Prompt-Guided Generation of Structured Chest X-Ray Report Using a Pre-trained LLM

TL;DR

This paper presents a prompt-guided method leveraging a pre-trained LLM to generate structured, clinically relevant chest X-ray reports with focused anatomical and contextual information, improving report clarity and utility.

Contribution

It introduces a novel prompt-based approach that combines anatomical detection and clinical prompts to produce structured radiology reports using a pre-trained LLM.

Findings

Strong performance on language generation metrics

Enhanced report structure and clinical relevance

Effective focus on anatomical regions

Abstract

Medical report generation automates radiology descriptions from images, easing the burden on physicians and minimizing errors. However, current methods lack structured outputs and physician interactivity for clear, clinically relevant reports. Our method introduces a prompt-guided approach to generate structured chest X-ray reports using a pre-trained large language model (LLM). First, we identify anatomical regions in chest X-rays to generate focused sentences that center on key visual elements, thereby establishing a structured report foundation with anatomy-based sentences. We also convert the detected anatomy into textual prompts conveying anatomical comprehension to the LLM. Additionally, the clinical context prompts guide the LLM to emphasize interactivity and clinical requirements. By integrating anatomy-focused sentences and anatomy/clinical prompts, the pre-trained LLM can generate structured chest X-ray reports tailored to prompted anatomical regions and clinical contexts. We evaluate using language generation and clinical effectiveness metrics, demonstrating strong performance.