Joint segmentation of multiple sclerosis lesions and brain anatomy in mri scans of any contrast and resolution with CNNs

Benjamin Billot, Stefano Cerri, Koen Van Leemput, Adrian V. Dalca, Juan Eugenio Iglesias

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

We present the first deep learning method to segment Multiple Sclerosis lesions and brain structures from MRI scans of any (possibly multimodal) contrast and resolution. Our method only requires segmentations to be trained (no images), as it leverages the generative model of Bayesian segmentation to generate synthetic scans with simulated lesions, which are then used to train a CNN. Our method can be retrained to segment at any resolution by adjusting the amount of synthesised partial volume. By construction, the synthetic scans are perfectly aligned with their labels, which enables training with noisy labels obtained with automatic methods. The training data are generated on the fly, and aggressive augmentation (including artefacts) is applied for improved generalisation. We demonstrate our method on two public datasets, comparing it with a state-of-the-art Bayesian approach implemented in FreeSurfer, and dataset specific CNNs trained on real data. The code is available at https://github.com/BBillot/SynthSeg.

Original languageEnglish
Title of host publicationProceedings of the 18th International Symposium on Biomedical Imaging
PublisherIEEE
Publication date2021
Pages1971-1974
ISBN (Electronic)978-1-6654-1246-9
DOIs
Publication statusPublished - 2021
Event2021 IEEE 18th International Symposium on Biomedical Imaging - Virtual, Nice, France
Duration: 13 Apr 202116 Apr 2021
Conference number: 18
https://biomedicalimaging.org/2021/

Conference

Conference2021 IEEE 18th International Symposium on Biomedical Imaging
Number18
LocationVirtual
Country/TerritoryFrance
CityNice
Period13/04/202116/04/2021
Internet address
SeriesProceedings - International Symposium on Biomedical Imaging
ISSN1945-7928

Bibliographical note

Funding Information:
Supported by the EU (ERC Starting Grant 677697, Marie Curie 765148), the EPSRC (EP-L016478/1), and the NIH (1RF1MH123195-01, 1R01AG0-64027-01A1, R01NS112161).

Fingerprint

Dive into the research topics of 'Joint segmentation of multiple sclerosis lesions and brain anatomy in mri scans of any contrast and resolution with CNNs'. Together they form a unique fingerprint.

Cite this