LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916026345586688 |
|---|---|
| author | Jahangir, Md. Zihad Bin Kabir, Muhammad Ashad Akter, Sumaiya Jahan, Israt Chau, Minh |
| author_facet | Jahangir, Md. Zihad Bin Kabir, Muhammad Ashad Akter, Sumaiya Jahan, Israt Chau, Minh |
| contents | Automated radiology report generation holds significant potential to reduce radiologists' workload and enhance diagnostic accuracy. However, generating precise and clinically meaningful reports from chest radiographs remains challenging due to the complexity of medical language and the need for contextual understanding. Existing models often struggle with maintaining both accuracy and contextual relevance. In this paper, we present LLaMA-XR, a novel framework that integrates LLaMA 3.1 with DenseNet-121-based image embeddings and Quantized Low-Rank Adaptation (QLoRA) fine-tuning. LLaMA-XR achieves improved coherence and clinical accuracy while maintaining computational efficiency. This efficiency is driven by an optimization strategy that enhances parameter utilization and reduces memory overhead, enabling faster report generation with lower computational resource demands. Extensive experiments conducted on the IU X-ray benchmark dataset demonstrate that LLaMA-XR outperforms a range of state-of-the-art methods. Our model achieves a ROUGE-L score of 0.433 and a METEOR score of 0.336, establishing new performance benchmarks in the domain. These results underscore LLaMA-XR's potential as an effective and efficient AI system for automated radiology reporting, offering enhanced clinical utility and reliability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03178 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning Jahangir, Md. Zihad Bin Kabir, Muhammad Ashad Akter, Sumaiya Jahan, Israt Chau, Minh Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Automated radiology report generation holds significant potential to reduce radiologists' workload and enhance diagnostic accuracy. However, generating precise and clinically meaningful reports from chest radiographs remains challenging due to the complexity of medical language and the need for contextual understanding. Existing models often struggle with maintaining both accuracy and contextual relevance. In this paper, we present LLaMA-XR, a novel framework that integrates LLaMA 3.1 with DenseNet-121-based image embeddings and Quantized Low-Rank Adaptation (QLoRA) fine-tuning. LLaMA-XR achieves improved coherence and clinical accuracy while maintaining computational efficiency. This efficiency is driven by an optimization strategy that enhances parameter utilization and reduces memory overhead, enabling faster report generation with lower computational resource demands. Extensive experiments conducted on the IU X-ray benchmark dataset demonstrate that LLaMA-XR outperforms a range of state-of-the-art methods. Our model achieves a ROUGE-L score of 0.433 and a METEOR score of 0.336, establishing new performance benchmarks in the domain. These results underscore LLaMA-XR's potential as an effective and efficient AI system for automated radiology reporting, offering enhanced clinical utility and reliability. |
| title | LLaMA-XR: A Novel Framework for Radiology Report Generation using LLaMA and QLoRA Fine Tuning |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.03178 |