Gadolinium contrast-enhanced lesion segmentation in multiple sclerosis: a deep-learning approach.
Motivation: Detection of contrast-enhanced lesions (CELs) is fundamental for the diagnosis and monitoring of Multiple Sclerosis (MS) patients. This task is time-consuming and variable in the clinical setting. However, only a few studies reported automatic approaches. Goal(s): To develop a deep-learning tool to automatically detect and segment CELs in clinical MRI scans from MS patients. Approach: We implemented a UNet-based network with an adapted sampling strategy to overcome the scarcity of CELs. We considered the data imbalance to weight the training loss function. Results: The model performance was evaluated for different lesion-volume ranges and achieved high performance even in low-volume lesions. Impact: We developed a deep-learning method fulfilling clinical needs in detecting and segmenting lesions characterized by low volume, low numbers per patient and heterogeneous shapes.
Authors
- Nina de Oliveira S. Siebenborn
- Emanuele Pravatà (ORCID: https://orcid.org/0000-0002-5225-2993)
- Franca Wagner (ORCID: https://orcid.org/0000-0001-7502-4814)
- Riccardo Galbusera (ORCID: https://orcid.org/0000-0002-3092-8737)
- Luca Remonda (ORCID: https://orcid.org/0000-0003-3140-9135)
- Claire Bridel (ORCID: https://orcid.org/0000-0001-7267-7676)
- María Isabel Vargas (ORCID: https://orcid.org/0000-0002-6571-5336)
- Andrew Lung-Tat Chan (ORCID: https://orcid.org/0000-0003-3434-7283)
- Patrice H. Lalive (ORCID: https://orcid.org/0000-0003-0607-5778)
- Lutz Achtnichts
- Alessandro Cagol (ORCID: https://orcid.org/0000-0002-7703-0553)
- Anke Salmen (ORCID: https://orcid.org/0000-0002-4751-299X)
- Claudio Gobbi (ORCID: https://orcid.org/0000-0002-7554-0664)
- Jens Kühle (ORCID: https://orcid.org/0000-0002-6963-8892)
- Po‐Jui Lu (ORCID: https://orcid.org/0000-0001-6031-6865)
- Ludwig Kappos (ORCID: https://orcid.org/0000-0003-4175-5509)
- Matthias Weigel (ORCID: https://orcid.org/0000-0002-4910-1414)
- Giulio Disanto (ORCID: https://orcid.org/0000-0002-8512-6096)
- Esther Ruberte (ORCID: https://orcid.org/0000-0002-0195-4602)
- Chiara Zecca (ORCID: https://orcid.org/0000-0002-9990-3431)
- Johannes Weber (ORCID: https://orcid.org/0000-0002-6106-3916)
- Renaud Du Pasquier (ORCID: https://orcid.org/0000-0002-2786-3434)
- David Leppert (ORCID: https://orcid.org/0000-0001-6172-801X)
- Pascal Benkert (ORCID: https://orcid.org/0000-0001-6525-8174)
- Caroline Pot (ORCID: https://orcid.org/0000-0002-1146-3129)
- Oliver Findling (ORCID: https://orcid.org/0000-0003-4298-4370)
- Mario Ocampo‐Pineda (ORCID: https://orcid.org/0000-0003-2239-7355)
- Jochen Vehoff (ORCID: https://orcid.org/0000-0001-9531-8262)
- Cristina Granziera (ORCID: https://orcid.org/0000-0002-4917-8761)
- Johanna Lieb (ORCID: https://orcid.org/0000-0003-0821-3257)
- Lester Melie‐García (ORCID: https://orcid.org/0000-0001-5602-8916)
- Tobias Derfuss (ORCID: https://orcid.org/0000-0001-8431-8769)
- Martina Greselin (ORCID: https://orcid.org/0009-0002-9398-5306)
- Stefanie Müller
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
- 2024-11-26
- DOI
- https://doi.org/10.58530/2024/4850
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00