MTL subregion segmentation atlas with 7T and 3T multi-modality MRI

Volumetry of subregions in the medial temporal lobe (MTL) computed from automatic segmentation in MRI can track neurodegeneration in Alzheimer’s disease. However, image quality may vary in MRI. Poor-quality MR images can lead to unreliable segmentation of MTL subregions. Considering that different MRI contrast mechanisms and field strengths (jointly referred to as “modalities” here) offer distinct advantages in imaging different parts of the MTL, we developed a multi-modality segmentation model using both 7 tesla (7T) and 3 tesla (3T) structural MRI to obtain robust segmentation in poor-quality images. MRI modalities, including 3T T1-weighted, 3T T2-weighted, 7T T1-weighted, and 7T T2-weighted (7T-T2w) of 197 participants were collected from a longitudinal aging study at the Penn Alzheimer’s Disease Research Center. Among them, 7T-T2w was used as the primary modality, and all other modalities were rigidly registered to the 7T-T2w. A model derived from nnU-Net took these registered modal..., , , # Multi-modality atlas for medial temporal lobe subregion at 7T and 3T MRI

## Description of the data and file structure

This is a multi-modality dataset of medial temporal lobe in brain MRI for the paper about [multi-modality subregion segmentation model](https://doi.org/10.1002/hipo.70036). 7T-T2w, 7T-T1w, 3T-T2w, and 3T-T1w data are available at ROI level from 25 anonymized subjects.

This dataset is included in the zip file \"multi_modality_atlas.zip\", which contains four subfolders, each corresponding to a different step in the multi-modality segmentation pipeline. Below is a description of the subfolder structure and their contents:

1. **`multi_modality_training_atlas`**: Atlas raw data with nnUNet format. All subjects were anonymized by being given a fake nnunet ID. Two consecutive numbers (e.g., `001` and `002`, `017` and `018`, etc.) represent the left and right MTL ROIs, respectively, for the same subject. The primary modality is 7T-T2w (channel 0000), and the ROIs of the ot...,