Table 1. Quantitative results of different algorithms for the testing images in Figures 3,5,7.

Algorithm	Lung				Abdominal 1				Abdominal 2
	PSNR	SSIM	NRMSE		PSNR	SSIM	NRMSE		PSNR	SSIM	NRMSE
LDCT	38.5195	0.8967	0.0119		30.4167	0.5876	0.0301		31.6664	0.6469	0.0261
TV	41.8727	0.9567	0.0081		37.3804	0.8786	0.0135		38.0982	0.8945	0.0124
RedCNN-MSE	44.8781	0.9782	0.0057		40.0759	0.9348	0.0099		41.2589	0.9467	0.0087
ADAPTIVE-MSE	44.3783	0.9774	0.0060		39.6627	0.9364	0.0104		40.5510	0.9441	0.0094
RedCNN-VGG-1000*MSE	47.0619	0.9852	0.0044		40.5442	0.9425	0.0094		42.0989	0.9540	0.0079
ADAPTIVE-VGG-5000*MSE	46.3096	0.9842	0.0048		40.1877	0.9405	0.0098		41.6529	0.9520	0.0083
ADAPTIVE-VGG-1000*MSE	46.0407	0.9835	0.0050		39.5937	0.9342	0.0105		41.1898	0.9485	0.0087

NRMSE, normalized root mean square error; SSIM, structural similarity index metric; PSNR, peak signal-to-noise ratio.