Convolutional Neural Network Algorithm to Determine Lateralization of Seizure Onset in Patients With Epilepsy

Abstract

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.

Machine learning applied to epilepsy: bibliometric and visual analysis from 2004 to 2023

“…Traditionally, this task requires the expertise of a trained neurologist, but the ML model has shown considerable accuracy, thereby simplifying the diagnostic process and enabling faster patient evaluation. MRI Image Analysis for Surgical Planning: In a groundbreaking study, researchers applied convolutional neural networks (CNNs) to analyze MRI scans of epilepsy patients ( 56 ). The model successfully identified epileptogenic zones with high precision, aiding neurosurgeons in planning surgical interventions with improved accuracy, potentially increasing the success rate of epilepsy surgeries.…”

Charting the Progress of Epilepsy Classification: Navigating a Shifting Landscape

“…He proposed that this condition could have origins in the brain, challenging the prevailing belief that supernatural influences caused it. Nevertheless, it was not until the contemporary age that epilepsy was perceived as a neurological condition characterized by discernible physiological foundations [2]. The alteration in perspective has been crucial in advancing epilepsy categorization and its essential function in diagnosing and treating the condition.…”