Diagnostic accuracy of deep learning vs. human raters for detecting osteoporotic vertebral compression fractures in routine CT scans
Question Can dedicated deep learning-based algorithms improve diagnostic performance for accurate detection and grading of osteoporotic vertebral fractures on CT scans? Findings Deep learning models specifically trained for vertebral fracture detection and grading can reach comparable performance as experts for the identification and grading of osteoporotic fractures. Clinical relevance Specifically trained deep learning models represent a valuable advancement for improving the identification and grading of osteoporotic fractures in clinical practice, bringing these tools a significant step closer to routine clinical implementation.
Authors
- Nico Sollmann (ORCID: https://orcid.org/0000-0002-8120-2223)
- David Schinz (ORCID: https://orcid.org/0000-0003-3734-1135)
- Michael Dieckmeyer (ORCID: https://orcid.org/0000-0002-8349-4813)
- Malek El Husseini (ORCID: https://orcid.org/0000-0002-2952-3708)
- Thomas Baum
- Sebastian Rühling (ORCID: https://orcid.org/0000-0002-9518-7810)
- Maximilian T. Löffler (ORCID: https://orcid.org/0000-0002-6022-3682)
- Matthias Keicher (ORCID: https://orcid.org/0000-0003-2037-6796)
- Evamaria Olga Riedel
- Arthur Wagner
- Jan S. Kirschke
- Isabel Seeger
- Benedikt Wiestler
- Luca Malagutti
- Anna S. Walburga
Institutions
- University of Bern (CH)
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- University Hospital of Bern (CH)
- University Medical Center Freiburg (DE)
- TUM Klinikum (DE)
- Universitätsklinikum Erlangen (DE)
- Translational Research in Oncology (FR)
- University Hospital Ulm (DE)
- Technical University of Munich (DE)
Publication Details
- Journal
- European Radiology
- Published
- 2026-02-24
- DOI
- https://doi.org/10.1007/s00330-026-12393-y
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Bayerische Staatsministerium für Wirtschaft, Landesentwicklung und Energie