Fig. 6From: Disentangled generative adversarial network for low-dose CTThe 2D (a) and radial 1D (b) normalized NPS results from all the methods. NPS is calculated with a 120 Ă— 120 pixel ROI and ground truth subtraction is used as the background removal method. Our methods, i.e., PNSR-oriented DNSN and visual perception-oriented DNSGAN achieved noticeable improvements on noise removalBack to article page