Highlights Machine learning and artificial intelligence have gained popularity for medical applications. We applied support vector machine (SV) and deep learning (DL) in termporal lobe epilepsy (TLE) Structural and diffusion-based models showed similar classification accuracies. Diffusion-based models to diagnose TLE performed better or similar compared to models to lateralize TLE. Models for patients with hippocampal sclerosis were more accurate than models that stratified non-lesional patients.

Epilepsy incidence and prevalence peaks in older adults yet systematic studies of brain ageing and cognition in older adults with epilepsy remain limited. Here, we characterize patterns of cortical atrophy and cognitive impairment in 73 older adults with temporal lobe epilepsy (>55 years) and compare these patterns to those observed in 70 healthy controls and 79 patients with amnestic mild cognitive impairment, the prodromal stage of Alzheimer’s disease. Patients with temporal lobe epilepsy were recruited from four tertiary epilepsy surgical centres; amnestic mild cognitive impairment and control subjects were obtained from the Alzheimer’s Disease Neuroimaging Initiative database. Whole brain and region of interest analyses were conducted between patient groups and controls, as well as between temporal lobe epilepsy patients with early-onset (age of onset <50 years) and late-onset (>50 years) seizures. Older adults with temporal lobe epilepsy demonstrated a similar pattern and magnitude of medial temporal lobe atrophy to amnestic mild cognitive impairment. Region of interest analyses revealed pronounced medial temporal lobe thinning in both patient groups in bilateral entorhinal, temporal pole, and fusiform regions (all P < 0.05). Patients with temporal lobe epilepsy demonstrated thinner left entorhinal cortex compared to amnestic mild cognitive impairment (P = 0.02). Patients with late-onset temporal lobe epilepsy had a more consistent pattern of cortical thinning than patients with early-onset epilepsy, demonstrating decreased cortical thickness extending into the bilateral fusiform (both P < 0.01). Both temporal lobe epilepsy and amnestic mild cognitive impairment groups showed significant memory and language impairment relative to healthy control subjects. However, despite similar performances in language and memory encoding, patients with amnestic mild cognitive impairment demonstrated poorer delayed memory performances relative to both early and late-onset temporal lobe epilepsy. Medial temporal lobe atrophy and cognitive impairment overlap between older adults with temporal lobe epilepsy and amnestic mild cognitive impairment highlights the risks of growing old with epilepsy. Concerns regarding accelerated ageing and Alzheimer’s disease co-morbidity in older adults with temporal lobe epilepsy suggests an urgent need for translational research aimed at identifying common mechanisms and/or targeting symptoms shared across a broad neurological disease spectrum.

Objective: Recent work has shown that people with common epilepsies have characteristic patterns of cortical thinning, and that these changes may be progressive over time. Leveraging a large multicenter cross-sectional cohort, we investigated whether regional morphometric changes occur in a sequential manner, and whether these changes in people with mesial temporal lobe epilepsy and hippocampal sclerosis (MTLE-HS) correlate with clinical features.Methods: We extracted regional measures of cortical thickness, surface area, and subcortical brain volumes from T1-weighted (T1W) magnetic resonance imaging (MRI) scans collected by the ENIGMA-Epilepsy consortium, comprising 804 people with MTLE-HS and 1625 healthy controls from 25 centers. Features with a moderate case-control effect size (Cohen d ≥ .5) were used to train an event-based model (EBM), which estimates a sequence of disease-specific biomarker changes from cross-sectional data and assigns a biomarker-based fine-grained disease stage to individual patients. We tested for associations between EBM disease stage and duration of epilepsy, age at onset, and antiseizure medicine (ASM) resistance. Results:In MTLE-HS, decrease in ipsilateral hippocampal volume along with increased asymmetry in hippocampal volume was followed by reduced thickness in neocortical regions, reduction in ipsilateral thalamus volume, and finally, increase in ipsilateral lateral ventricle volume. EBM stage was correlated with duration of illness (Spearman ρ = .293, p = 7.03 × 10 −16 ), age at onset (ρ = −.18, p = 9.82 × 10 −7 ), and ASM resistance (area under the curve = .59, p = .043, Mann-Whitney U test). However, associations were driven by cases assigned to EBM Stage 0, which represents MTLE-HS with mild or nondetectable abnormality on T1W MRI.

Background and Objectives:A new frontier in diagnostic radiology is the inclusion of machine-assisted support tools that facilitate the identification of subtle lesions often not visible to the human eye. Structural neuroimaging plays an essential role in the identification of lesions in patients with epilepsy, which often coincide with the seizure focus. Here we explore the potential for a convolutional neural network (CNN) to determine lateralization of seizure onset in patients with epilepsy using T1-weighted structural MRI scans as input.Methods:Using a dataset of 359 patients with temporal lobe epilepsy (TLE) from 7 surgical centers, we tested whether a CNN based on T1-weighted images could classify seizure laterality concordant with clinical team consensus. This CNN was compared to a randomized model (comparison to chance) and a hippocampal volume logistic regression (comparison to current clinically-available measures). Furthermore, we leveraged a CNN feature visualization technique to identify regions used to classify patients.Results:Across 100 runs, the CNN model was concordant with clinician lateralization on average 78% (SD= 5.1%) of runs with the best performing model achieving 89% concordance. The CNN outperformed the randomized model (average concordance of 51.7%) on 100% of runs with an average improvement of 26.2% and outperformed the hippocampal volume model (average concordance of 71.7%) on 85% of runs with an average improvement of 6.25%. Feature visualization maps revealed that in addition to the medial temporal lobe, regions in the lateral temporal lobe, cingulate, and precentral gyrus aided in classification.Discussion:These extra-temporal lobe features underscore the importance of whole-brain models to highlight areas worthy of clinician scrutiny during temporal lobe epilepsy lateralization. This proof-of-concept study illustrates that a CNN applied to structural MRI data can visually aid clinician-led localization of epileptogenic zone and identify extra-hippocampal regions that may require additional radiological attention.Classification of Evidence:This study provides Class II evidence that in patients with drug-resistant unilateral temporal lobe epilepsy, a convolutional neural network algorithm derived from T1-weighted MR images can correctly classify seizure laterality.