MedQ-UNI: Toward Unified Medical Image Quality Assessment and Restoration via Vision-Language Modeling

2026-03-18

AI Summary

This work addresses the limited generalization of existing medical image restoration methods and their lack of integration with quality assessment. The authors propose MedQ-UNI, a novel framework that pioneers a “quality-first, then restoration” paradigm by unifying cross-modal and cross-degradation image restoration and quality evaluation within a single vision-language model. Key innovations include leveraging structured natural language descriptions to guide the restoration process, designing a multimodal autoregressive dual-expert architecture with shared attention mechanisms, and constructing the first large-scale paired multimodal medical image dataset enabling joint training. Without task-specific adaptation, this unified model achieves state-of-the-art performance across five distinct restoration tasks while simultaneously generating high-fidelity, interpretable structured quality descriptions.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Existing medical image restoration (Med-IR) methods are typically modality-specific or degradation-specific, failing to generalize across the heterogeneous degradations encountered in clinical practice. We argue this limitation stems from the isolation of Med-IR from medical image quality assessment (Med-IQA), as restoration models without explicit quality understanding struggle to adapt to diverse degradation types across modalities. To address these challenges, we propose MedQ-UNI, a unified vision-language model that follows an assess-then-restore paradigm, explicitly leveraging Med-IQA to guide Med-IR across arbitrary modalities and degradation types. MedQ-UNI adopts a multimodal autoregressive dual-expert architecture with shared attention: a quality assessment expert first identifies degradation issues through structured natural language descriptions, and a restoration expert then conditions on these descriptions to perform targeted image restoration. To support this paradigm, we construct a large-scale dataset of approximately 50K paired samples spanning three imaging modalities and five restoration tasks, each annotated with structured quality descriptions for joint Med-IQA and Med-IR training, along with a 2K-sample benchmark for evaluation. Extensive experiments demonstrate that a single MedQ-UNI model, without any task-specific adaptation, achieves state-of-the-art restoration performance across all tasks while generating superior descriptions, confirming that explicit quality understanding meaningfully improves restoration fidelity and interpretability.

Problem

• medical image restoration
• medical image quality assessment
• modality-specific degradation
• heterogeneous degradations
• vision-language modeling

Innovation

• vision-language modeling
• medical image quality assessment
• medical image restoration
• unified framework
• structured language description