SynthRAR: Ring Artifacts Reduction in CT with Unrolled Network and Synthetic Data Training

TL;DR

This work tackles ring artifact reduction in CT caused by non-ideal detector responses by formulating the problem as a physics-informed inverse problem and solving it with a dual-domain unrolled network. SynthRAR integrates estimations of inconsistent and invalid detector responses into a modified forward projection within an ISTA-Net framework and learns corrections from synthetic data generated from natural images. The approach achieves state-of-the-art performance across in-distribution and out-of-distribution datasets and scanning geometries, with strong generalization and reduced reliance on real clinical data. While promising for clinical deployment, the authors note challenges for multi-row/cone-beam CT and emphasize the need for on-device validation and scanner-specific adaptation.

Abstract

Defective and inconsistent responses in CT detectors can cause ring and streak artifacts in the reconstructed images, making them unusable for clinical purposes. In recent years, several ring artifact reduction solutions have been proposed in the image domain or in the sinogram domain using supervised deep learning methods. However, these methods require dedicated datasets for training, leading to a high data collection cost. Furthermore, existing approaches focus exclusively on either image-space or sinogram-space correction, neglecting the intrinsic correlations from the forward operation of the CT geometry. Based on the theoretical analysis of non-ideal CT detector responses, the RAR problem is reformulated as an inverse problem by using an unrolled network, which considers non-ideal response together with linear forward-projection with CT geometry. Additionally, the intrinsic correlations of ring artifacts between the sinogram and image domains are leveraged through synthetic data derived from natural images, enabling the trained model to correct artifacts without requiring real-world clinical data. Extensive evaluations on diverse scanning geometries and anatomical regions demonstrate that the model trained on synthetic data consistently outperforms existing state-of-the-art methods.

Figures (10)

• Figure 1: Illustration of non-ideal responses in sinogram data and corresponding reconstructed CT images, which has ring and streak artifacts due to inconsistent detector and invalid detector responses.
• Figure 2: Illustration of the proposed SynthRAR model, which utilizes the basic ISTA-Net with modified components for IR and IM estimations. The model performs ring artifact correction through K iterative updates, progressively refining the reconstruction at each iteration.
• Figure 3: Illustration of modified forward projection step. The input CT at iteration k is transformed to sinogram with known CT geometry. In addition, the original sinogram is processed by two individual networks to estimate IR and IM measurements for function $\tilde{A}x = (-\ln{{H}_{IR}} + Ax)\times{H}_{IM}$.
• Figure 4: Illustration of networks to estimate IR and IM from sinogram. The IR output is processed by Sigmoid and rescaled to the common definition range of inconsistent responses (a=0.75 and b=0.5 in our implementation). The IM output is processed by Sigmoid to predict binary mask of invalid detectors.
• Figure 5: Illustration of synthetic CT-like training data generation based on the definitions of forward projection, IR and IM. The natural gray-scale image is masked by a circle to simulate the CT appearance with re-scaled intensity value to random range 0.5-0.7 for linear attenuation coefficient $\mu$.