Automated hippocampal segmentation in patients with epilepsy: available free online

Abstract

Purpose: Hippocampal sclerosis, a common cause of refractory focal epilepsy, requires hippocampal volumetry for accurate diagnosis and surgical planning. Manual segmentation is time-consuming and subject to interrater/intrarater variability. Automated algorithms perform poorly in patients with temporal lobe epilepsy. We validate and make freely available online a novel automated method.

Methods: Manual hippocampal segmentation was performed on 876, 3T MRI scans and 202, 1.5T scans. A template database of 400 high-quality manual segmentations was used to perform automated segmentation of all scans with a multi-atlas-based segmentation propagation method adapted to perform label fusion based on local similarity to ensure accurate segmentation regardless of pathology. Agreement between manual and automated segmentations was assessed by degree of overlap (Dice coefficient) and comparison of hippocampal volumes.

Key findings: The automated segmentation algorithm provided robust delineation of the hippocampi on 3T scans with no more variability than that seen between different human raters (Dice coefficients: interrater 0.832, manual vs. automated 0.847). In addition, the algorithm provided excellent results with the 1.5T scans (Dice coefficient 0.827), and automated segmentation remained accurate even in small sclerotic hippocampi. There was a strong correlation between manual and automated hippocampal volumes (Pearson correlation coefficient 0.929 on the left and 0.941 on the right in 3T scans).

Significance: We demonstrate reliable identification of hippocampal atrophy in patients with hippocampal sclerosis, which is crucial for clinical management of epilepsy, particularly if surgical treatment is being contemplated. We provide a free online Web-based service to enable hippocampal volumetry to be available globally, with consequent greatly improved evaluation of those with epilepsy.

Keywords: Epilepsy surgery; Hippocampal sclerosis; Hippocampal segmentation; Magnetic resonance imaging.

Figure 1

Automated hippocampal segmentation algorithm. The templates that are the most similar to the new image are selected from the template database and fused to produce the new segmentation.

Figure 2

Manual and automated hippocampal volumes on 3T scans. There is good agreement between the volumes for both the left and right hippocampi.

Figure 3

Bland-Altman plots for manual and automated hippocampal volumes on 3T scans. There is no evidence of bias between the methods for both the left and right hippocampi.

Figure 4

Corrected volumes and asymmetry for subjects in the template database. Scatterplot of sum of left and right hippocampal volumes versus difference between these volumes (corrected for intracranial volume) divided into groups by the prior clinical classification.