Welcome to the official repository for CRL2025: MRI Atlas of the Human Fetal Brain: Reference and Segmentation Tools for Fetal Brain MRI Analysis This repository contains the source code and test data used in our study
Accurate characterization of in-utero brain development is essential for understanding typical and atypical neurodevelopment. Building upon previous efforts to construct spatiotemporal fetal brain MRI atlases, we present the CRL-2025 fetal brain atlas, which is a spatiotemporal (4D) atlas of the developing fetal brain between 21 and 37 gestational weeks. This atlas is constructed from carefully processed MRI scans of 160 healthy fetuses using a temporally consistent diffeomorphic registration framework integrated with kernel regression in age. CRL-2025 uniquely includes detailed tissue segmentations, transient white matter compartments, and parcellation into 124 anatomical regions. This atlas offers significantly enhanced anatomical details over the CRL-2017 atlas, and is released along with the CRL diffusion MRI atlas with its newly created tissue segmentation and labels as well as deep-learning based multiclass segmentation models for fine-grained fetal brain MRI segmentation. The CRL-2025 atlas and its associated tools provide a robust and scalable platform for fetal brain MRI segmentation, groupwise analysis, and early neurodevelopmental research, and are publicly released to support the broader research community.
The overall schematic of the proposed model is as follows:
The pretrained models, datasets and all the nessacry materials used in our paper are available at:
If you find the article or code helpful, please cite the journal version of our paper: