Optimizing Large Language Models for Automated Protocoling of Abdominal and Pelvic CT Scans: The Power of Context
Radiology · 01.01.2026 · 318 (1)
DOI: 10.1148/radiol.252105 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology, erschienen am 01.01.2026. Verfasst von Bryan W Buckley und 6 weiteren Autor:innen. Beteiligte Einrichtung: University Medical Imaging Toronto, Joint Department of Medical Imaging, University Health Network, Mount Sinai Hospital and Women's College Hospital…. Hauptthemen laut MEDLINE: Tomography, X-Ray Computed, Pelvis, Radiography, Abdominal. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 34 Literaturangaben.
Abstract (Originalsprache)
For protocoling abdominal and pelvic CT scans, the large language model GPT-4o (version 2024-08-06; Open AI) selected optimal protocols more frequently than radiologists when optimized with prompting; fine-tuning did not further improve performance.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- University Medical Imaging Toronto, Joint Department of Medical Imaging, University Health Network, Mount Sinai Hospital and Women's College Hospital, Department of Medical Imaging, University of Toronto, Toronto Genera…
- Department of Biostatistics, University Health Network, Toronto, Canada.
ORCID-Profile: Bryan W Buckley, Adriano B Dias, Yangqing Deng, Heidi Schmidt, Ania Kielar, Satheesh Krishna, Rajesh Bhayana
Zitieren
APA
Buckley, B. W., Dias, A. B., Deng, Y., Schmidt, H., Kielar, A., Krishna, S., & Bhayana, R. (2026). Optimizing Large Language Models for Automated Protocoling of Abdominal and Pelvic CT Scans: The Power of Context. Radiology, 318(1). https://doi.org/10.1148/radiol.252105
Vancouver
Buckley BW, Dias AB, Deng Y, Schmidt H, Kielar A, Krishna S, et al. Optimizing Large Language Models for Automated Protocoling of Abdominal and Pelvic CT Scans: The Power of Context. Radiology. 2026;318(1). doi:10.1148/radiol.252105
BibTeX
@article{Buckley2026,
author = {Buckley, Bryan W and Dias, Adriano B and Deng, Yangqing and Schmidt, Heidi and Kielar, Ania and Krishna, Satheesh and Bhayana, Rajesh},
title = {Optimizing Large Language Models for Automated Protocoling of Abdominal and Pelvic CT Scans: The Power of Context},
journal = {Radiology},
year = {2026},
volume = {318},
number = {1},
doi = {10.1148/radiol.252105}
}
EUVIMED