MRI-Based Machine Learning Prediction Framework to Lateralize Hippocampal Sclerosis in Patients With Temporal Lobe Epilepsy

Abstract

Objective.MRI fails to reveal hippocampal pathology in 30-50% of temporal lobe epilepsy (TLE) surgical candidates. To address this clinical challenge, we developed an automated MRI-based classifier that lateralizes the side of covert hippocampal pathology in TLE.Methods.We trained a surface-based linear discriminant classifier that uses T1-weighted (morphology) and T2-weighted as well as FLAIR/T1 (intensity) features. The classifier was trained on 60 TLE patients (mean age: 35.6; 58% female) with histologically-verified hippocampal sclerosis (HS). Images were deemed as MRI-negative in 42% of cases based on neuroradiological reading (40% based on hippocampal volumetry). The predictive model automatically labelled patients as left or right TLE. Lateralization accuracy was compared to electro-clinical data, including side of surgery. Accuracy of the classifier was further assessed in two independent TLE cohorts with similar demographics and electro-clinical characteristics (n=57; 58% MRI-negative).Results.The overall lateralization accuracy was 93% (95%; CI 92% - 94%), regardless of HS visibility. In MRI-negative TLE, the combination of T2 and FLAIR/T1 intensities provided the highest accuracy both in the training (84%, area-under-the-curve (AUC): 0.95±0.02) and the validation cohorts (Cohort 1: 90%, AUC: 0.99; Cohort 2: 76%, AUC: 0.94).Conclusion.This prediction model for TLE lateralization operates on readily available conventional MRI contrasts and offers gain in accuracy over visual radiological assessment. The combined contribution of decreased T1- and increased T2-weighted intensities makes the synthetic FLAIR/T1 contrast particularly effective in MRI-negative HS, setting the basis for broad clinical translation.

The Role of MRI in the Treatment of Drug-Resistant Focal Epilepsy

“…The combination of SurfPatch with 3D surface-based shape models [40, 41] sampling multicontrast features along the central path of hippocampal subfields allows mapping morphological changes at a laminar level that may not be identified visually, thus furthering our knowledge of the HS spectrum [42]. Recently, a linear discriminant classifier trained on T1- and FLAIR-derived laminar features of histologically validated HS accurately lateralized the focus in 93% of TLE patients, with a remarkable 85% sensitivity in MRI-negative cases [43] (Fig. 1).…”

Interpretable deep learning‐based hippocampal sclerosis classification

“…Namely, the interpretation methods used in the previous studies had a few drawbacks. Some of them were too dense and noisy 36 or plotted on the automatically generated asymmetry maps, not on the MRI itself, 37 hence the clinician had to further match the interpretations with the anatomical brain regions. In another work, 38 the regions identified as important also included irrelevant regions like background or cranium, which cannot be truly associative with the prediction.…”

Artificial Intelligence Applications in the Imaging of Epilepsy and Its Comorbidities: Present and Future

“…In recent years, ML algorithms using multimodal MRI have been shown to lateralize hippocampal pathology in patients with temporal lobe epilepsy (TLE) and hippocampal sclerosis (HS). 18 , 19 A recent ENIGMA-Epilepsy study investigated the performance of ML and DL algorithms using structural MRI and diffusion MRI (dMRI) to classify controls vs patients with TLE with HS and MRI-negative TLE. 13 This study revealed that structural MRI and dMRI-based models had similar accuracy and that models for TLE-HS were more accurate than for MRI-negative TLE.…”