Improving Radiology Report Generation with Semantic Understanding.
Authors
Ahn S,Park H,Yoo J,Choi J
Affiliations (3)
Affiliations (3)
- Interdisciplinary Program for Bioengineering, Graduate School, Seoul National University, South Korea.
- Integrated Major in Innovative Medical Science, Graduate School, Seoul National University, South Korea.
- Department of Biomedical Engineering, College of Medicine, Seoul National University, South Korea.
Abstract
This study proposes RRG-LLM, a model designed to enhance RRG by effectively learning medical domain with minimal computational resources. Initially, LLM is finetuned by LoRA, enabling efficient adaptation to the medical domain. Subsequently, only the linear projection layer that project the image into text is finetuned to extract important information from the radiology image and project it onto the text dimension. Proposed model demonstrated notable improvements in report generation. The performance of ROUGE-L was improved by 0.096 (51.7%) and METEOR by 0.046 (42.85%) compared to the baseline model.
Topics
SemanticsRadiology Information SystemsNatural Language ProcessingJournal Article