CAP-IQA: Context-Aware Prompt-Guided CT Image Quality Assessment

TL;DR

CAP-IQA is a novel framework that combines text prompts and image context to accurately assess CT image quality, effectively handling real-world degradations and outperforming existing methods on benchmark datasets.

Contribution

This work introduces a context-aware, prompt-guided CT image quality assessment framework with causal debiasing, improving interpretability and generalizability over prior approaches.

Findings

Achieves higher correlation scores than top leaderboard methods.

Effective in real-world degradations like noise and motion artifacts.

Demonstrates strong generalization on pediatric CT datasets.

Abstract

Prompt-based methods, which encode medical priors through descriptive text, have been only minimally explored for CT Image Quality Assessment (IQA). While such prompts can embed prior knowledge about diagnostic quality, they often introduce bias by reflecting idealized definitions that may not hold under real-world degradations such as noise, motion artifacts, or scanner variability. To address this, we propose the Context-Aware Prompt-guided Image Quality Assessment (CAP-IQA) framework, which integrates text-level priors with instance-level context prompts and applies causal debiasing to separate idealized knowledge from factual, image-specific degradations. Our framework combines a CNN-based visual encoder with a domain-specific text encoder to assess diagnostic visibility, anatomical clarity, and noise perception in abdominal CT images. The model leverages radiology-style prompts and context-aware fusion to align semantic and perceptual representations. On the 2023 LDCTIQA challenge benchmark, CAP-IQA achieves an overall correlation score of 2.8590 (sum of PLCC, SROCC, and KROCC), surpassing the top-ranked leaderboard team (2.7427) by 4.24%. Moreover, our comprehensive ablation experiments confirm that prompt-guided fusion and the simplified encoder-only design jointly enhance feature alignment and interpretability. Furthermore, evaluation on an in-house dataset of 91,514 pediatric CT images demonstrates the true generalizability of CAP-IQA in assessing perceptual fidelity in a different patient population.