🤖 AI Summary
This work addresses the challenge of ring and streak artifacts in computed tomography (CT) caused by low-performance pixels (LPP) in detectors, which severely compromise clinical diagnosis. The authors propose a dual-domain joint correction method based on an unrolled network that, for the first time, integrates the CT geometric forward model into a deep learning framework to collaboratively model LPP-induced artifacts in both the sinogram and image domains. Training data are synthesized from natural images, eliminating the need for real clinical defect measurements and enabling end-to-end training as well as cross-scanner deployment. Under simulated detector defect rates of 1–2%, the proposed method significantly outperforms existing techniques, effectively suppressing artifacts while demonstrating strong practicality and generalization capability.
📝 Abstract
Low performance pixels (LPP) in Computed Tomography (CT) detectors would lead to ring and streak artifacts in the reconstructed images, making them clinically unusable. In recent years, several solutions have been proposed to correct LPP artifacts, either in the image domain or in the sinogram domain using supervised deep learning methods. However, these methods require dedicated datasets for training, which are expensive to collect. Moreover, existing approaches focus solely either on image-space or sinogram-space correction, ignoring the intrinsic correlations from the forward operation of the CT geometry. In this work, we propose an unrolled dual-domain method based on synthetic data to correct LPP artifacts. Specifically, the intrinsic correlations of LPP between the sinogram and image domains are leveraged through synthetic data generated from natural images, enabling the trained model to correct artifacts without requiring any real-world clinical data. In experiments simulating 1-2% detectors defect near the isocenter, the proposed method outperformed the state-of-the-art approaches by a large margin. The results indicate that our solution can correct LPP artifacts without the cost of data collection for model training, and it is adaptable to different scanner settings for software-based applications.