnormalities associate with type and localization of focal epileptogenic lesions. Epilepsia, 2015, 56(1): 125-132.
[26]
10. Meng Lu, Xiang Jing, Kotecha R, et al. White matter abnormalities in children and adolescents with temporal lobe epilepsy. Magn Reson Imaging, 2010, 28(9): 1290-1298.
[27]
11. Liu Zhenyin, Xu Yong, An Jie, et al. Altered brain white matter integrity in temporal lobe epilepsy: a TBSS study. J Neuroimaging, 2015, 25(3): 460-464.
