The Performance of Large Language Models in Bone Tumour Imaging: Comparative Analysis with Radiologists Using Text and Image-based Evaluation
Proceedings of the Bulgarian Academy of Sciences · 28.01.2026 · 79 (1) · 95-102
DOI: 10.7546/crabs.2026.01.12 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Bulgarian Academy of Sciences, online erschienen am 28.01.2026. Verfasst von Eren Çamur und 3 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref).
Abstract (Originalsprache)
Large language models (LLMs) are emerging as transformative tools in radiology, with potential to enhance diagnostic workflows. However, their performance in bone tumour imaging – a domain requiring both knowledge-based reasoning and visual interpretation -- remains unclear. This study compares the diagnostic performance of LLMs with radiologists across text and image-based tasks. In this cross-sectional study, two LLMs and two radiologists (a junior and a senior) were evaluated using fifty text-based multiple-choice questions (MCQs) and fifty radiographs with clinical vignettes from a public dataset. Participants classified lesions as benign or malignant, identified “don't-touch” lesions, and provided the most likely diagnosis. Responses were benchmarked against a reference standard using McNemar's tests. In MCQs, ChatGPT-5 (92.0%) and Gemini 2.5 Pro (90.0%) achieved accuracies comparable to SR (88.0%) and JR (84.0%) (p > 0.05). For benign--malignant classification, LLMs (50.0%, 48.0%) were similar to JR (66.0%) but inferior to SR (94.0%) (p < 0.05). In identifying “don't-touch”' lesions, LLMs (46.0%) matched JR (64.0%) yet underperformed compared to SR (92.0%) (p < 0.05). For specific diagnosis, LLMs showed low accuracy (38.0%, 30.0%) versus JR (60.0%) and SR (86.0%) (p < 0.01). LLMs may serve as useful adjuncts for clinicians and radiologists in text-based tasks and in distinguishing between benign and malignant bone tumours. However, their diagnostic accuracy remains limited.
Zitieren
APA
Çamur, E., Cesur, T., Güneş, Y., & Duran, S. (2026). The Performance of Large Language Models in Bone Tumour Imaging: Comparative Analysis with Radiologists Using Text and Image-based Evaluation. Proceedings of the Bulgarian Academy of Sciences, 79(1), 95-102. https://doi.org/10.7546/crabs.2026.01.12
Vancouver
Çamur E, Cesur T, Güneş Y, Duran S. The Performance of Large Language Models in Bone Tumour Imaging: Comparative Analysis with Radiologists Using Text and Image-based Evaluation. Proceedings of the Bulgarian Academy of Sciences. 2026;79(1):95-102. doi:10.7546/crabs.2026.01.12
BibTeX
@article{amur2026,
author = {Çamur, Eren and Cesur, Turay and Güneş, Yasin and Duran, Semra},
title = {The Performance of Large Language Models in Bone Tumour Imaging: Comparative Analysis with Radiologists Using Text and Image-based Evaluation},
journal = {Proceedings of the Bulgarian Academy of Sciences},
year = {2026},
volume = {79},
number = {1},
pages = {95--102},
doi = {10.7546/crabs.2026.01.12}
}
EUVIMED