Automatic segmentation of hepatic metastases on DWI images based on a deep learning method: assessment of tumor treatment response according to the RECIST 1.1 criteria

Table 4 The segmentation results of liver and liver metastases in the testing dataset and validation cohort

	Testing dataset				Validation cohort
	Target Lesions < 5	Target Lesions ≥ 5	P value	all	Target Lesions < 5	Target Lesions ≥ 5	P value	all
Liver segmentation
DSC	0.95 ± 0.02	0.95 ± 0.02	0.976	0.95 ± 0.16	0.97 ± 0.04	0.96 ± 0.04	0.116	0.97 ± 0.04
VS	0.98 ± 0.01	0.98 ± 0.01	0.465	0.98 ± 0.01	0.98 ± 0.04	0.97 ± 0.04	0.122	0.97 ± 0.04
HD (mm)	15.34 ± 5.54	13.15 ± 4.43	0.635	14.39 ± 5.15	12.98 ± 7.51	14.30 ± 7.52	0.617	13.39 ± 7.47
Liver metastases segmentation
DSC	0.88 ± 0.07	0.88 ± 0.08	0.433	0.87 ± 0.07	0.86 ± 0.09	0.84 ± 0.09	0.836	0.85 ± 0.08
VS	0.94 ± 0.05	0.94 ± 0.06	0.477	0.94 ± 0.06	0.90 ± 0.10	0.88 ± 0.09	0.814	0.89 ± 0.09
HD (mm)	20.11 ± 14.93	25.99 ± 11.78	0.065	22.67 ± 13.83	23.81 ± 12.86	26.31 ± 9.48	0.081	25.53 ± 12.11

DSC Dice similarity coefficient, VS Volumetric similarity, HD Hausdorff distance

ISSN: 1471-2407