Radiology Report Generation for Low-Quality X-Ray Images

2026-04-11

AI Summary

This work addresses the significant performance degradation of existing radiology report generation models on low-quality chest X-ray images, which commonly suffer from noise and artifacts in clinical settings. To enhance robustness to image quality variations, the authors propose a novel framework that first establishes LRRG—the first benchmark specifically designed for low-quality radiology report generation—and introduces an Automated Quality Assessment Agent (AQAA) to identify degraded samples. Building upon this, they devise a dual-cycle training mechanism based on bilevel optimization and gradient consistency, which aligns gradient directions across images of varying quality to learn diagnostic features invariant to image degradation. Experimental results demonstrate that the proposed approach substantially improves both the accuracy and stability of generated reports under image quality deterioration.

Technology Category

• Knowledge Representation and Reasoning: Qualitative Reasoning
• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

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.

Problem

• Radiology Report Generation
• Low-Quality X-Ray Images
• Image Quality Degradation
• Vision-Language Models
• Clinical Artifacts

Innovation

• Low-quality Radiology Report Generation
• Vision-Language Models
• Automated Quality Assessment
• Dual-loop Training
• Gradient Consistency