EUVIMEDEUVIMED entdecken
Open Access

ONCO-RADS–guided Large Language Models for Extraction and Classification of Incidental Findings on Whole-Body Imaging Reports

Mickael Tordjman iD, Murat Yuce iD, Zelong Liu iD, Anis Meribout iD, Ian Bolger iD, Amine Geahchan, Francisco Restrepo iD, Himanshu Joshi iD, Hao-Chih Lee, Timothy Deyer iD, Zahi Fayad iD, Sara Lewis iD und 3 weitere

Radiology: Imaging Cancer · 2026

DOI: 10.1148/rycan.250484 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology: Imaging Cancer, 2026. Verfasst von Mickael Tordjman und 14 weiteren Autor:innen. Beteiligte Einrichtung: BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY 10029. Hauptthemen laut MEDLINE: Large Language Models, Incidental Findings, Whole Body Imaging, Magnetic Resonance Imaging. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The large language models ChatGPT-o1 and Gemini-2.5-Pro, guided with Oncologically Relevant Findings Reporting and Data System (ONCO-RADS) prompts, accurately extracted and classified incidental findings from whole-body imaging reports and outperformed these strategies without ONCO-RADS prompts and the medical named entity recognition model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsIncidental FindingsWhole Body ImagingMagnetic Resonance ImagingNeoplasmsHumansRetrospective StudiesMaleReproducibility of ResultsFemaleMiddle AgedAged

Stichwörter der Autor:innen

Incidental FindingsLarge Language ModelsWhole-Body MRI

Autor:innen und Institutionen

  • BioMedical Engineering and Imaging Institute, Icahn School of Medicine at Mount Sinai, 1470 Madison Ave, New York, NY 10029.
  • Department of Diagnostic, Molecular and Interventional Radiology, Mount Sinai Hospital, New York, NY.
  • East River Medical Imaging, New York, NY.
  • Department of Radiology, Cornell Medicine, New York, NY.
  • Division of Radiology, IEO European Institute of Oncology IRCCS, Milan, Italy.
  • Department of Oncology and Hemato-Oncology, University of Milan, Milan, Italy.

ORCID-Profile: Mickael Tordjman, Murat Yuce, Zelong Liu, Anis Meribout, Ian Bolger, Francisco Restrepo, Himanshu Joshi, Timothy Deyer, Zahi Fayad, Sara Lewis, Giuseppe Petralia, Xueyan Mei, Bachir Taouli

Zitieren

APA

Tordjman, M., Yuce, M., Liu, Z., Meribout, A., Bolger, I., Geahchan, A., Restrepo, F., Joshi, H., Lee, H. C., Deyer, T., Fayad, Z., Lewis, S., Petralia, G., Mei, X., & Taouli, B. (2026). ONCO-RADS–guided Large Language Models for Extraction and Classification of Incidental Findings on Whole-Body Imaging Reports. Radiology: Imaging Cancer. https://doi.org/10.1148/rycan.250484

Vancouver

Tordjman M, Yuce M, Liu Z, Meribout A, Bolger I, Geahchan A, et al. ONCO-RADS–guided Large Language Models for Extraction and Classification of Incidental Findings on Whole-Body Imaging Reports. Radiology: Imaging Cancer. 2026. doi:10.1148/rycan.250484

BibTeX
@article{Tordjman2026,
  author = {Tordjman, Mickael and Yuce, Murat and Liu, Zelong and Meribout, Anis and Bolger, Ian and Geahchan, Amine and Restrepo, Francisco and Joshi, Himanshu and Lee, Hao-Chih and Deyer, Timothy and Fayad, Zahi and Lewis, Sara and Petralia, Giuseppe and Mei, Xueyan and Taouli, Bachir},
  title = {ONCO-RADS–guided Large Language Models for Extraction and Classification of Incidental Findings on Whole-Body Imaging Reports},
  journal = {Radiology: Imaging Cancer},
  year = {2026},
  doi = {10.1148/rycan.250484}
}
Kostenlos starten →