Resource-Efficient Medical Report Generation using Large Language Models
This work addresses the time-consuming and error-prone task of manual radiology report writing for radiologists, though it appears incremental as it builds on existing LLM methods.
The authors tackled medical report generation from chest X-ray images by proposing a lightweight framework using vision-enabled Large Language Models, achieving better or comparable performance to previous solutions on the MIMIC-CXR dataset with high precision and strong contextual understanding.
Medical report generation is the task of automatically writing radiology reports for chest X-ray images. Manually composing these reports is a time-consuming process that is also prone to human errors. Generating medical reports can therefore help reduce the burden on radiologists. In other words, we can promote greater clinical automation in the medical domain. In this work, we propose a new framework leveraging vision-enabled Large Language Models (LLM) for the task of medical report generation. We introduce a lightweight solution that achieves better or comparative performance as compared to previous solutions on the task of medical report generation. We conduct extensive experiments exploring different model sizes and enhancement approaches, such as prefix tuning to improve the text generation abilities of the LLMs. We evaluate our approach on a prominent large-scale radiology report dataset - MIMIC-CXR. Our results demonstrate the capability of our resource-efficient framework to generate patient-specific reports with strong medical contextual understanding and high precision.