AI-based lumbar central canal stenosis classification on sagittal MR images is comparable to experienced radiologists using axial images
Question How can the classification of lumbar central canal stenosis (LCCS) be made more efficient? Findings Multiclass and binary AI models, using only sagittal MR images, performed on par with experienced radiologists who also had access to axial sequences. Clinical relevance Our AI algorithm accurately classifies LCCS from sagittal MRI, matching experienced radiologists. This study offers a promising tool for automated LCCS assessment from sagittal T2 MRI, potentially reducing the reliance on additional axial imaging.
Authors
- Marinus de Kleuver (ORCID: https://orcid.org/0000-0002-3506-1212)
- Miranda L. van Hooff (ORCID: https://orcid.org/0000-0001-5313-6436)
- Matthieu Rutten
- Myrthe Vestering (ORCID: https://orcid.org/0009-0000-9931-4306)
- Bram van Ginneken (ORCID: https://orcid.org/0000-0003-2028-8972)
- Nikolas Leßmann (ORCID: https://orcid.org/0000-0001-7935-9611)
- Jasper W. van der Graaf (ORCID: https://orcid.org/0000-0001-8684-5175)
- Jacco Spermon
- Bas Maresch (ORCID: https://orcid.org/0000-0003-0410-7967)
- Liron Brundel
Institutions
- Radboud University Nijmegen (NL)
- Radboud University Medical Center (NL)
- Radboud Institute for Molecular Life Sciences (NL)
- Ziekenhuis Gelderse Vallei (NL)
- Sint Maartenskliniek (NL)
- Jeroen Bosch Ziekenhuis (NL)
Publication Details
- Journal
- European Radiology
- Published
- 2024-09-20
- DOI
- https://doi.org/10.1007/s00330-024-11080-0
- Citations
- 5
- Primary Topic
- Spine and Intervertebral Disc Pathology
- Type
- article
- Field-Weighted Citation Impact
- 2.12