Table 6. The average PSNR, SSIM, ICC, and MAE between the HQ and the experimental LQ images and between the HQ and the reconstructed images using the GS algorithm, the MF method, the DnCNN, N2N, MIRNet, and incSRCNN networks for the cross-validation analysis.

Image	Metric	LQ	GS	Median Filter	DnCNN	N2N	MIRNet	incSRCNN
CARS channel	PSNR	18.6 ± 1.31	14.9 ± 1.36	18.9 ± 1.37	19.1 ± 1.38	14.2 ± 1.73	12.8 ± 2.23	15.3 ± 0.87
	SSIM	0.39 ± 0.08	0.33 ± 0.05	0.44 ± 0.06	0.47 ± 0.07	0.27 ± 0.13	0.17 ± 0.17	0.39 ± 0.07
	ICC	0.72 ± 0.10	0.73 ± 0.03	0.78 ± 0.01	0.78 ± 0.01	0.52 ± 0.03	0.30 ± 0.04	0.79 ± 0.02
	MAE	0.09 ± 0.01	0.16 ± 0.09	0.09 ± 0.08	0.09 ± 0.08	0.16 ± 0.20	0.18 ± 0.23	0.15 ± 0.07
TPEF channel	PSNR	22.5 ± 3.19	21.2 ± 2.67	23.0 ± 3.56	23.4 ± 3.93	18.5 ± 2.44	15.5 ± 4.31	17.7 ± 1.66
	SSIM	0.58 ± 0.11	0.60 ± 0.04	0.72 ± 0.09	0.74 ± 0.09	0.59 ± 0.11	0.35 ± 0.20	0.35 ± 0.16
	ICC	0.82 ± 0.06	0.83 ± 0.02	0.87 ± 0.01	0.87 ± 0.01	0.74 ± 0.02	0.52 ± 0.05	0.85 ± 0.02
	MAE	0.05 ± 0.01	0.06 ± 0.05	0.04 ± 0.05	0.04 ± 0.05	0.09 ± 0.07	0.12 ± 0.18	0.11 ± 0.06
SHG channel	PSNR	22.9 ± 2.63	20.3 ± 1.17	23.4 ± 2.79	23.4 ± 2.73	20.2 ± 2.63	15.8 ± 4.49	18.8 ± 1.53
	SSIM	0.62 ± 0.09	0.52 ± 0.05	0.67 ± 0.09	0.68 ± 0.08	0.59 ± 0.10	0.38 ± 0.18	0.27 ± 0.15
	ICC	0.76 ± 0.07	0.78 ± 0.02	0.80 ± 0.01	0.79 ± 0.01	0.68 ± 0.02	0.43 ± 0.04	0.78 ± 0.02
	MAE	0.04 ± 0.01	0.08 ± 0.06	0.04 ± 0.05	0.04 ± 0.06	0.06 ± 0.07	0.10 ± 0.15	0.09 ± 0.05
MM image	PSNR	21.3 ± 2.38	18.8 ± 1.73	21.8 ± 2.57	22.0 ± 2.68	17.6 ± 2.27	14.7 ± 3.68	17.3 ± 1.36
	SSIM	0.53 ± 0.09	0.48 ± 0.05	0.61 ± 0.08	0.63 ± 0.08	0.48 ± 0.11	0.30 ± 0.18	0.34 ± 0.12
	ICC	0.77 ± 0.07	0.78 ± 0.02	0.82 ± 0.01	0.81 ± 0.01	0.65 ± 0.02	0.42 ± 0.04	0.81 ± 0.02
	MAE	0.06 ± 0.01	0.10 ± 0.06	0.06 ± 0.06	0.06 ± 0.06	0.10 ± 0.12	0.13 ± 0.19	0.12 ± 0.06