EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LLaMA-XR: A Novel Framework for Radiology Report Generation Using LLaMA and QLoRA Fine Tuning

Md Zihad Bin Jahangir iD, Muhammad Ashad Kabir iD, Sumaiya Akter iD, Israt Jahan iD, Minh Chau iD

Bioengineering · 23.04.2026 · 13 (5) · 493

DOI: 10.3390/bioengineering13050493 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 23.04.2026. Verfasst von Md Zihad Bin Jahangir und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, Southeast University, Dhaka 1215, Bangladesh. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The goal of automated radiology report generation is to help radiologists in their task of creating descriptive reports from chest radiographs. However, the process of creating coherent and contextually accurate reports has been challenging, mainly due to the intricacies of medical language and the need to correlate visual data with textual descriptions.

Methods

This study presents LLaMA-XR, a novel framework that integrates Meta LLaMA 3.1 Large Language Model with DenseNet-121-based image embeddings and Quantized Low-Rank Adaptation (QLoRA) fine-tuning.

Results

The experiment conducted on the IU X-ray dataset demonstrates that LLaMA-XR outperforms a range of state-of-the-art methods. It achieves an ROUGE-L score of 0.433 and a METEOR score of 0.336, establishing new performance benchmarks in the domain.

Conclusions

These results underscore LLaMA-XR’s potential as an effective artificial intelligence system for automated radiology reporting, offering enhanced performance.

Schlagwörter

Stichwörter der Autor:innen

LLaMAchest X-rayfine-tuningradiologyreport generation

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, Southeast University, Dhaka 1215, Bangladesh.
  • School of Computing, Mathematics and Engineering, Charles Sturt University, Bathurst, NSW 2795, Australia.
  • Department of Computer Science and Engineering, University of Liberal Arts Bangladesh, Dhaka 1207, Bangladesh.
  • Medical Imaging Group, School of Dentistry and Medical Sciences, Charles Sturt University, Wagga Wagga, NSW 2650, Australia.

ORCID-Profile: Md Zihad Bin Jahangir, Muhammad Ashad Kabir, Sumaiya Akter, Israt Jahan, Minh Chau

Zitieren

APA

Jahangir, M. Z. B., Kabir, M. A., Akter, S., Jahan, I., & Chau, M. (2026). LLaMA-XR: A Novel Framework for Radiology Report Generation Using LLaMA and QLoRA Fine Tuning. Bioengineering, 13(5), 493. https://doi.org/10.3390/bioengineering13050493

Vancouver

Jahangir MZB, Kabir MA, Akter S, Jahan I, Chau M. LLaMA-XR: A Novel Framework for Radiology Report Generation Using LLaMA and QLoRA Fine Tuning. Bioengineering. 2026;13(5):493. doi:10.3390/bioengineering13050493

BibTeX
@article{Jahangir2026,
  author = {Jahangir, Md Zihad Bin and Kabir, Muhammad Ashad and Akter, Sumaiya and Jahan, Israt and Chau, Minh},
  title = {LLaMA-XR: A Novel Framework for Radiology Report Generation Using LLaMA and QLoRA Fine Tuning},
  journal = {Bioengineering},
  year = {2026},
  volume = {13},
  number = {5},
  pages = {493},
  doi = {10.3390/bioengineering13050493}
}
Kostenlos starten →