Extrahippocampal Radiomics Analysis Can Potentially Identify Laterality in Patients With MRI-Negative Temporal Lobe Epilepsy.

E-Nae Cheong,Woo Hyun Shim,Da Eun Jung,Ji Eun Park

doi:10.3389/fneur.2021.706576

Abstract

Objective: The objective of the study was to investigate whether radiomics features of extrahippocampal regions differ between patients with epilepsy and healthy controls, and whether any differences can identify patients with magnetic resonance imaging (MRI)-negative temporal lobe epilepsy (TLE).Methods: Data from 36 patients with hippocampal sclerosis (HS) and 50 healthy controls were used to construct a radiomics model. A total of 1,618 radiomics features from the affected hippocampal and extrahippocampal regions were compared with features from healthy controls and the unaffected side of patients. Using a stepwise selection method with a univariate t-test and elastic net penalization, significant predictors for identifying TLE were separately selected for the hippocampus (H+) and extrahippocampal region (H–). Each model was independently validated with an internal set of MRI-negative adult TLE patients (n = 22) and pediatric validation cohort with MRI-negative TLE (n = 20) from another tertiary center; diagnostic performance was calculated using area under the curve (AUC) of the receiver-operating-characteristic curve analysis.Results: Forty-eight significant H+ radiomic features and 99 significant H– radiomic features were selected from the affected side of patients and used to create a hippocampus model and an extrahippocampal model, respectively. Texture features were the most frequently selected feature. Training set showed slightly higher accuracy between hippocampal (AUC = 0.99) and extrahippocampal model (AUC = 0.97). In the internal validation and external validation sets, the extrahippocampal model (AUC = 0.80 and 0.92, respectively) showed higher diagnostic performance for identifying the affected side of patients than the hippocampus model (AUC = 0.67 and 0.69).Significance: Radiomics revealed extrahippocampal abnormality in the affected side of patients with TLE and could potentially help to identify MRI-negative TLE.Classification of Evidence: Class IV Criteria for Rating Diagnostic Accuracy Studies.

Highlights

Identification of the lateralization of temporal lobe epilepsy (TLE) is important for presurgical workup, and precise localization of the epileptogenic focus is associated with a good surgical outcome
684 features showed a significant difference between the affected and unaffected hippocampus according to univariate t-tests; the elastic net penalization method applied to these features showed 48 features to be predictive of the laterality of epilepsy (α = 0.9)
We identified radiomic features measured in the hippocampal and extrahippocampal regions of the affected side of patients with TLE that significantly differed from those of the unaffected side and those of healthy controls

Summary

Introduction

Identification of the lateralization of temporal lobe epilepsy (TLE) is important for presurgical workup, and precise localization of the epileptogenic focus is associated with a good surgical outcome. Metabolic imaging using [18F]fluorodeoxyglucose-positron emission tomography (FDG-PET) showed that hypometabolism is not restricted to the mesial temporal lobe and that twothirds of patients have a hypometabolism pattern in the adjacent lateral and posterior temporal lobe [2, 3] Such MRI-negative but PET-positive TLE is a surgically remediable syndrome [4,5,6,7] that primarily involves the lateral temporal neocortex rather than mesial lobe structures. Radiation exposure exists in PET and may not be appropriate for patients especially in children, due to the potential for long-term toxicity This opens up the possibility that identification of extratemporal abnormalities could predict laterality in patients with MRI-negative TLE. Use of a non-invasive and no radiationbased MRI imaging tool for radiomics will be beneficial for pediatric patients, who will benefit from early management and monitoring

Methods

Results

Conclusion