This repository contains the pipelines for MONAI-based automated analysis for 7T neonatal brain MRI.
-
The repository, scripts and DL models were designed and created at the Department of Early Life Imaging, King's College London.
-
Please email alena.uus (at) kcl.ac.uk if in case of any questions.
Development of these analysis tools was supported by projects led by Prof Mary Rutherford, Prof Tomoki Arichi, Prof Jonathan O’Muircheartaigh, Prof Shaihan Malik and Prof Jo Hajnal.
The automated docker tags are fetalsvrtk/svrtk:7t_brain_analysis_amd (AMD systems only)
AUTOMATED 3D T2w BRAIN SEGMENTATION:
Input data requirements:
- sufficient SNR and image quality, no extreme shading artifacts
- good quality 3D SVR
- full ROI coverage
- standard radiological space
- 25-45 weeks PMA
- no extreme structural anomalies
- 7T
Note: you will need >16GB GPU
docker pull fetalsvrtk/svrtk:7t_brain_analysis
#auto multi-ROI brain tissue and internal capsule segmentation
docker run --rm --gpus all --mount type=bind,source=LOCATION_ON_YOUR_MACHINE,target=/home/data fetalsvrtk/svrtk:7t_brain_analysis_amd sh -c ' bash /home/7t-brain-analysis/scripts/run-7t-neo-brain-segmentation-internal-capsule-multi-bounti-042026.sh /home/data/[path_to_t2w_recon.nii.gz] /home/data/[path_to_tmp_processing_folder] /home/data/[path_to_output_multi_tissue_label.nii.gz] /home/data/[path_to_output_ic_wm_label.nii.gz] ; '
The 7t-brain-analysis code and all scripts are distributed under the terms of the GNU General Public License v3.0. This program is free software: you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation version 3 of the License.
This software is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
In case you found this repository useful please give appropriate credit to the software.
Internal capsule segmentation (will be updated soon):
Casella, C., Uus, A., Dedominicis, L., Willers Moore, J., Clayden, B., Galanides, E., Bridgen, P., Di Cio, P., Tomazinho, I., Da Costa, C., Gallo, D., Arulkumaran, S., Deprez, M., Counsell, S. J., Hajnal, J. V., O’Muircheartaigh, J., Rutherford, M. A., Malik, S., Arichi, T. (2026) Automated assessment of neonatal internal capsule maturation on T2-weighted MRI across 7T and 3T. medRxiv; doi: https://doi.org/****
Multi-regional brain tissue segmentation:
Uus, A., Fukami-Gartner, A., Kyriakopoulou, V., Cromb, D., Morgan, T., Arulkumaran, S., Egloff Collado, A., Luis, A., Bos, R., Makropoulos, A., Schuh, A., Robinson, E., Sousa, H., Deprez, M., Cordero-Grande, L., Bradshaw, C., Colford, K., Hutter, J., Price, A., O’Muircheartaigh, J., Hammers, A., Rueckert, D., Counsell, S., McAlonan, G., Arichi, T., Edwards, A. D., Hajnal, J. V., Rutherford, M. A., Story, L. (2026). Multi-BOUNTI: Multi-lobe Brain vOlUmetry and segmeNtation for feTal and neonatal MRI. medRxiv, 2026.04.21.26351376. https://doi.org/10.64898/2026.04.21.26351376
This software has been developed for research purposes only, and hence should not be used as a diagnostic tool. In no event shall the authors or distributors be liable to any direct, indirect, special, incidental, or consequential damages arising of the use of this software, its documentation, or any derivatives thereof, even if the authors have been advised of the possibility of such damage.