A Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis Derived From Deep Learning-Based Segmentation of T1w-MRI

Abstract

PurposeHippocampal volumetry is an important biomarker to quantify atrophy in patients with mesial temporal lobe epilepsy. We investigate the sensitivity of automated segmentation methods to support radiological assessments of hippocampal sclerosis (HS). Results from FreeSurfer and FSL-FIRST are contrasted to a deep learning (DL)-based segmentation method.Materials and MethodsWe used T1-weighted MRI scans from 105 patients with epilepsy and 354 healthy controls. FreeSurfer, FSL, and a DL-based method were applied for brain anatomy segmentation. We calculated effect sizes (Cohen's d) between left/right HS and healthy controls based on the asymmetry of hippocampal volumes. Additionally, we derived 14 shape features from the segmentations and determined the most discriminating feature to identify patients with hippocampal sclerosis by a support vector machine (SVM).ResultsDeep learning-based segmentation of the hippocampus was the most sensitive to detecting HS. The effect sizes of the volume asymmetries were larger with the DL-based segmentations (HS left d= −4.2, right = 4.2) than with FreeSurfer (left= −3.1, right = 3.7) and FSL (left= −2.3, right = 2.5). For the classification based on the shape features, the surface-to-volume ratio was identified as the most important feature. Its absolute asymmetry yielded a higher area under the curve (AUC) for the deep learning-based segmentation (AUC = 0.87) than for FreeSurfer (0.85) and FSL (0.78) to dichotomize HS from other epilepsy cases. The robustness estimated from repeated scans was statistically significantly higher with DL than all other methods.ConclusionOur findings suggest that deep learning-based segmentation methods yield a higher sensitivity to quantify hippocampal sclerosis than atlas-based methods and derived shape features are more robust. We propose an increased asymmetry in the surface-to-volume ratio of the hippocampus as an easy-to-interpret quantitative imaging biomarker for HS.

Reliable brain morphometry from contrast‐enhanced T1w‐MRI in patients with multiple sclerosis

“…Our findings of smaller error bars when using DL+-DiReCT instead of FreeSurfer together with larger group separation capabilities strongly suggest DL-based input for SCN estimation as an alternative. Enhanced robustness of DL+DiReCT compared to Free-Surfer has been reported before (Rebsamen et al, 2020(Rebsamen et al, , 2022Rusak et al, 2022). SCN analysis revealed clear separation between the two subgroups of MS, with DL+DiReCT from both non-enhanced and CE images.…”

Distinct and shared patterns of brain plasticity during electroconvulsive therapy and treatment as usual in depression: an observational multimodal MRI-study

“…The method was validated with a large cohort and shows similar robustness (test-retest reliability) than FreeSurfer [ 44 ]. However, DL + DiReCT was more sensitive than FreeSurfer to detect changes in cortical thickness related to age [ 44 ], dementia [ 44 ] and multiple sclerosis [ 46 ] and to identify hippocampal sclerosis in epilepsy [ 47 ]. For both hemispheres, DL + DiReCT was used to extract global mean cortical thickness, and mean thickness of bilateral insulae, caudal ACC and medial and lateral OFC.…”

Hippocampal volume in patients with bilateral and unilateral peripheral vestibular dysfunction

“…Hippocampal subfields were segmented using a dedicated module ( Iglesias et al, 2015 ) of the FreeSurfer pipeline. Additionally, the images were processed using DL + DiReCT ( Rebsamen et al, 2020 , Rebsamen et al, 2022 ), from which 16 shape features of the hippocampi were derived using pyradiomics ( van Griethuysen et al, 2017 ). With a data-driven approach, we investigated the discriminatory power of these features to classify patients with vestibular dysfunction and its subgroup from healthy controls using a machine-learning classifier.…”