A Model of Regularization Parameter Determination in Low-Dose X-Ray CT Reconstruction Based on Dictionary Learning
Reconstructed images from low-dose projection data of the Shepp-Logan phantom. From top to bottom, the noise levels are 0.0%, 0.1%, and 0.2% in turn. From left to right, the reconstruction algorithms are SART, GPBB, ADSIR, and AWR-ADSIR, respectively. The display window is .