Metadata Quality in Imaging Trials: A Knowledge Graph-Based Approach
We present a method for transforming DICOM metadata into a knowledge graph for advanced analytics. This allows metadata quality assessment in imaging trials through custom metrics, e.g., regarding attribute completeness. Our results are of practical use for automated quality checks for multifaceted trials.
Authors
- Dagmar Krefting (ORCID: https://orcid.org/0000-0002-7238-5339)
- Heiko Tzschätzsch (ORCID: https://orcid.org/0000-0001-9458-2221)
- Felix Balzer (ORCID: https://orcid.org/0000-0003-1575-2056)
- Elias Grünewald (ORCID: https://orcid.org/0000-0001-9076-9240)
- Marc Dewey (ORCID: https://orcid.org/0000-0002-4402-2733)
- Friederike Seyderhelm (ORCID: https://orcid.org/0009-0007-6972-3759)
- Tim Kilgus (ORCID: https://orcid.org/0009-0002-2908-8272)
- Alaa Bejaoui (ORCID: https://orcid.org/0009-0003-5824-0218)
Institutions
- Universitätsmedizin Göttingen (DE)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- Studies in health technology and informatics
- Published
- 2025-05-15
- DOI
- https://doi.org/10.3233/shti250408
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Deutsche Forschungsgemeinschaft