Software: Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE
Creators
- 1. Signal Processing Laboratory (LTS5), École Polytechnique Fédérale de Lausanne, Switzerland
- 2. University Hospital of Old Age Psychiatry and Psychotherapy, University of Bern, Bern, Switzerland
- 3. Translational Imaging in Neurology Basel, Department of Medicine and Biomedical Engineering, University Hospital Basel and University of Basel, Basel, Switzerland
- 4. Department of Radiology, Lausanne University Hospital and University of Lausanne, Switzerland
Description
This page presents the software and a trained model relative to the paper "Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE." NeuroImage: Clinical (2020).
The software presented on this page is for research purposes only.
Given as input the registered FLAIR and MP2RAGE Magnetic Resonance Imaging scans of Multiple Sclerosis patients, the software estimates the lesion segmentation (including both white matter and cortical lesions). For further information about its usage please read the README.txt file within the upload or contact the authors (francesco.larosa@epfl.ch).
This software depends on the NiftyNet framework (https://niftynet.readthedocs.io/) and it is based on Tensorflow (https://www.tensorflow.org/). A GPU is required to train the network with new data.
The software presented on this page is for research purposes only.
People using in part or fully this software should cite:
1) Gibson, Eli, et al. "NiftyNet: a deep-learning platform for medical imaging." Computer methods and programs in biomedicine 158 (2018): 113-122.
2) La Rosa, Francesco, et al. "Multiple sclerosis cortical and WM lesion segmentation at 3TMRI: a deep learning method based on FLAIR and MP2RAGE." NeuroImage: Clinical (2020): 102335.
3) F. La Rosa, A. Abdulkadir, J.-Ph. Thiran, C. Granziera, M. Bach Cuadra, Software: Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE (Version v1.0), 2020, Zenodo. http://doi.org/10.5281/zenodo.3932835
Files
FrancescoLR/MS-lesion-segmentation-v1.0.zip
Files
(55.5 MB)
| Name | Size | Download all |
|---|---|---|
|
md5:2698abe0cddaf9b6eea19389f42e4351
|
55.5 MB | Preview Download |
Additional details
Related works
- Is identical to
- Software: https://github.com/FrancescoLR/MS-lesion-segmentation/tree/v1.0 (URL)
- Is supplement to
- Journal article: 10.1016/j.nicl.2020.102335 (DOI)
Funding
- TRABIT – Translational Brain Imaging Training Network 765148
- European Commission
- MRI-based pattern recognition techniques in dementia diagnostics 320030-173880
- Swiss National Science Foundation
- INsIDER: ImagiNg the Interplay between Axonal DamagE and Repair in Multiple Sclerosis PP00P3_176984
- Swiss National Science Foundation
References
- Gibson, E., Li, W., Sudre, C., Fidon, L., Shakir, D. I., Wang, G., ... & Whyntie, T. (2018). NiftyNet: a deep-learning platform for medical imaging. Computer methods and programs in biomedicine, 158, 113-122.
- La Rosa, F., Abdulkadir, A., Fartaria, M. J., Rahmanzadeh, R., Lu, P. J., Galbusera, R., ... & Cuadra, M. B. (2020). Multiple sclerosis cortical and WM lesion segmentation at 3T MRI: a deep learning method based on FLAIR and MP2RAGE. NeuroImage: Clinical, 102335.