Many methods applied to data acquired by various imaging modalities have been evaluated for their benefit in localizing lesions in magnetic resonance (MR) negative epilepsy patients. No approach has proven to be a stand-alone method with sufficiently high sensitivity and specificity. The presented study addresses the potential benefit of the automated fusion of results of individual methods in presurgical evaluation. We collected electrophysiological, MR, and nuclear imaging data from 137 patients with pharmacoresistant MR-negative/inconclusive focal epilepsy. A subgroup of 32 patients underwent surgical treatment with known postsurgical outcomes and histopathology. We employed a Gaussian mixture model to reveal several classes of gray matter tissue. Classes specific to epileptogenic tissue were identified and validated using the surgery subgroup divided into two disjoint sets. We evaluated the classification accuracy of the proposed method at a voxel-wise level and assessed the effect of individual methods. The training of the classifier resulted in six classes of gray matter tissue. We found a subset of two classes specific to tissue located in resected areas. The average classification accuracy (i.e., the probability of correct classification) was significantly higher than the level of chance in the training group (0.73) and even better in the validation surgery subgroup (0.82). Nuclear imaging, diffusion-weighted imaging, and source localization of interictal epileptic discharges were the strongest methods for classification accuracy. We showed that the automatic fusion of results can identify brain areas that show epileptogenic gray matter tissue features. The method might enhance the presurgical evaluations of MR-negative epilepsy patients.

Brno Epilepsy Center 1st Department of Neurology St Anne's University Hospital and Medical Faculty of Masaryk University Brno Czech Republic

Central European Institute of Technology Masaryk University Brno Czech Republic

Medical Faculty Masaryk University Brno Czech Republic

Zobrazit více v PubMed

Ahmed, B. , Thesen, T. , Blackmon, K. , Zhao, Y. , Devinsky, O. , Kuzniecky, R. , & Brodley, C . (2014). Hierarchical conditional random fields for outlier detection: An application to detecting epileptogenic cortical malformations. Paper Presented at the Proceedings of the 31st International Conference on Machine Learning, Proceedings of Machine Learning Research. Retrieved from http://proceedings.mlr.press

Ashburner, J. , & Friston, K. J. (2005). Unified segmentation. NeuroImage, 26(3), 839–851. 10.1016/j.neuroimage.2005.02.018 PubMed DOI

Bernasconi, A. , & Bernasconi, N. (2011). Unveiling epileptogenic lesions: The contribution of image processing. Epilepsia, 52, 20–24. 10.1111/j.1528-1167.2011.03146.x PubMed DOI

Bernhardt, B. C. , Hong, S. J. , Bernasconi, A. , & Bernasconi, N. (2015). Magnetic resonance imaging pattern learning in temporal lobe epilepsy: Classification and prognostics. Annals of Neurology, 77(3), 436–446. 10.1002/ana.24341 PubMed DOI

Bonilha, L. , Lee, C. Y. , Jensen, J. H. , Tabesh, A. , Spampinato, M. V. , Edwards, J. C. , … Helpern, J. A. (2015). Altered microstructure in temporal lobe epilepsy: A diffusional kurtosis imaging study. AJNR American Journal of Neuroradiology, 36(4), 719–724. 10.3174/ajnr.A4185 PubMed DOI PMC

Boscolo Galazzo, I. , Storti, S. F. , del Felice, A. , Pizzini, F. B. , Arcaro, C. , Formaggio, E. , … Manganotti, P. (2015). Patient‐specific detection of cerebral blood flow alterations as assessed by arterial spin labeling in drug‐resistant epileptic patients. PLoS One, 10(5), e0123975. 10.1371/journal.pone.0123975 PubMed DOI PMC

Colliot, O. , Antel, S. B. , Naessens, V. B. , Bernasconi, N. , & Bernasconi, A. (2006). In vivo profiling of focal cortical dysplasia on high‐resolution MRI with computational models. Epilepsia, 47(1), 134–142. 10.1111/j.1528-1167.2006.00379.x PubMed DOI

Colombo, N. , Salamon, N. , Raybaud, C. , Ozkara, C. , & Barkovich, A. J. (2009). Imaging of malformations of cortical development. Epileptic Disorders, 11(3), 194–205. 10.1684/epd.2009.0262 PubMed DOI

Dachet, F. , Bagla, S. , Keren‐Aviram, G. , Morton, A. , Balan, K. , Saadat, L. , … Loeb, J. A. (2015). Predicting novel histopathological microlesions in human epileptic brain through transcriptional clustering. Brain, 138(Pt 2), 356–370. 10.1093/brain/awu350 PubMed DOI PMC

Delalleau, O. , Courville, A. , & Bengio, Y. (2018). Efficient EM training of Gaussian mixtures with missing data. arXiv, 1–6.

el Azami, M. , Hammers, A. , Costes, N. , & Lartizien, C. (2013). Computer aided diagnosis of intractable epilepsy with MRI imaging based on textural information. Paper Presented at the 2013 International Workshop on Pattern Recognition in Neuroimaging.

Feindel, K. W. (2013). Can we develop pathology‐specific MRI contrast for “MR‐negative” epilepsy? Epilepsia, 54, 71–74. 10.1111/epi.12189 PubMed DOI

Fellah, S. , Callot, V. , Viout, P. , Confort‐Gouny, S. , Scavarda, D. , Dory‐Lautrec, P. , … Girard, N. (2012). Epileptogenic brain lesions in children: The added‐value of combined diffusion imaging and proton MR spectroscopy to the presurgical differential diagnosis. Childs Nervous System, 28(2), 273–282. 10.1007/s00381-011-1604-9 PubMed DOI

Guerrini, R. , Sicca, F. , & Parmeggiani, L. (2003). Epilepsy and malformations of the cerebral cortex. Epileptic Disorders, 5(Suppl 2), S9–S26. PubMed

Juhasz, C. , & John, F. (2020). Utility of MRI, PET, and ictal SPECT in presurgical evaluation of non‐lesional pediatric epilepsy. Seizure‐European Journal of Epilepsy, 77, 15–28. 10.1016/j.seizure.2019.05.008 PubMed DOI PMC

Kini, L. G. , Gee, J. C. , & Litt, B. (2016). Computational analysis in epilepsy neuroimaging: A survey of features and methods. NeuroImage: Clinical, 11, 515–529. 10.1016/j.nicl.2016.02.013 PubMed DOI PMC

Kotikalapudi, R. , Martin, P. , Marquetand, J. , Lindig, T. , Bender, B. , & Focke, N. K. (2018). Systematic assessment of multispectral voxel‐based morphometry in previously MRI‐negative focal epilepsy. American Journal of Neuroradiology, 39(11), 2014–2021. 10.3174/ajnr.A5809 PubMed DOI PMC

Krsek, P. , Kudr, M. , Jahodova, A. , Komarek, V. , Maton, B. , Malone, S. , … Duchowny, M. (2013). Localizing value of ictal SPECT is comparable to MRI and EEG in children with focal cortical dysplasia. Epilepsia, 54(2), 351–358. 10.1111/epi.12059 PubMed DOI

Lai, C. R. , Guo, S. W. , Cheng, L. N. , & Wang, W. S. (2017). A comparative study of feature selection methods for the discriminative analysis of temporal lobe epilepsy. Frontiers in Neurology, 8, 633. 10.3389/fneur.2017.00633 PubMed DOI PMC

Lascano, A. M. , Perneger, T. , Vulliemoz, S. , Spinelli, L. , Garibotto, V. , Korff, C. M. , … Seeck, M. (2016). Yield of MRI, high‐density electric source imaging (HD‐ESI), SPECT and PET in epilepsy surgery candidates. Clinical Neurophysiology, 127(1), 150–155. 10.1016/j.clinph.2015.03.025 PubMed DOI

Lee, S. M. , Kwon, S. , & Lee, Y. J. (2019). Diagnostic usefulness of arterial spin labeling in MR negative children with new onset seizures. Seizure‐European Journal of Epilepsy, 65, 151–158. 10.1016/j.seizure.2019.01.024 PubMed DOI

Ma, D. , Jones, S. E. , Deshmane, A. , Sakaie, K. , Pierre, E. Y. , Larvie, M. , … Wang, Z. I. (2019). Development of high‐resolution 3D MR fingerprinting for detection and characterization of epileptic lesions. Journal of Magnetic Resonance Imaging, 49(5), 1333–1346. 10.1002/jmri.26319 PubMed DOI

Megevand, P. , & Seeck, M. (2020). Electric source imaging for presurgical epilepsy evaluation: Current status and future prospects. Expert Review of Medical Devices, 17(5), 405–412. 10.1080/17434440.2020.1748008 PubMed DOI

Michel, C. M. , & Brunet, D. (2019). EEG source imaging: A practical review of the analysis steps. Frontiers in Neurology, 10, 325. 10.3389/fneur.2019.00325 PubMed DOI PMC

Mikl, M. , Marecek, R. , Hlustik, P. , Pavlicova, M. , Drastich, A. , Chlebus, P. , … Krupa, P. (2008). Effects of spatial smoothing on fMRI group inferences. Magnetic Resonance Imaging, 26(4), 490–503. 10.1016/j.mri.2007.08.006 PubMed DOI

Muhlau, M. , Wohlschlager, A. M. , Gaser, C. , Valet, M. , Weindl, A. , Nunnemann, S. , … Ilg, R. (2009). Voxel‐based morphometry in individual patients: A pilot study in early Huntington disease. AJNR. American Journal of Neuroradiology, 30(3), 539–543. 10.3174/ajnr.A1390 PubMed DOI PMC

Noth, U. , Gracien, R. M. , Maiworm, M. , Reif, P. S. , Hattingen, E. , Knake, S. , … Deichmann, R. (2020). Detection of cortical malformations using enhanced synthetic contrast images derived from quantitative T1 maps. NMR in Biomedicine, 33(2), e4203. 10.1002/nbm.4203 PubMed DOI

Pardoe, H. , & Kuzniecky, R. (2014). Advanced imaging techniques in the diagnosis of nonlesional epilepsy: MRI, MRS, PET, and SPECT. Epilepsy Currents, 14(3), 121–124. 10.5698/1535-7597-14.3.121 PubMed DOI PMC

Rathore, C. , Dickson, J. C. , Teotonio, R. , Ell, P. , & Duncan, J. S. (2014). The utility of 18F‐fluorodeoxyglucose PET (FDG PET) in epilepsy surgery. Epilepsy Research, 108(8), 1306–1314. 10.1016/j.eplepsyres.2014.06.012 PubMed DOI

Rudie, J. D. , Colby, J. B. , & Salamon, N. (2015). Machine learning classification of mesial temporal sclerosis in epilepsy patients. Epilepsy Research, 117, 63–69. 10.1016/j.eplepsyres.2015.09.005 PubMed DOI

Salmond, C. H. , Ashburner, J. , Vargha‐Khadem, F. , Connelly, A. , Gadian, D. G. , & Friston, K. J. (2002). Distributional assumptions in voxel‐based morphometry. NeuroImage, 17(2), 1027–1030. 10.1006/nimg.2002.1153 PubMed DOI

Shultz, S. R. , O'Brien, T. J. , Stefanidou, M. , & Kuzniecky, R. I. (2014). Neuroimaging the epileptogenic process. Neurotherapeutics, 11(2), 347–357. 10.1007/s13311-014-0258-1 PubMed DOI PMC

Smith, J. R. , Lee, M. R. , King, D. W. , Murro, A. M. , Park, Y. D. , Lee, G. P. , … Harp, R. (1997). Results of lesional vs. nonlesional frontal lobe epilepsy surgery. Stereotactic and Functional Neurosurgery, 69(1–4 Pt 2), 202–209. PubMed

Sulc, V. , Stykel, S. , Hanson, D. P. , Brinkmann, B. H. , Jones, D. T. , Holmes, D. R. , … Worrell, G. A. (2014). Statistical SPECT processing in MRI‐negative epilepsy surgery. Neurology, 82(11), 932–939. 10.1212/wnl.0000000000000209 PubMed DOI PMC

Tellez‐Zenteno, J. F. , Ronquillo, L. H. , Moien‐Afshari, F. , & Wiebe, S. (2010). Surgical outcomes in lesional and non‐lesional epilepsy: A systematic review and meta‐analysis. Epilepsy Research, 89(2–3), 310–318. 10.1016/j.eplepsyres.2010.02.007 PubMed DOI

Vytvarova, E. , Marecek, R. , Fousek, J. , Strycek, O. , & Rektor, I. (2017). Large‐scale cortico‐subcortical functional networks in focal epilepsies: The role of the basal ganglia. NeuroImage: Clinical, 14, 28–36. 10.1016/j.nicl.2016.12.014 PubMed DOI PMC

Whelan, C. D. , Altmann, A. , Botia, J. A. , Jahanshad, N. , Hibar, D. P. , Absil, J. , … Grp, E. N.‐E. W. (2018). Structural brain abnormalities in the common epilepsies assessed in a worldwide ENIGMA study. Brain, 141, 391–408. 10.1093/brain/awx341 PubMed DOI PMC

Winston, G. P. , Vos, S. B. , Caldairou, B. , Hong, S. J. , Czech, M. , Wood, T. C. , … Bernasconi, A. (2020). Microstructural imaging in temporal lobe epilepsy: Diffusion imaging changes relate to reduced neurite density. NeuroImage: Clinical, 26, 10.1016/j.nicl.2020.102231 PubMed DOI PMC

Yamazoe, T. , von Ellenrieder, N. , Khoo, H. M. , Huang, Y. H. , Zazubovits, N. , Dubeau, F. , & Gotman, J. (2019). Widespread interictal epileptic discharge more likely than focal discharges to unveil the seizure onset zone in EEG‐fMRI. Clinical Neurophysiology, 130(4), 429–438. 10.1016/j.clinph.2018.12.014 PubMed DOI

Multimodal combination of neuroimaging methods for localizing the epileptogenic zone in MR-negative epilepsy

The benefit of the diffusion kurtosis imaging in presurgical evaluation in patients with focal MR-negative epilepsy

Epileptogenic zone detection in MRI negative epilepsy using adaptive thresholding of arterial spin labeling data