Evaluation of a deep learning segmentation tool to help detect spinal cord lesions from combined T2 and STIR acquisitions in people with multiple sclerosis
Question No tool to help detect MS SC lesions is used in clinical practice despite their frequency and prognostic value. Findings This DL-based tool led to improvement in clinicians' sensitivity in detecting SC lesions from both sagittal T2 and STIR sequences, without decreasing precision. Clinical relevance Our study indicated the potential of a DL-based tool to assist clinicians in the challenging task of detecting SC lesions in people with MS on a combination of sequences commonly acquired in clinical practice.
Authors
- François Cotton (ORCID: https://orcid.org/0000-0003-0046-2478)
- Baptiste Lodé
- Adil Maarouf (ORCID: https://orcid.org/0000-0002-6755-496X)
- Frédérique Charbonneau (ORCID: https://orcid.org/0000-0002-3696-0834)
- Bertrand Bourre (ORCID: https://orcid.org/0000-0002-2459-2480)
- Clément Mehier (ORCID: https://orcid.org/0000-0002-4793-9299)
- Burhan Rashid Hussein (ORCID: https://orcid.org/0000-0002-9683-8689)
- Augustin Lecler (ORCID: https://orcid.org/0000-0001-7869-1815)
- Loïc Duron (ORCID: https://orcid.org/0000-0002-4279-1176)
- Romain Casey (ORCID: https://orcid.org/0000-0002-5918-9261)
- Alexandre Bani‐Sadr (ORCID: https://orcid.org/0000-0002-1808-2484)
- Anne Kerbrat (ORCID: https://orcid.org/0000-0002-4530-3553)
- Benoît Combès (ORCID: https://orcid.org/0000-0003-4161-7093)
- Camille Cathelineau
- Cédric Meurée
- Allan R. Martin (ORCID: https://orcid.org/0000-0002-9495-5654)
- A Poulin
- Jenn-Jye Hong
- Gilles Edan (ORCID: https://orcid.org/0000-0002-9641-6734)
- Ricky Walsh (ORCID: https://orcid.org/0000-0002-2363-5506)
- Nicolas Lassalle
- Guilhem Courbon
- Olivier Outteryck (ORCID: https://orcid.org/0000-0003-3197-373X)
- Jean-Christophe Ferré
- Céline Delpierre
- Françoise Durand-Dubief
- Malo Gaubert
- Guillaume Criton
- Jeanne Le Bars
- Sophie Motillon-Alonso
- Francesca Galassi (ORCID: https://orcid.org/0000-0002-8788-2856)
Institutions
- Université Claude Bernard Lyon 1 (FR)
- École Normale Supérieure de Lyon (FR)
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Lyon College (US)
- Université de Lyon (FR)
- Université Paris Cité (FR)
- Aix-Marseille Université (FR)
- Université de Lille (FR)
- Institut de Recherche en Informatique et Systèmes Aléatoires (FR)
- Centre Hospitalier Universitaire de Lille (FR)
- Hospices Civils de Lyon (FR)
- Hôpital Pierre Wertheimer (FR)
- CIC Rennes (FR)
- Fondation Ophtalmologique Adolphe de Rothschild (FR)
- Centre de Recherche en Acquisition et Traitement de l'Image pour la Santé (FR)
- Centre Hospitalier Universitaire de Rouen (FR)
- Centre Hospitalier Universitaire de Rennes (FR)
- Hôpital de la Timone (FR)
- Université de Rennes (FR)
- Université de Rouen Normandie (FR)
Publication Details
- Journal
- European Radiology
- Published
- 2025-04-04
- DOI
- https://doi.org/10.1007/s00330-025-11541-0
- Primary Topic
- Multiple Sclerosis Research Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Agence Nationale de la Recherche
- Centre Hospitalier Universitaire de Rennes