Table 1.

nRMSE (%) and SSIM statistics (mean ± std) obtained from concentration-time series data fitting. The SSIM value can vary between –1 and 1, where 1 indicates perfect similarity.

	Models
Metric	Patlak	eTofts	CNN: Patlak trained	CNN: eTofts trained
nRMSE (%)	1.1200 ± 0.5225	1.0575 ± 0.5744	1.6398 ± 0.6878	1.7360 ± 0.7408
SSIM	0.9812 ± 0.0141	0.9835 ± 0.0127	0.9750 ± 0.0138	0.9719 ± 0.0162