Style-Aware Radiology Report Generation with RadGraph and Few-Shot Prompting

Benjamin Yan, Ruochen Liu, David E Kuo, Subathra Adithan, Eduardo Pontes Reis, Stephen Kwak, Vasantha Kumar Venugopal, Chloe P O'Connell, Agustina Saenz, Pranav Rajpurkar, Michael Moor

Submission Type: Regular Long Paper

Submission Track: NLP Applications

Submission Track 2: Human-Centered NLP

Keywords: language model, radiology, report generation, few-shot prompting, in-context learning, radgraph

Abstract: Automatically generated reports from medical images promise to improve the workflow of radiologists. Existing methods consider an image-to-report modeling task by directly generating a fully-fledged report from an image. However, this conflates the content of the report (e.g., findings and their attributes) with its style (e.g., format and choice of words), which can lead to clinically inaccurate reports. To address this, we propose a two-step approach for radiology report generation. First, we extract the content from an image; then, we verbalize the extracted content into a report that matches the style of a specific radiologist. For this, we leverage RadGraph---a graph representation of reports---together with large language models (LLMs). In our quantitative evaluations, we find that our approach leads to beneficial performance. Our human evaluation with clinical raters highlights that the AI-generated reports are indistinguishably tailored to the style of individual radiologist despite leveraging only a few examples as context.

Submission Number: 1280