Clinical validation of automated hippocampal segmentation in temporal lobe epilepsy

Abstract

ObjectiveTo provide a multi-atlas framework for automated hippocampus segmentation in temporal lobe epilepsy (TLE) and clinically validate the results with respect to surgical lateralization and post-surgical outcome.MethodsWe retrospectively identified 47 TLE patients who underwent surgical resection and 12 healthy controls. T1-weighted 3 T MRI scans were acquired for all subjects, and patients were identified by a neuroradiologist with regards to lateralization and degree of hippocampal sclerosis (HS). Automated segmentation was implemented through the Joint Label Fusion/Corrective Learning (JLF/CL) method. Gold standard lateralization was determined from the surgically resected side in Engel I (seizure-free) patients at the two-year timepoint. ROC curves were used to identify appropriate thresholds for hippocampal asymmetry ratios, which were then used to analyze JLF/CL lateralization.ResultsThe optimal template atlas based on subject images with varying appearances, from normal-appearing to severe HS, was demonstrated to be composed entirely of normal-appearing subjects, with good agreement between automated and manual segmentations. In applying this atlas to 26 surgically resected seizure-free patients at a two-year timepoint, JLF/CL lateralized seizure onset 92% of the time. In comparison, neuroradiology reads lateralized 65% of patients, but correctly lateralized seizure onset in these patients 100% of the time. When compared to lateralized neuroradiology reads, JLF/CL was in agreement and correctly lateralized all 17 patients. When compared to nonlateralized radiology reads, JLF/CL correctly lateralized 78% of the nine patients.SignificanceWhile a neuroradiologist's interpretation of MR imaging is a key, albeit imperfect, diagnostic tool for seizure localization in medically-refractory TLE patients, automated hippocampal segmentation may provide more efficient and accurate epileptic foci localization. These promising findings demonstrate the clinical utility of automated segmentation in the TLE MR imaging pipeline prior to surgical resection, and suggest that further investigation into JLF/CL-assisted MRI reading could improve clinical outcomes. Our JLF/CL software is publicly available at https://www.nitrc.org/projects/ashs/.

Loss of hippocampal dentation in hippocampal sclerosis and its relationship to memory dysfunction

“…T1w source images were converted to NIfTI format and interpolated up to .25‐mm isotropic resolution. They were then processed using the ASHS software package 34 with the Penn Temporal Lobe Epilepsy T1‐MRI Whole Hippocampus ASHS Atlas 35 to generate ultra‐high‐resolution hippocampal segmentations. Segmentation in the superresolution space captures surface contours that are encoded in the grayscale data of the native resolution images but not visible in native resolution segmentations 29 .…”

Volumetric glutamate imaging (GluCEST) using 7T MRI can lateralize nonlesional temporal lobe epilepsy: A preliminary study

“…7T MPRAGE images from all four patients were linearly registered to the respective CEST maps using Advanced Normalization Tools (ANTs) (Avants, Tustison, Song, et al., 2011). ASHS segmentation (an automated technique for segmenting hippocampal subfields and extra‐hippocampal medial temporal cortices from high‐resolution T2w‐MRI at 7T MRI) was then performed on 7T oblique coronal T2‐weighted imaging acquired perpendicular to the long axis of the hippocampus which resulted in segmentations of bilateral subfields of the hippocampi (Hadar et al., 2018; Shah et al., 2018). The segmentation included subiculum, Cornu Ammonis (CA) 1, 2, and 3 and dentate gyrus (DG).…”

“…CA2 and CA3 were not included in the primary analyses because of the lower reliability of these regions, as opposed to the more reliable CA1, DG, and subiculum; this has been previously noted in the ASHS technique and is thought to be potentially due to inherent error and sampling issues involved in gross geometrical approximations of cellular transitions (Schoene‐Bake et al., 2014; Wisse et al., 2016). Overall, ASHS has been both pathologically and clinically validated (Hadar et al., 2018; Wisse et al., 2016). Supplementary analysis of the volumes was conducted on all hippocampal subfields.…”

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

“…More recent work based on nonconventional contrasts, including diffusion 29 and network parameters, [30][31][32] has targeted whole-brain anomalies in patients with MRI-positive TLE. Only 2 previous studies have addressed the lateralization challenge in both MRI-positive and MRI-negative TLE, 33,34 operating on T1-derived volumetry with groups predefined by side and visibility of hippocampal atrophy on MRI. In 1 study, 33 besides the lack of histopathologic confirmation, anatomic structures identifying TLE groups were mainly outside the mesiotemporal lobe, different across groups, and difficult to interpret, particularly in MRI-negative patients.…”