Fast, accurate and robust sparse-view CT reconstruction via residual-guided Golub-Kahan iterative reconstruction technique (RGIRT)

Reduction of projection views in X-ray computed tomography (CT) can protect patients from over exposure to ionizing radiation, thus is highly attractive for clinical applications. However, image reconstruction for sparse-view CT which aims to produce decent images from few projection views remains a challenge. To address this, we propose a Residual-guided Golub-Kahan Iterative Reconstruction Technique (RGIRT). RGIRT utilizes an inner-outer dual iteration framework, with a flexible least square QR (FLSQR) algorithm implemented in the inner iteration and a restarted iterative scheme applied in the outer iteration. The inner FLSQR employs a flexible Golub-Kahan (FGK) bidiagonalization method to reduce the dimension of the inverse problem, and a weighted generalized cross-validation (WGCV) method to adaptively estimate the regularization hyper-parameter. The inner iteration efficiently yields the intermediate reconstruction result, while the outer iteration minimizes the residual and refines the solution by using the result obtained from the inner iteration. Reconstruction performance of RGIRT is evaluated and compared to other reference methods (FBPConvNet, SART-TV, and FLSQR) using realistic mouse cardiac micro-CT data. Experiment results demonstrate RGIRTs merits for sparse-view CT reconstruction in high accuracy, efficient computation, and stable convergence.