Deep-PRL: a deep learning network for the identification of paramagnetic rim lesions in multiple sclerosis
Motivation: PRLs are an important diagnostic biomarker in people with multiple sclerosis (pwMS). Their identification on MRI is time-consuming and subject to high inter-rater variability. However, the use of AI could support this identification process. Goal(s): We leverage multi-contrast MRI to improve the identification of PRLs. Approach: Deep-PRL is an attention-based CNN, fusing features of T1-w and unwrapped phase images from 185 pwMS. The approach consists in a nested cross-validation with patient stratification. Results: The test performance outperformed state-of-the-art methods, achieving a mean F1 score of 0.860 ± 0.048 and an AUC of 0.982 ± 0.007. Impact: These results represent a significant step towards the integration of an AI tool to assist clinicians in the identification of PRLs, thereby improving the clinical management of pwMS.
Authors
- Vincent Andrearczyk (ORCID: https://orcid.org/0000-0003-0793-5821)
- Federico Spagnolo (ORCID: https://orcid.org/0000-0001-9606-0400)
- Alessandro Cagol (ORCID: https://orcid.org/0000-0002-7703-0553)
- Pedro M. Gordaliza (ORCID: https://orcid.org/0000-0001-5305-3104)
- Adrien Depeursinge (ORCID: https://orcid.org/0000-0002-2362-0304)
- Meritxell Bach Cuadra (ORCID: https://orcid.org/0000-0003-2730-4285)
- Po‐Jui Lu (ORCID: https://orcid.org/0000-0001-6031-6865)
- Ashutosh Bhardwaj (ORCID: https://orcid.org/0000-0002-7544-3258)
- Mario Ocampo‐Pineda (ORCID: https://orcid.org/0000-0003-2239-7355)
- Cristina Granziera (ORCID: https://orcid.org/0000-0002-4917-8761)
- Xinjie Chen (ORCID: https://orcid.org/0009-0009-7031-9985)
- Batuhan Ayci (ORCID: https://orcid.org/0000-0003-3418-7822)
Publication Details
- Journal
- Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition
- Published
- 2025-09-16
- DOI
- https://doi.org/10.58530/2025/1300
- Primary Topic
- Microbial infections and disease research
- Type
- article
- Field-Weighted Citation Impact
- 0.00