|
|
Machine learning for detecting mesial temporal lobe epilepsy by structural and functional neuroimaging |
Baiwan Zhou1, Dongmei An2, Fenglai Xiao2,3, Running Niu1, Wenbin Li1, Wei Li2, Xin Tong2, Graham J Kemp4, Dong Zhou2(), Qiyong Gong1,5, Du Lei1,6,7() |
1. Huaxi MR Research Center (HMRRC), Department of Radiology, West China Hospital of Sichuan University, Chengdu 610041, China 2. Department of Neurology, West China Hospital of Sichuan University, Chengdu 610041, China 3. Department of Clinical and Experimental Epilepsy, Institute of Neurology, University College London, London WC1E 6BT, UK 4. Institute of Ageing and Chronic Disease, Faculty of Health and Life Sciences, University of Liverpool, Liverpool L9 7AL, UK 5. Department of Psychology, School of Public Administration, Sichuan University, Chengdu 610041, China 6. Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, London SE5 8AF, UK 7. Department of Psychiatry and Behavioral Neuroscience, University of Cincinnati, Cincinnati, OH 45219, USA |
|
|
Abstract Mesial temporal lobe epilepsy (mTLE), the most common type of focal epilepsy, is associated with functional and structural brain alterations. Machine learning (ML) techniques have been successfully used in discriminating mTLE from healthy controls. However, either functional or structural neuroimaging data are mostly used separately as input, and the opportunity to combine both has not been exploited yet. We conducted a multimodal ML study based on functional and structural neuroimaging measures. We enrolled 37 patients with left mTLE, 37 patients with right mTLE, and 74 healthy controls and trained a support vector ML model to distinguish them by using each measure and the combinations of the measures. For each single measure, we obtained a mean accuracy of 74% and 69% for discriminating left mTLE and right mTLE from controls, respectively, and 64% when all patients were combined. We achieved an accuracy of 78% by integrating functional data and 79% by integrating structural data for left mTLE, and the highest accuracy of 84% was obtained when all functional and structural measures were combined. These findings suggest that combining multimodal measures within a single model is a promising direction for improving the classification of individual patients with mTLE.
|
Keywords
mesial temporal lobe epilepsy
functional magnetic resonance imaging
structural magnetic resonance imaging
machine learning
support vector machine
|
Corresponding Author(s):
Dong Zhou,Du Lei
|
Just Accepted Date: 07 November 2019
Online First Date: 07 January 2020
Issue Date: 12 October 2020
|
|
1 |
J Engel Jr. Mesial temporal lobe epilepsy: what have we learned? Neuroscientist 2001; 7(4): 340–352
https://doi.org/10.1177/107385840100700410
pmid: 11488399
|
2 |
H Burianová, NL Faizo, M Gray, J Hocking, G Galloway, D Reutens. Altered functional connectivity in mesial temporal lobe epilepsy. Epilepsy Res 2017; 137: 45–52
https://doi.org/10.1016/j.eplepsyres.2017.09.001
pmid: 28923408
|
3 |
S Chen, L Chen, H Huang, W Lin. Relationship between resting state functional magnetic resonance imaging and memory function in mesial temporal lobe epilepsy. J Neurol Sci 2017; 372: 117–125
https://doi.org/10.1016/j.jns.2016.10.048
pmid: 28017196
|
4 |
N Memarian, PM Thompson, J Engel Jr, RJ Staba. Quantitative analysis of structural neuroimaging of mesial temporal lobe epilepsy. Imaging Med 2013; 5(3): 10–14
https://doi.org/10.2217/iim.13.28
pmid: 24319498
|
5 |
M Liu, Z Chen, C Beaulieu, DW Gross. Disrupted anatomic white matter network in left mesial temporal lobe epilepsy. Epilepsia 2014; 55(5): 674–682
https://doi.org/10.1111/epi.12581
pmid: 24650167
|
6 |
Y Kassahun, R Perrone, E De Momi, E Berghöfer, L Tassi, MP Canevini, R Spreafico, G Ferrigno, F Kirchner. Automatic classification of epilepsy types using ontology-based and genetics-based machine learning. Artif Intell Med 2014; 61(2): 79–88
https://doi.org/10.1016/j.artmed.2014.03.001
pmid: 24743020
|
7 |
UR Acharya, R Yanti, JW Zheng, MMR Krishnan, JH Tan, RJ Martis, CM Lim. Automated diagnosis of epilepsy using CWT, HOS and texture parameters. Int J Neural Syst 2013; 23(3): 1350009
https://doi.org/10.1142/S0129065713500093
pmid: 23627656
|
8 |
WT Kerr, AY Cho, A Anderson, PK Douglas, EP Lau, ES Hwang, KR Raman, A Trefler, MS Cohen, ST Nguyen, NM Reddy, DH Silverman. Balancing clinical and pathologic relevence in the machine learning diagnosis of epilepsy. Int Workshop Pattern Recognit Neuroimaging 2013; 2013: 86–89
https://doi.org/10.1109/PRNI.2013.31
pmid: 25302313
|
9 |
NK Focke, M Yogarajah, MR Symms, O Gruber, W Paulus, JS Duncan. Automated MR image classification in temporal lobe epilepsy. Neuroimage 2012; 59(1): 356–362
https://doi.org/10.1016/j.neuroimage.2011.07.068
pmid: 21835245
|
10 |
N Memarian, S Kim, S Dewar, J Engel Jr, RJ Staba. Multimodal data and machine learning for surgery outcome prediction in complicated cases of mesial temporal lobe epilepsy. Comput Biol Med 2015; 64: 67–78
https://doi.org/10.1016/j.compbiomed.2015.06.008
pmid: 26149291
|
11 |
JD Rudie, JB Colby, N Salamon. Machine learning classification of mesial temporal sclerosis in epilepsy patients. Epilepsy Res 2015; 117: 63–69
https://doi.org/10.1016/j.eplepsyres.2015.09.005
pmid: 26421492
|
12 |
Z Yang, J Choupan, D Reutens, J Hocking. Lateralization of temporal lobe epilepsy based on resting-state functional magnetic resonance imaging and machine learning. Front Neurol 2015; 6: 184
https://doi.org/10.3389/fneur.2015.00184
pmid: 26379618
|
13 |
J Del Gaizo, N Mofrad, JH Jensen, D Clark, R Glenn, J Helpern, L Bonilha. Using machine learning to classify temporal lobe epilepsy based on diffusion MRI. Brain Behav 2017; 7(10): e00801
https://doi.org/10.1002/brb3.801
pmid: 29075561
|
14 |
J An, P Fang, W Wang, Z Liu, D Hu, S Qiu. Decreased white matter integrity in mesial temporal lobe epilepsy: a machine learning approach. Neuroreport 2014; 25(10): 788–794
https://doi.org/10.1097/WNR.0000000000000178
pmid: 24918460
|
15 |
FR Pereira, A Alessio, MS Sercheli, T Pedro, E Bilevicius, JM Rondina, HF Ozelo, G Castellano, RJ Covolan, BP Damasceno, F Cendes. Asymmetrical hippocampal connectivity in mesial temporal lobe epilepsy: evidence from resting state fMRI. BMC Neurosci 2010; 11(1): 66
https://doi.org/10.1186/1471-2202-11-66
pmid: 20525202
|
16 |
N Kemmotsu, HM Girard, BC Bernhardt, L Bonilha, JJ Lin, ES Tecoma, VJ Iragui, DJ Hagler Jr, E Halgren, CR McDonald. 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
https://doi.org/10.1111/j.1528-1167.2011.03278.x
pmid: 21972957
|
17 |
NE Kucukboyaci, HM Girard, DJ Hagler Jr, J Kuperman, ES Tecoma, VJ Iragui, E Halgren, CR McDonald. Role of frontotemporal fiber tract integrity in task-switching performance of healthy controls and patients with temporal lobe epilepsy. J Int Neuropsychol Soc 2012; 18(1): 57–67
https://doi.org/10.1017/S1355617711001391
pmid: 22014246
|
18 |
AC Coan, BM Campos, GC Beltramini, CL Yasuda, RJ Covolan, F Cendes. Distinct functional and structural MRI abnormalities in mesial temporal lobe epilepsy with and without hippocampal sclerosis. Epilepsia 2014; 55(8): 1187–1196
https://doi.org/10.1111/epi.12670
pmid: 24903633
|
19 |
W Liao, Z Zhang, Z Pan, D Mantini, J Ding, X Duan, C Luo, Z Wang, Q Tan, G Lu, H Chen. Default mode network abnormalities in mesial temporal lobe epilepsy: a study combining fMRI and DTI. Hum Brain Mapp 2011; 32(6): 883–895
https://doi.org/10.1002/hbm.21076
pmid: 20533558
|
20 |
CY Wee, PT Yap, D Zhang, K Denny, JN Browndyke, GG Potter, KA Welsh-Bohmer, L Wang, D Shen. Identification of MCI individuals using structural and functional connectivity networks. Neuroimage 2012; 59(3): 2045–2056
https://doi.org/10.1016/j.neuroimage.2011.10.015
pmid: 22019883
|
21 |
C Scanlon, SG Mueller, I Cheong, M Hartig, MW Weiner, KD Laxer. Grey and white matter abnormalities in temporal lobe epilepsy with and without mesial temporal sclerosis. J Neurol 2013; 260(9): 2320–2329
https://doi.org/10.1007/s00415-013-6974-3
pmid: 23754695
|
22 |
B Braga, CL Yasuda, F Cendes. White matter atrophy in patients with mesial temporal lobe epilepsy: voxel-based morphometry analysis of T1- and T2-Weighted MR Images. Radiol Res Pract 2012; 2012: 481378
https://doi.org/10.1155/2012/481378
pmid: 23150823
|
23 |
A Labate, A Cerasa, U Aguglia, L Mumoli, A Quattrone, A Gambardella. Neocortical thinning in “benign” mesial temporal lobe epilepsy. Epilepsia 2011; 52(4): 712–717
https://doi.org/10.1111/j.1528-1167.2011.03038.x
pmid: 21453353
|
24 |
Z Zhang, G Lu, Y Zhong, Q Tan, H Chen, W Liao, L Tian, Z Li, J Shi, Y Liu. fMRI study of mesial temporal lobe epilepsy using amplitude of low-frequency fluctuation analysis. Hum Brain Mapp 2010; 31(12): 1851–1861
https://doi.org/10.1002/hbm.20982
pmid: 20225278
|
25 |
J Zhong, S Chen, Q Ouyang, D An, S Lu. Study on the ReHo in treatment-naïve of temporal lobe epilepsy patients with depressive symptoms using resting functional-MRI (fMRI). J Biomedical Eng (Sheng Wu Yi Xue Gong Cheng Xue Za Zhi) 2012; 29(2): 229–232 (in Chinese)
pmid: 22616163
|
26 |
H Zeng, R Pizarro, VA Nair, C La, V Prabhakaran. Alterations in regional homogeneity of resting-state brain activity in mesial temporal lobe epilepsy. Epilepsia 2013; 54(4): 658–666
https://doi.org/10.1111/epi.12066
pmid: 23294137
|
27 |
Commission on Classification and Terminology of the International League Against Epilepsy. Proposal for revised classification of epilepsies and epileptic syndromes. Epilepsia 1989; 30(4): 389–399
https://doi.org/10.1111/j.1528-1157.1989.tb05316.x
pmid: 2502382
|
28 |
SD Shorvon. The etiologic classification of epilepsy. Epilepsia 2011; 52(6): 1052–1057
https://doi.org/10.1111/j.1528-1167.2011.03041.x
pmid: 21449936
|
29 |
B Fischl, A van der Kouwe, C Destrieux, E Halgren, F Ségonne, DH Salat, E Busa, LJ Seidman, J Goldstein, D Kennedy, V Caviness, N Makris, B Rosen, AM Dale. Automatically parcellating the human cerebral cortex. Cereb Cortex 2004; 14(1): 11–22
https://doi.org/10.1093/cercor/bhg087
pmid: 14654453
|
30 |
RS Desikan, F Ségonne, B Fischl, BT Quinn, BC Dickerson, D Blacker, RL Buckner, AM Dale, RP Maguire, BT Hyman, MS Albert, RJ Killiany. An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interest. Neuroimage 2006; 31(3): 968–980
https://doi.org/10.1016/j.neuroimage.2006.01.021
pmid: 16530430
|
31 |
C Cortes, V Vapnik. Support-vector networks. Mach Learn 1995; 20(3): 273–297
https://doi.org/10.1007/BF00994018
|
32 |
CC Chang, CJ Lin. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2011; 2(3): 115–121
https://doi.org/10.1145/1961189.1961199
|
33 |
F Pedregosa, G Varoquaux, A Gramfort, V Michel, B Thirion, O Grisel, M Blondel, P Prettenhofer, R Weiss, V Dubourg, J Vanderplas, A Passos, D Cournapeau, M Brucher, M Perrot, E Duchesnay. Scikit-learn: machine learning in Python. J Mach Learn Res 2011; 12: 2825–2830
|
34 |
W Pettersson-Yeo, S Benetti, AF Marquand, R Joules, M Catani, SCR Williams, P Allen, P McGuire, A Mechelli. An empirical comparison of different approaches for combining multimodal neuroimaging data with support vector machine. Front Neurosci 2014; 8: 189
https://doi.org/10.3389/fnins.2014.00189
pmid: 25076868
|
35 |
N Tzourio-Mazoyer, B Landeau, D Papathanassiou, F Crivello, O Etard, N Delcroix, B Mazoyer, M Joliot. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 2002; 15(1): 273–289
https://doi.org/10.1006/nimg.2001.0978
pmid: 11771995
|
36 |
JS Damoiseaux, SA Rombouts, F Barkhof, P Scheltens, CJ Stam, SM Smith, CF Beckmann. Consistent resting-state networks across healthy subjects. Proc Natl Acad Sci USA 2006; 103(37): 13848–13853
https://doi.org/10.1073/pnas.0601417103
pmid: 16945915
|
37 |
RL Buckner, JR Andrews-Hanna, DL Schacter. The brain’s default network: anatomy, function, and relevance to disease. Ann N Y Acad Sci 2008; 1124(1): 1–38
https://doi.org/10.1196/annals.1440.011
pmid: 18400922
|
38 |
D Cantor-Rivera, AR Khan, M Goubran, SM Mirsattari, TM Peters. Detection of temporal lobe epilepsy using support vector machines in multi-parametric quantitative MR imaging. Comput Med Imaging Graph 2015; 41: 14–28
https://doi.org/10.1016/j.compmedimag.2014.07.002
pmid: 25103878
|
39 |
N Kemmotsu, NE Kucukboyaci, CE Cheng, HM Girard, ES Tecoma, VJ Iragui, CR McDonald. Alterations in functional connectivity between the hippocampus and prefrontal cortex as a correlate of depressive symptoms in temporal lobe epilepsy. Epilepsy Behav 2013; 29(3): 552–559
https://doi.org/10.1016/j.yebeh.2013.09.039
pmid: 24176688
|
40 |
CR McDonald, DJ Hagler Jr, ME Ahmadi, E Tecoma, V Iragui, L Gharapetian, AM Dale, E Halgren. Regional neocortical thinning in mesial temporal lobe epilepsy. Epilepsia 2008; 49(5): 794–803
https://doi.org/10.1111/j.1528-1167.2008.01539.x
pmid: 18266751
|
41 |
NE Kucukboyaci, N Kemmotsu, CE Cheng, HM Girard, ES Tecoma, VJ Iragui, CR McDonald. Functional connectivity of the hippocampus in temporal lobe epilepsy: feasibility of a task-regressed seed-based approach. Brain Connect 2013; 3(5): 464–474
https://doi.org/10.1089/brain.2013.0150
pmid: 23869604
|
42 |
GJ Ji, Z Zhang, H Zhang, J Wang, DQ Liu, YF Zang, W Liao, G Lu. Disrupted causal connectivity in mesial temporal lobe epilepsy. PLoS One 2013; 8(5): e63183
https://doi.org/10.1371/journal.pone.0063183
pmid: 23696798
|
43 |
D Pustina, G Doucet, M Sperling, A Sharan, J Tracy. Increased microstructural white matter correlations in left, but not right, temporal lobe epilepsy. Hum Brain Mapp 2015; 36(1): 85–98
https://doi.org/10.1002/hbm.22614
pmid: 25137314
|
44 |
J Lu, W Li, H He, F Feng, Z Jin, L Wu. Altered hemispheric symmetry found in left-sided mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE/HS) but not found in right-sided MTLE/HS. Magn Reson Imaging 2013; 31(1): 53–59
https://doi.org/10.1016/j.mri.2012.06.030
pmid: 22925605
|
45 |
WA Lishman, ER McMeekan. Handedness in relation to direction and degree of cerebral dominance for language. Cortex 1977; 13(1): 30–43
https://doi.org/10.1016/S0010-9452(77)80051-8
pmid: 844306
|
46 |
Q Zhang, Q Wu, H Zhu, L He, H Huang, J Zhang, W Zhang. Multimodal MRI-based classification of trauma survivors with and without post-traumatic stress disorder. Front Neurosci 2016; 10: 292
https://doi.org/10.3389/fnins.2016.00292
pmid: 27445664
|
47 |
C Hinrichs, V Singh, G Xu, SC; Alzheimers Disease Neuroimaging Initiative. JohnsonPredictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population. Neuroimage 2011; 55(2): 574–589
https://doi.org/10.1016/j.neuroimage.2010.10.081
pmid: 21146621
|
48 |
DS Barron, N Tandon, JL Lancaster, PT Fox. Thalamic structural connectivity in medial temporal lobe epilepsy. Epilepsia 2014; 55(6): e50–e55
https://doi.org/10.1111/epi.12637
pmid: 24802969
|
49 |
B Peng, L Wu, L Zhang, Y Chen. The relationship between hippocampal volumes and nonverbal memory in patients with medial temporal lobe epilepsy. Epilepsy Res 2014; 108(10): 1839–1844
https://doi.org/10.1016/j.eplepsyres.2014.09.007
pmid: 25443451
|
50 |
KM Sequeira, A Tabesh, RK Sainju, SM DeSantis, T Naselaris, JE Joseph, MA Ahlman, KM Spicer, SS Glazier, JC Edwards, L Bonilha. Perfusion network shift during seizures in medial temporal lobe epilepsy. PLoS One 2013; 8(1): e53204
https://doi.org/10.1371/journal.pone.0053204
pmid: 23341932
|
51 |
EH Bertram. Extratemporal lobe circuits in temporal lobe epilepsy. Epilepsy Behav 2014; 38: 13–18
https://doi.org/10.1016/j.yebeh.2014.07.012
pmid: 25238899
|
52 |
T Sankar, N Bernasconi, H Kim, A Bernasconi. Temporal lobe epilepsy: differential pattern of damage in temporopolar cortex and white matter. Hum Brain Mapp 2008; 29(8): 931–944
https://doi.org/10.1002/hbm.20437
pmid: 17636561
|
53 |
G Curia, C Lucchi, J Vinet, F Gualtieri, C Marinelli, A Torsello, L Costantino, G Biagini. Pathophysiogenesis of mesial temporal lobe epilepsy: is prevention of damage antiepileptogenic? Curr Med Chem 2014; 21(6): 663–688
https://doi.org/10.2174/0929867320666131119152201
pmid: 24251566
|
54 |
W Liao, Z Zhang, Z Pan, D Mantini, J Ding, X Duan, C Luo, G Lu, H Chen. Altered functional connectivity and small-world in mesial temporal lobe epilepsy. PLoS One 2010; 5(1): e8525
https://doi.org/10.1371/journal.pone.0008525
pmid: 20072616
|
55 |
F Pittau, C Grova, F Moeller, F Dubeau, J Gotman. Patterns of altered functional connectivity in mesial temporal lobe epilepsy. Epilepsia 2012; 53(6): 1013–1023
https://doi.org/10.1111/j.1528-1167.2012.03464.x
pmid: 22578020
|
56 |
V Menon. Large-scale brain networks and psychopathology: a unifying triple network model. Trends Cogn Sci 2011; 15(10): 483–506
https://doi.org/10.1016/j.tics.2011.08.003
pmid: 21908230
|
57 |
Z Zhang, G Lu, Y Zhong, Q Tan, W Liao, Z Wang, Z Wang, K Li, H Chen, Y Liu. Altered spontaneous neuronal activity of the default-mode network in mesial temporal lobe epilepsy. Brain Res 2010; 1323: 152–160
https://doi.org/10.1016/j.brainres.2010.01.042
pmid: 20132802
|
58 |
M Cataldi, M Avoli, E de Villers-Sidani. Resting state networks in temporal lobe epilepsy. Epilepsia 2013; 54(12): 2048–2059
https://doi.org/10.1111/epi.12400
pmid: 24117098
|
59 |
V Bouilleret, F Semah, F Chassoux, M Mantzaridez, A Biraben, R Trebossen, MJ Ribeiro. Basal ganglia involvement in temporal lobe epilepsy: a functional and morphologic study. Neurology 2008; 70(3): 177–184
https://doi.org/10.1212/01.wnl.0000297514.47695.48
pmid: 18195263
|
60 |
S Vieira, WHL Pinaya, A Mechelli. Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications. Neurosci Biobehav Rev 2017; 74(Pt A): 58–75
https://doi.org/10.1016/j.neubiorev.2017.01.002
pmid: 28087243
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|