Cover Image

How green are large language models for radiology report labelling?: comparing human, rule-based and hybrid workflows

To address limited quantitative data on sustainable use of large language models (LLMs) in radiology, we quantified the resource footprint of LLMs for labelling CT pulmonary embolism reports and assessed how a hybrid rule-based-LLM workflow changes time, cost and carbon emissions compared with manua...

Full description

Saved in:
Bibliographic Details
Main Authors: Fink, Matthias A. (Author) , Bischoff, Arved (Author) , Atsiatorme, Edem (Author) , Kremer, Alexander (Author) , Kroschke, Jonas (Author) , Moll, Martin (Author) , Stein, Patrick (Author) , Riebl, Veronika (Author) , Leichenich, Timo (Author) , Kauczor, Hans-Ulrich (Author) , Schlamp, Kai (Author)
Format: Article (Journal)
Language:English
Published: 27 May 2026
In: Insights into imaging
Year: 2026, Volume: 17, Issue: 1, Pages: 1-11
ISSN:1869-4101
DOI:10.1186/s13244-026-02289-2
Online Access:Verlag, kostenfrei, Volltext: https://link.springer.com/article/10.1186/s13244-026-02289-2
Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s13244-026-02289-2
Get full text
Author Notes:Matthias A. Fink, Arved Bischoff, Edem Atsiatorme, Alexander Kremer, Jonas Kroschke, Martin Moll, Patrick Stein, Veronika Riebl, Timo Leichenich, Hans-Ulrich Kauczor and Kai Schlamp
Description
Summary:To address limited quantitative data on sustainable use of large language models (LLMs) in radiology, we quantified the resource footprint of LLMs for labelling CT pulmonary embolism reports and assessed how a hybrid rule-based-LLM workflow changes time, cost and carbon emissions compared with manual labelling.
Item Description:Gesehen am 26.08.2026
Physical Description:Online Resource
ISSN:1869-4101
DOI:10.1186/s13244-026-02289-2

Similar Items