Automated vertebrae identification and segmentation with structural uncertainty analysis in longitudinal CT scans of patients with multiple myeloma
The proposed pipeline significantly outperforms Payer's method, enhancing segmentation accuracy and reducing longitudinal matching errors while minimizing evaluation workload. Its uncertainty analysis ensures robust performance, making it a valuable tool for longitudinal studies in multiple myeloma.
Authors
- Bart de Keizer (ORCID: https://orcid.org/0000-0002-6270-9483)
- Jorrit‐Jan Verlaan (ORCID: https://orcid.org/0000-0001-8105-6660)
- Kenneth G. A. Gilhuijs (ORCID: https://orcid.org/0000-0003-2087-8649)
- Monique C. Minnema (ORCID: https://orcid.org/0000-0002-3139-8379)
- Margot Jak (ORCID: https://orcid.org/0000-0001-8092-3566)
- Djennifer K Madzia-Madzou
Institutions
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- University Medical Center Utrecht (NL)
Publication Details
- Journal
- European Journal of Radiology
- Published
- 2025-05-03
- DOI
- https://doi.org/10.1016/j.ejrad.2025.112160
- Citations
- 1
- Primary Topic
- Medical Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.67
Funders
- Hanarth Fonds