Predicting postoperative language outcome using presurgical fMRI, MEG, TMS, and high gamma ECoG

被引:24
作者
Babajani-Feremi, Abbas [1 ,2 ]
Holder, Christen M. [3 ]
Narayana, Shalini [1 ,2 ]
Fulton, Stephen P. [3 ]
Choudhri, Asim F. [3 ]
Boop, Frederick A. [3 ]
Wheless, James W. [3 ]
机构
[1] Univ Tennessee, Hlth Sci Ctr, Dept Pediat, Memphis, TN 38163 USA
[2] Univ Tennessee, Le Bonheur Childrens Hosp, Neurosci Inst, Dept Anat & Neurobiol, Memphis, TN 38163 USA
[3] Univ Tennessee, Hlth Sci Ctr, Le Bonheur Childrens Hosp, Neurosci Inst,Dept Pediat, 51 N Dunlap St,Suite P320, Memphis, TN 38105 USA
关键词
fMRI; MEG; TMS; High gamma electrocorticography (hgECoG); Postoperative language outcome; TRANSCRANIAL MAGNETIC STIMULATION; ANTERIOR TEMPORAL LOBECTOMY; DIRECT CORTICAL STIMULATION; SUPPORT VECTOR MACHINE; RESTING-STATE FMRI; ELECTRICAL-STIMULATION; EPILEPSY SURGERY; NAMING DECLINE; COMBINING FMRI; BRAIN;
D O I
10.1016/j.clinph.2017.12.031
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
Objective: To predict the postoperative language outcome using the support vector regression (SVR) and results of multimodal presurgical language mapping. Methods: Eleven patients with epilepsy received presurgical language mapping using functional MRI (fMRI), magnetoencephalography (MEG), transcranial magnetic stimulation (TMS), and high-gamma electrocorticography (hgECoG), as well as pre- and postoperative neuropsychological evaluation of language. We constructed 15 (2(4)-1) SVR models by considering the extent of resected language areas identified by all subsets of four modalities as input feature vector and the postoperative language outcome as output. We trained and cross-validated SVR models, and compared the cross-validation (CV) errors of all models for prediction of language outcome. Results: Seven patients had some level of postoperative language decline and two of them had significant postoperative decline in naming. Some parts of language areas identified by four modalities were resected in these patients. We found that an SVR model consisting of fMRI, MEG, and hgECoG provided minimum CV error, although an SVR model consisting of fMRI and MEG was the optimal model that facilitated the best trade-off between model complexity and prediction accuracy. Conclusions: A multimodal SVR can be used to predict the language outcome. (C) 2018 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.
引用
收藏
页码:560 / 571
页数:12
相关论文
共 86 条
[1]  
Anguita Davide, 2009, Proceedings of the 2009 International Conference on Data Mining. DMIN 2009, P291
[2]   Integrated MEG and fMRI model: Synthesis and analysis [J].
Babajani, A ;
Nekooei, MH ;
Soltanian-Zadeh, H .
BRAIN TOPOGRAPHY, 2005, 18 (02) :101-113
[3]   Integrated MEG/EEG and fMRI model based on neural masses [J].
Babajani, Abbas ;
Soltanian-Zadeh, Hamid .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (09) :1794-1801
[4]   Language mapping using high gamma electrocorticography, fMRI, and TMS versus electrocortical stimulation [J].
Babajani-Feremi, Abbas ;
Narayana, Shalini ;
Rezaie, Roozbeh ;
Choudhri, Asim F. ;
Fulton, Stephen P. ;
Boop, Frederick A. ;
Wheless, James W. ;
Papanicolaou, Andrew C. .
CLINICAL NEUROPHYSIOLOGY, 2016, 127 (03) :1822-1836
[5]   Variation in the topography of the speech production cortex verified by cortical stimulation and high gamma activity [J].
Babajani-Feremi, Abbas ;
Rezaie, Roozbeh ;
Narayana, Shalini ;
Choudhri, Asim F. ;
Fulton, Stephen P. ;
Boop, Frederick A. ;
Wheless, James W. ;
Papanicolaou, Andrew C. .
NEUROREPORT, 2014, 25 (18) :1411-1417
[6]  
Balter S, 2016, BRAIN LANG
[7]  
Baron I.S., 2004, NEUROPSYCHOLOGICAL E
[8]   The cost of epilepsy in the United States: An estimate from population-based clinical and survey data [J].
Begley, CE ;
Famulari, M ;
Annegers, JF ;
Lairson, DR ;
Reynolds, TF ;
Coan, S ;
Dubinsky, S ;
Newmark, ME ;
Leibson, C ;
So, EL ;
Rocca, WA .
EPILEPSIA, 2000, 41 (03) :342-351
[9]   Mapping anterior temporal lobe language areas with fMRI: A multicenter normative study [J].
Binder, Jeffrey R. ;
Gross, William L. ;
Allendorfer, Jane B. ;
Bonilha, Leonardo ;
Chapin, Jessica ;
Edwards, Jonathan C. ;
Grabowski, Thomas J. ;
Langfitt, John T. ;
Loring, David W. ;
Lowe, Mark J. ;
Koenig, Katherine ;
Morgan, Paul S. ;
Ojemann, Jeffrey G. ;
Rorden, Christopher ;
Szaflarski, Jerzy P. ;
Tivarus, Madalina E. ;
Weaver, Kurt E. .
NEUROIMAGE, 2011, 54 (02) :1465-1475
[10]   Human brain language areas identified by functional magnetic resonance imaging [J].
Binder, JR ;
Frost, JA ;
Hammeke, TA ;
Cox, RW ;
Rao, SM ;
Prieto, T .
JOURNAL OF NEUROSCIENCE, 1997, 17 (01) :353-362