TLE lateralization using whole brain structural connectivity

Abstract

A prerequisite of temporal lobe epilepsy (TLE) surgery is to lateralize the disease. Recent studies have shown the capability of diffusion weighted MRI (DWMRI) in lateralizing TLE patients. This has been achieved by analyzing diffusion parameters of specific white matter tracts or regions known to be involved in the disease; however, other brain regions and connections have not been investigated for TLE lateralization. Whole brain structural connectivity using DWMRI provides a wealth of information regarding the structural connections in the brain. This information can be explored to find the most effective connections for TLE lateralization. In this work, we investigate the connectivity matrices calculated from DWMRI of 10 left and 10 right TLE patients to find the most effective connections for lateralizing the disease. Linear support vector machine (LSVM) classifier and leave-one-out cross validation scheme are used to estimate classification performance of the connectivity feature subsets. A subset of three connections with 100% classification accuracy is found. The corresponding LSVM classifier may be used to lateralize prospective TLE patients.

Artificial intelligence for classification of temporal lobe epilepsy with ROI-level MRI data: A worldwide ENIGMA-Epilepsy study

“…Structural-based models had a superior accuracy for detection over lateralization of TLE, particularly for SVM (83% detection vs. 67% lateralization, on average). The issue of epilepsy lateralization was one of the earliest to be addressed by machine learning approaches with modalities including positron emission tomography (PET) ( Lee et al, 2000 ), photon emission computed tomography (SPECT) ( Lopes et al, 2010 ), and diffusion magnetic resonance techniques ( Davoodi-Bojd et al, 2016 ) including diffusion tensor ( Ahmadi et al, 2009 , Concha et al, 2012 , Kamiya et al, 2016 ) and kurtosis ( Del Gaizo et al, 2017 ) imaging, with mean accuracies overall similar to those found in this study. Future studies might enhance lateralization accuracy by building classifiers based on multi-modal features, particularly for non-lesional patients, whose lateralization was suboptimal and often not better than that of a random model.…”

Machine learning applications in epilepsy

“…65 A number of studies have also applied machine learning techniques to morphometric analysis of structural MRI using T1-weighted and fluid-attenuated inversion recovery (FLAIR) sequences, both for detection 66 and lateralization 67 of TLE. Similar results have more recently been shown for analysis of diffusion-weighted imaging (DWI), 68 DTI, 69 and diffusion kurtosis imaging. 70 Recently, Jin and Chung also applied an SVM classifier to functional connectivity data from resting-state MEG, distinguishing 46 patients with TLE from matched controls with 95.1% accuracy and lateralizing TLEs with 76.2% accuracy.…”

Detecting Cortical Thickness Changes in Epileptogenic Lesions Using Machine Learning

“…On every iteration, mean kurtosis outperformed fractional anisotropy and mean diffusivity and had considerably greater average accuracy, with 82% mean kurtosis, 68% fractional anisotropy, and 51% mean diffusivity. Esmaeil Davoodi-Bojd et al [ 42 ] classified temporal lobe epilepsy lateralization using linear SVM. To determine the most efficient connections for lateralizing the disease, they examined the connectivity matrices produced from diffusion-weighted MRI of 10 left and 10 right patients.…”