Table 3.

Quantitative evaluation (MEAN ± SD) for 400 test images from the Va dataset. A detailed explanation of all used metrics can be found in Table 2.

	Algorithms	Tissue metrics			tSD	tMRE (top) tPSNR (bottom)
		Epidermis	Dermis	Vessel
$\left|\text{Relative error}\right|$	Unet-MSE	0.023 ± 0.028	0.349 ± 0.150	0.186 ± 0.055	0.133	0.186 ± 0.058
	Unet-MSRE	0.024 ± 0.023	0.065 ± 0.010	0.254 ± 0.155	0.100	0.114 ± 0.051
	Ours	0.062 ± 0.030	0.070 ± 0.013	0.081 ± 0.030	0.008	0.071 ± 0.020
PSNR (dB)	Unet-MSE	36.142 ± 8.917	4.160 ± 3.522	13.832 ± 2.271	13.392	18.045 ± 2.812
	Unet-MSRE	31.777 ± 4.944	22.051 ± 1.373	11.462 ± 4.168	8.296	21.763 ± 1.540
	Ours	22.700 ± 3.525	20.468 ± 2.929	20.168 ± 3.169	1.130	21.112 ± 2.738