Magnetic resonance imaging pattern learning in temporal lobe epilepsy: Classification and prognostics

Annals of Neurology - Tập 77 Số 3 - Trang 436-446 - 2015
Boris C. Bernhardt1, Seok‐Jun Hong1, Andrea Bernasconi1
1Neuroimaging of Epilepsy Laboratory, Montreal Neurological Institute and Hospital, McGill University, Montreal, Quebec, Canada.

Tóm tắt

ObjectiveIn temporal lobe epilepsy (TLE), although hippocampal atrophy lateralizes the focus, the value of magnetic resonance imaging (MRI) to predict postsurgical outcome is rather modest. Prediction solely based on the hippocampus may be hampered by widespread mesiotemporal structural damage shown by advanced imaging. Increasingly complex and high‐dimensional representation of MRI metrics motivates a shift to machine learning to establish objective, data‐driven criteria for pathogenic processes and prognosis.MethodsWe applied clustering to 114 consecutive unilateral TLE patients using 1.5T MRI profiles derived from surface morphology of hippocampus, amygdala, and entorhinal cortex. To evaluate the diagnostic validity of the classification, we assessed its yield to predict outcome in 79 surgically treated patients. Reproducibility of outcome prediction was assessed in an independent cohort of 27 patients evaluated on 3.0T MRI.ResultsFour similarly sized classes partitioned our cohort; in all, alterations spanned over the 3 mesiotemporal structures. Compared to 46 controls, TLE‐I showed marked bilateral atrophy; in TLE‐II atrophy was ipsilateral; TLE‐III showed mild bilateral atrophy; whereas TLE‐IV showed hypertrophy. Classes differed with regard to histopathology and freedom from seizures. Classwise surface‐based classifiers accurately predicted outcome in 92 ± 1% of patients, outperforming conventional volumetry. Predictors of relapse were distributed bilaterally across structures. Prediction accuracy was similarly high in the independent cohort (96%), supporting generalizability.InterpretationWe provide a novel description of individual variability across the TLE spectrum. Class membership was associated with distinct patterns of damage and outcome predictors that did not spatially overlap, emphasizing the ability of machine learning to disentangle the differential contribution of morphology to patient phenotypes, ultimately refining the prognosis of epilepsy surgery. Ann Neurol 2015;77:436–446

Từ khóa


Tài liệu tham khảo

10.1093/brain/awg034

10.1002/ana.410340607

Kim H, 2008, Surface‐based vector analysis using heat equation interpolation: a new approach to quantify local hippocampal volume changes, Med Image Comput Comput Assist Interv, 11, 1008

10.1093/brain/awh197

10.1111/epi.12220

10.1212/01.wnl.0000436069.20513.92

10.1038/nrneurol.2012.181

10.3171/2008.6.JNS17613

10.3171/jns.2006.104.4.513

10.1136/jnnp.73.5.486

10.1016/S0140-6736(11)60890-8

10.1002/ana.410400314

Engel J, 1993, Surgical treatment of the epilepsies, 609

Meencke HJ, 1991, Epilepsy surgery, 705

10.1097/00004728-199403000-00005

10.1109/42.668698

10.1212/WNL.42.9.1743

10.1212/WNL.52.9.1870

Styner M, 2006, Statistical shape analysis of brain structures using SPHARM‐PDM, 10.54294/owxzil

10.1016/j.neuroimage.2013.08.067

10.1212/01.wnl.0000436069.20513.92

Kim H, 2008, Surface‐based vector analysis using heat equation interpolation: a new approach to quantify local hippocampal volume changes, Med Image Comput Comput Assist Interv, 11, 1008

10.1093/brain/awh197

Duvernoy HM, 2005, The human hippocampus functional anatomy, vascularization and serial sections with MRI. Berlin, 10.1007/b138576

10.1007/s00429-005-0025-5

10.1002/cne.903550203

Duda RO, 2001, Pattern classification

10.1007/3-540-45372-5_26

10.1016/S1053-8119(09)70882-1

10.1016/j.neuroimage.2010.06.032

10.1002/(SICI)1097-0193(1999)8:2/3<98::AID-HBM5>3.0.CO;2-F

10.1016/j.media.2012.04.008

10.1111/j.1528-1167.2011.03155.x

10.1016/j.ijmedinf.2006.11.006

10.1371/journal.pone.0033096

10.1016/j.neuroimage.2005.07.052

10.1016/j.neuroimage.2011.07.068

10.1016/j.neuroimage.2013.01.014

10.1002/cne.902640306

10.1111/j.1528-1167.2005.43804.x

10.1016/j.neuroimage.2008.04.261

10.1097/00019052-200404000-00013

10.1002/ana.410300107

10.1016/j.tins.2009.08.002

10.1002/glia.20394

10.1002/glia.20380

10.1111/j.1528-1167.2007.01277.x

10.1093/brain/awh449

Thông tin
Thông tin xuất bản

Annals of Neurology

Tập 77 Số 3

436-446

Thông tin tác giả