Diagnostic Performance of MRI Volumetry in Epilepsy Patients With Hippocampal Sclerosis Supported Through a Random Forest Automatic Classification Algorithm

Abstract

Introduction: Several methods offer free volumetry services for MR data that adequately quantify volume differences in the hippocampus and its subregions. These methods are frequently used to assist in clinical diagnosis of suspected hippocampal sclerosis in temporal lobe epilepsy. A strong association between severity of histopathological anomalies and hippocampal volumes was reported using MR volumetry with a higher diagnostic yield than visual examination alone. Interpretation of volumetry results is challenging due to inherent methodological differences and to the reported variability of hippocampal volume. Furthermore, normal morphometric differences are recognized in diverse populations that may need consideration. To address this concern, we highlighted procedural discrepancies including atlas definition and computation of total intracranial volume that may impact volumetry results. We aimed to quantify diagnostic performance and to propose reference values for hippocampal volume from two well-established techniques: FreeSurfer v.06 and volBrain-HIPS.Methods: Volumetry measures were calculated using clinical T1 MRI from a local population of 61 healthy controls and 57 epilepsy patients with confirmed unilateral hippocampal sclerosis. We further validated the results by a state-of-the-art machine learning classification algorithm (Random Forest) computing accuracy and feature relevance to distinguish between patients and controls. This validation process was performed using the FreeSurfer dataset alone, considering morphometric values not only from the hippocampus but also from additional non-hippocampal brain regions that could be potentially relevant for group classification. Mean reference values and 95% confidence intervals were calculated for left and right hippocampi along with hippocampal asymmetry degree to test diagnostic accuracy.Results: Both methods showed excellent classification performance (AUC:> 0.914) with noticeable differences in absolute (cm3) and normalized volumes. Hippocampal asymmetry was the most accurate discriminator from all estimates (AUC:1~0.97). Similar results were achieved in the validation test with an automatic classifier (AUC:>0.960), disclosing hippocampal structures as the most relevant features for group differentiation among other brain regions.Conclusion: We calculated reference volumetry values from two commonly used methods to accurately identify patients with temporal epilepsy and hippocampal sclerosis. Validation with an automatic classifier confirmed the principal role of the hippocampus and its subregions for diagnosis.

Mapping hippocampal glutamate in mesial temporal lobe epilepsy with glutamate weighted CEST (GluCEST) imaging

“…This is particularly relevant for future studies since as LITT becomes more common, less histopathological samples will be available, and therefore the definition of lesional and non‐lesional MTLe will have to be done exclusively based on MRI. Fortunately, past studies have established that hippocampal volumetry is an excellent predictor of hippocampal sclerosis (Bernasconi, 2006 ; Princich et al, 2021 ), therefore as we recruit more subjects for a larger GluCEST study, group assignments will likely be defined by hippocampal volumetry together with MRI lesional status. Future studies from our group aim at acquiring a larger sample size of MTLe‐L, MTLe‐NL and controls subjects in order to perform a well‐powered study where differences between these groups can be explored in both an ROI and voxel‐wise fashion without the need for asymmetry measurements.…”

“…This is particularly relevant for future studies since as LITT becomes more common, less histopathological samples will be available, and therefore the definition of lesional and non-lesional MTLe will have to be done exclusively based on MRI. Fortunately, past studies have established that hippocampal volumetry is an excellent predictor of hippocampal sclerosis (Bernasconi, 2006;Princich et al, 2021), therefore as we recruit more subjects for a larger GluCEST study, group assignments will likely be defined by hippocampal volumetry together with MRI lesional status.…”

“…In addition, we used quantitative evidence from hippocampal volumetry, to corroborate our lateralization and group assignments. Hippocampal volume has been shown to be an excellent predictor of hippocampal sclerosis (Bernasconi, 2006 ; Princich et al, 2021 ). In order of importance, we considered histopathology first.…”

Epilepsy in Pediatric Patients—Evaluation of Brain Structures’ Volume Using VolBrain Software

“…Based on the analysis, it was found that the volume of the hippocampus decreased in the course of TLE. Moreover, hippocampal volumes ipsilateral to the hippocampal sclerosis side were significantly reduced compared with controls and also with the non-lesional side [ 32 ]. Additionally, some patients with left exhibited ipsilateral hippocampal atrophy and segmental volume depletion of the cornu ammonis, dentate gyrus, and stratum radiatum-lacunosum-moleculare.…”

Glucose Metabolism of Hippocampal Subfields in Medial Temporal Lobe Epilepsy

“…It is important to consider that few previous studies have addressed HS-related atrophy at the subfield level; moreover, the results have been inconsistent. [24][25][26][27] Two recent studies have reported on the use of automated segmentation. One study reported significant reductions in the volume of the contralateral presubiculum in patients with left MTLE.…”