Ring Artifacts Correction Based on Global–Local Feature Interaction Guidance in the Projection Domain

Ring artifacts frequently arise in CT imaging due to the inconsistent responses of detector units to X-rays. This effect is further exacerbated in photon-counting detectors, resulting in stripe artifacts in the sinogram. Under circular scanning, such artifacts manifest as concentric ring artifacts radiating from the center of rotation, severely degrading image quality. Based on the properties of the Radon transform and the inherent ray conjugacy in fan-beam CT systems, ideal sinograms exhibit smoothness and global correlation. Influenced by various physical factors and object properties during practical data acquisition, stripe artifacts exhibit localized high-frequency characteristics along both the detector and angular directions, with their intensities correlated with the projection values. Therefore, we propose a ring artifacts correction method based on the interaction guidance between global and local features in the projection domain. Applying the discrete wavelet transform, the sinogram is decomposed into low-frequency sub-bands that predominantly capture global feature and high-frequency sub-bands that primarily represent local feature, each corrected independently. To address the challenge of decoupling global and local feature within the sub-band images, we propose a global-local feature interaction guidance module to achieve precise correction of stripe artifacts. Extensive experimental results demonstrate that the proposed method consistently outperforms existing approaches in quantitative metrics and visual artifacts suppression, highlighting its robustness and clinical applicability.