High-resolution segmentations of the hypothalamus and its subregions for training of segmentation models

TL;DR

This paper introduces HELM, a high-resolution ex vivo MRI dataset with detailed hypothalamus labels, aimed at improving automated segmentation models through synthetic data, thereby reducing reliance on manual annotations.

Contribution

The paper presents a new dataset with detailed hypothalamic label maps from ultra-high resolution MRI, enabling better training of segmentation models using synthetic data.

Findings

Dataset includes 10 ex vivo brain hemispheres with detailed labels.

Supports development of segmentation models with synthetic data.

Facilitates research on hypothalamus segmentation in neuroimaging.

Abstract

Segmentation of brain structures on magnetic resonance imaging (MRI) is a highly relevant neuroimaging topic, as it is a prerequisite for different analyses such as volumetry or shape analysis. Automated segmentation facilitates the study of brain structures in larger cohorts when compared with manual segmentation, which is time-consuming. However, the development of most automated methods relies on large and manually annotated datasets, which limits the generalizability of these methods. Recently, new techniques using synthetic images have emerged, reducing the need for manual annotation. Here we provide HELM, Hypothalamic ex vivo Label Maps, a dataset composed of label maps built from publicly available ultra-high resolution ex vivo MRI from 10 whole hemispheres, which can be used to develop segmentation methods using synthetic data. The label maps are obtained with a combination of manual labels for the hypothalamic regions and automated segmentations for the rest of the brain, and mirrored to simulate entire brains. We also provide the pre-processed ex vivo scans, as this dataset can support future projects to include other structures after these are manually segmented.