Automatic structuring of radiology reports with on-premise open-source large language models
Question Why has structured reporting not been widely adopted in radiology despite clear benefits and how can we improve this? Findings A locally hosted large language model successfully structured narrative reports, showing variation between languages and findings. Critical relevance Structured reporting provides many benefits, but its integration into the clinical routine is limited. Automating the extraction of structured information from radiology reports enables the capture of structured data while allowing the radiologist to maintain their reporting workflow.
Authors
- Bettina Baeßler (ORCID: https://orcid.org/0000-0002-3244-3864)
- Caroline Laqua
- Daniel Truhn (ORCID: https://orcid.org/0000-0002-9605-0728)
- Daniel Pinto dos Santos (ORCID: https://orcid.org/0000-0003-4785-6394)
- Tugba Akinci D’Antonoli (ORCID: https://orcid.org/0000-0002-7237-711X)
- Amar Hekalo (ORCID: https://orcid.org/0000-0002-7325-9107)
- Piotr Woźnicki (ORCID: https://orcid.org/0000-0002-9437-3785)
- Sebastian Foersch (ORCID: https://orcid.org/0000-0002-4740-6900)
- Jakob Nikolas Kather (ORCID: https://orcid.org/0000-0002-3730-5348)
- Fabian Christopher Laqua (ORCID: https://orcid.org/0000-0002-3761-0350)
- Sandy Engelhardt (ORCID: https://orcid.org/0000-0001-8816-7654)
- Ina Fiku
Institutions
- Goethe University Frankfurt (DE)
- University of Cologne (DE)
- Johannes Gutenberg University Mainz (DE)
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- University Medical Center of the Johannes Gutenberg University Mainz (DE)
- Psychiatry Baselland (CH)
- National Center for Tumor Diseases (DE)
- Universitätsklinikum Aachen (DE)
- Universitätsklinikum Würzburg (DE)
- German Centre for Cardiovascular Research (DE)
- University Hospital Frankfurt (DE)
- University Hospital Carl Gustav Carus (DE)
Publication Details
- Journal
- European Radiology
- Published
- 2024-10-10
- DOI
- https://doi.org/10.1007/s00330-024-11074-y
- Citations
- 22
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 7.64
Funders
- Bundesministerium für Bildung und Forschung