Automated Structured Radiology Report Generation

TL;DR

This paper introduces Structured Radiology Report Generation (SRRG), a new task that converts free-form chest X-ray reports into standardized, structured formats to improve clinical consistency and evaluation.

Contribution

It presents a novel dataset created with large language models, a disease classification model (SRR-BERT), and a new evaluation metric (F1-SRR-BERT) for structured report quality assessment.

Findings

SRRG dataset validated by radiologists

SRR-BERT enables precise disease classification

F1-SRR-BERT improves evaluation of structured reports

Abstract

Automated radiology report generation from chest X-ray (CXR) images has the potential to improve clinical efficiency and reduce radiologists' workload. However, most datasets, including the publicly available MIMIC-CXR and CheXpert Plus, consist entirely of free-form reports, which are inherently variable and unstructured. This variability poses challenges for both generation and evaluation: existing models struggle to produce consistent, clinically meaningful reports, and standard evaluation metrics fail to capture the nuances of radiological interpretation. To address this, we introduce Structured Radiology Report Generation (SRRG), a new task that reformulates free-text radiology reports into a standardized format, ensuring clarity, consistency, and structured clinical reporting. We create a novel dataset by restructuring reports using large language models (LLMs) following strict structured reporting desiderata. Additionally, we introduce SRR-BERT, a fine-grained disease classification model trained on 55 labels, enabling more precise and clinically informed evaluation of structured reports. To assess report quality, we propose F1-SRR-BERT, a metric that leverages SRR-BERT's hierarchical disease taxonomy to bridge the gap between free-text variability and structured clinical reporting. We validate our dataset through a reader study conducted by five board-certified radiologists and extensive benchmarking experiments.