CT-DegradBench: A Physics-Informed Benchmark for CT Degradation Detection and Severity Estimation
For researchers and practitioners in medical image enhancement, this benchmark provides a unified evaluation framework for CT degradation analysis, addressing the lack of standardized multi-degradation datasets.
The paper introduces CT-DegradBench, a benchmark for detecting and estimating severity of CT image degradations (noise, blur, streaking, aliasing, metal artifacts) under single- and mixed-artifact conditions. The proposed SeSpeCT framework, combining semantic priors from medical vision-language models with spectral features, outperforms baselines in joint artifact type and severity prediction.
Computed tomography (CT) images are frequently degraded by acquisition artifacts, including noise, blur, streaking, aliasing, and metal artifacts. Yet CT enhancement is still largely evaluated using image quality metrics with limited perceptual and clinical validity, while existing datasets remain focused on isolated restoration tasks, hindering unified benchmarking across diverse degradation types. We present CT-DegradBench, a dataset and benchmark for CT degradation detection and severity estimation under controlled single- and mixed-artifact settings. CT-DegradBench enables systematic evaluation across multiple degradation families and severity levels within a common experimental framework. We further propose SeSpeCT (Semantic-Spectral CT degradation estimation), a framework that combines semantic priors from medical vision-language models with complementary frequency-domain cues for artifact analysis. SeSpeCT constructs a training-free semantic quality axis in the multimodal embedding space using radiology-informed text prompts, without task-specific fine-tuning, and combines it with spectral features that capture degradation-specific frequency patterns. The resulting representation enables joint prediction of artifact type and severity. Experimental results show that SeSpeCT consistently outperforms the evaluated baselines under both single- and mixed-degradation settings. The framework is available at https://github.com/yousranb/CT-DEGRADBENCH.