# Intensity-Based Assessment of Hippocampal Segmentation Algorithms Using Paired Precontrast and Postcontrast MRI

## TL;DR

This paper introduces a new method to assess hippocampal segmentation accuracy using MRI intensity data, showing that some algorithms perform better than others.

## Contribution

A novel intensity-based method for evaluating hippocampal segmentation accuracy using precontrast and postcontrast MRI data.

## Key findings

- HippMapp3r and e2dhipseg showed the least correction volume, indicating higher accuracy.
- Dedicated hippocampal algorithms outperformed whole-brain segmentation methods.
- Current methods using virtual or manual labels fail to capture segmentation inaccuracies.

## Abstract

Hippocampal segmentation is essential in neuroimaging for evaluating conditions like Alzheimer’s dementia and mesial temporal sclerosis, where small volume changes can significantly impact normative percentiles. However, inaccurate segmentation is common due to the inclusion of non-hippocampal structures such as choroid plexus and cerebrospinal fluid (CSF), leading to volumetric overestimation and confounding of functional analyses. Current methods of assessment largely rely on virtual or manual ground truth labels, which can fail to capture these inaccuracies. To address this shortcoming, this study introduces a more direct voxel intensity-based method of segmentation assessment. Using paired precontrast and postcontrast T1-weighted MRIs, hippocampal segmentations were refined by adding marginal gray matter and removing marginal CSF and enhancement to determine a total required correction volume. Six segmentation algorithms—e2dhipseg, HippMapp3r, hippodeep, AssemblyNet, FastSurfer, and QuickNat—were implemented and compared. HippMapp3r and e2dhipseg, followed closely by hippodeep, exhibited the least total correction volumes, indicating superior accuracy. Dedicated hippocampal segmentation algorithms outperformed whole-brain methods.