Machine learning classification of mesial temporal sclerosis in epilepsy patients

Abstract

a b s t r a c tBackground and purpose: Novel approaches applying machine-learning methods to neuroimaging data seek to develop individualized measures that will aid in the diagnosis and treatment of brain-based disorders such as temporal lobe epilepsy (TLE). Using a large cohort of epilepsy patients with and without mesial temporal sclerosis (MTS), we sought to automatically classify MTS using measures of cortical morphology, and to further relate classification probabilities to measures of disease burden. Materials and methods: Our sample consisted of high-resolution T1 structural scans of 169 adults with epilepsy collected across five different 1.5 T and four different 3 T scanners at UCLA. We applied a multiple support vector machine recursive feature elimination algorithm to morphological measures generated from FreeSurfer's automated segmentation and parcellation in order to classify Epilepsy patients with MTS (n = 85) from those without MTS (N = 84). Results: In addition to hippocampal volume, we found that alterations in cortical thickness, surface area, volume and curvature in inferior frontal and anterior and inferior temporal regions contributed to a classification accuracy of up to 81% (p = 1.3 × 10 −17 ) in identifying MTS. We also found that MTS classification probabilities were associated with a longer duration of disease for epilepsy patients both with and without MTS. Conclusions: In addition to implicating extra-hippocampal involvement of MTS, these findings shed further light on the pathogenesis of TLE and may ultimately assist in the development of automated tools that incorporate multiple neuroimaging measures to assist clinicians in detecting more subtle cases of TLE and MTS.

Using machine learning to classify temporal lobe epilepsy based on diffusion MRI

“…An SVM study using T1‐weighted images performed by Rudie et al. achieved a prediction accuracy of up to 81% for patients with TLE compared to those with other structural abnormalities, and it additionally found correlations between predictive value and clinical disease progression (Rudie, Colby, & Salamon, 2015). …”

Learning to see the invisible: A data‐driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy

“…[5][6][7][8][9][10] Focke et al generated maps of gray matter voxel relevance across the brain by visualizing the weights assigned to each feature by a support vector machine (SVM) classifier trained to lateralize temporal lobe epilepsy (TLE) in 38 MRI-positive patients. [5][6][7][8][9][10] Focke et al generated maps of gray matter voxel relevance across the brain by visualizing the weights assigned to each feature by a support vector machine (SVM) classifier trained to lateralize temporal lobe epilepsy (TLE) in 38 MRI-positive patients.…”

“…Detection of brain abnormalities on magnetic resonance (MR) images using contemporary methods such as machine learning is an emerging and promising area of research. [5][6][7][8][9][10] Focke et al generated maps of gray matter voxel relevance across the brain by visualizing the weights assigned to each feature by a support vector machine (SVM) classifier trained to lateralize temporal lobe epilepsy (TLE) in 38 MRI-positive patients. 6 These relevance maps provided an interesting demonstration of the distribution of morphological gray matter changes found in MRI-positive TLE patients.…”

Automatic Lateralization of Temporal Lobe Epilepsy Based on MEG Network Features Using Support Vector Machines

“…Additionally, graph-theory metrics are able to summarize the network properties with less computational cost than the voxel-based and skeletonbased methods [8,10,59]. Additionally, for classification of TLE lateralization, MEG has higher temporal resolution than MRI [9,45], fMRI [33], or DTI [8,10,59]. Thus, method that can analyze the effects of different frequency bands, especially the frequency band in which epileptiform discharges, was generated.…”

“…As a classification tool, the SVM technique is flexible, automated, and sufficiently fast to operate in a clinical setting [8]. SVM algorithms have been applied for measuring brain morphology [9], including 2 Complexity cortical thickness, volume, curvature, and identification of MTS in TLE patients. SVM approaches have been utilized to determine lateralization of the TLE epileptogenic focus with diffusion tensor imaging (DTI) structural connectomes [10].…”