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.
@article{arxiv.2605.16431,
title = {CT-DegradBench: A Physics-Informed Benchmark for CT Degradation Detection and Severity Estimation},
author = {Yousra Nabila Taifour and Marouane Tliba and Zuheng Ming and Marie Luong and Nour Aburaed and Aladine Chetouani and Gorkem Durak and Alessandro Bruno and Faouzi Alaya Cheikh and Habib Zaidi and Ulas Bagci and Azeddine Beghdadi},
journal= {arXiv preprint arXiv:2605.16431},
year = {2026}
}
Comments
Accepted in CVPR 2026 VISION Workshop (DEXTER track)