Radiology Report Generation for Low-Quality X-Ray Images

TL;DR

This paper introduces a robust radiology report generation framework that maintains performance across varying image qualities by using a quality assessment agent and a dual-loop training strategy.

Contribution

It presents a novel framework with an automated quality assessment and a bi-level optimization training method to improve report generation on low-quality X-ray images.

Findings

Effectively mitigates performance loss on low-quality images

Establishes a new Low-quality Radiology Report Generation benchmark

Demonstrates improved diagnostic feature learning across image qualities

Abstract

Vision-Language Models (VLMs) have significantly advanced automated Radiology Report Generation (RRG). However, existing methods implicitly assume high-quality inputs, overlooking the noise and artifacts prevalent in real-world clinical environments. Consequently, current models exhibit severe performance degradation when processing suboptimal images. To bridge this gap, we propose a robust report generation framework explicitly designed for image quality variations. We first introduce an Automated Quality Assessment Agent (AQAA) to identify low-quality samples within the MIMIC-CXR dataset and establish the Low-quality Radiology Report Generation (LRRG) benchmark. To tackle degradation-induced shifts, we propose a novel Dual-loop Training Strategy leveraging bi-level optimization and gradient consistency. This approach ensures the model learns quality-agnostic diagnostic features by aligning gradient directions across varying quality regimes. Extensive experiments demonstrate that our approach effectively mitigates model performance degradation caused by image quality deterioration. The code and data will be released upon acceptance.