Table 2. Performance of Deep Learning Algorithm in Liver and Spleen Segmentation in Test Dataset-1.

	Dice Similarity Score
	Liver Segmentation	Spleen Segmentation
Total	0.973 ± 0.019 (0.907–0.999)	0.974 ± 0.018 (0.940–0.999)
Subgroups
Healthy liver	0.975 ± 0.017 (0.974–0.999)	0.971 ± 0.017 (0.948–0.998)
Fatty liver disease	0.976 ± 0.019 (0.952–0.999)	0.974 ± 0.018 (0.947–0.999)
Non-cirrhotic chronic liver disease	0.974 ± 0.019 (0.945–0.999)	0.974 ± 0.018 (0.944–0.999)
Liver cirrhosis	0.970 ± 0.016 (0.926–0.997)	0.978 ± 0.018 (0.940–0.999)
Post-hepatectomy	0.968 ± 0.030 (0.907–0.999)	0.972 ± 0.020 (0.947–0.999)
p value*	0.6	0.26

Unless otherwise indicated, data are expressed as mean ± standard deviation; data in parentheses are range. ^*p values for comparison of dice similarity score among five subgroups using Kruskal-Wallis test.