. 2024 Feb 26;14:4678. doi: 10.1038/s41598-024-53997-y

Table 7.

Comparison of descriptive statistics from models trained with segments, segments with vessel (color channel) and segments with spleen on liver surgery cohort C_LS.

	Seg 1,				Seg 2,				Seg 3,				Seg 4,				Seg 5–8,				Spleen,
	N = 33¹				N = 33¹				N = 33¹				N = 33¹				N = 33¹				N=33¹
	(IntraMD^2a = 0.88)				(IntraMD^2a = 0.88)				(IntraMD^2a = 0.94)				(IntraMD^2a = 0.92)				(IntraMD^2a = 0.99)
	(InterMD^2b = 0.82)				(InterMD^2b = 0.85)				(InterMD^2b = 0.91)				(InterMD^2b = 0.88)				(InterMD^2b = 0.96)
	M_paU-Net¹	M_nnUnet¹	M_seg+spleen¹	M_vess¹	M_paU-Net¹	M_nnUnet¹	M_seg+spleen¹	M_vess¹	M_paU-Net¹	M_nnUnet¹	M_{seg+ spleen}¹	M_vess¹	M_paU-Net¹	M_nnUnet¹	M_seg+ _spleen¹	M_vess¹	M_paU-Net¹	M_nnUnet¹	M_seg+spleen¹	M_vess¹	M_seg+spleen¹
Dice	0.91	0.94	0.94	0.94	0.87	0.88	0.86	0.86	0.90	0.93	0.91	0.91	0.89	0.93	0.92	0.93	0.97	0.98	0.98	0.98	0.96
	0.85,0.17	0.92,0.06	0.92,0.07	0.86, 0.23	0.85, 0.06	0.86, 0.06	0.85, 0.07	0.80, 0.22	0.89, 0.05	0.91, 0.04	0.91, 0.04	0.85, 0.22	0.86, 0.09	0.91, 0.06	0.90, 0.07	0.86, 0.23	0.96, 0.03	0.98, 0.02	0.98, 0.02	0.91, 0.24	0.91, 0.23
	0.96,0.00	0.98,0.75	0.98,0.69	0.98, 0.00	0.93, 0.62	0.94, 0.63	0.94, 0.62	0.93, 0.00	0.95, 0.69	0.96, 0.75	0.96, 0.76	0.96, 0.00	0.96, 0.58	0.97, 0.72	0.96, 0.63	0.97, 0.00	0.99, 0.88	0.99, 0.92	0.99, 0.91	0.99, 0.00	0.98, 0.00
${HD}_{95}^{3}$	4	2.5	2.8	2.5	8	7.8	8.5	6.8	7	5.4	5.8	5.8	10	5.0	5.8	5.0	5	2.5	3.0	2.2	2.1
	14, 2	3.0, 1.6	3.2, 2.0	3.0, 1.9	9, 5	8.1, 3.2	9.4, 4.1	7.9, 4.8	10, 10	8.7, 14.8	6.6, 3.0	6.4, 4.1	12, 8	6.8, 5.2	7.4, 5.0	6.2, 4.6	9, 12	4.1, 3.8	4.6, 4.3	5.5, 9.9	2.2, 0.8
	229, 2	6.4, 0.9	8.3, 0.8	8.0, 0.0	23, 3	15.7, 2.8	22.3, 3.0	23.4, 0.0	55, 3	89.8, 2.5	15.4, 2.7	22.2, 0.0	36, 3	23.2, 1.7	18.9, 2.5	16.1, 0.0	65, 1	16.2, 0.8	19.8, 0.8	51.6, 0.0	5.2, 1.3
Avg. ${HD}_{A}^{3}$	0.20	0.11	0.10	0.11	0.38	0.39	0.50	0.40	0.31	0.22	0.26	0.23	0.42	0.16	0.21	0.17	0.09	0.03	0.04	0.03	0.05
	6.70,35.86	0.17,0.16	0.19,0.21	0.18, 0.19	0.59, 0.40	0.51, 0.37	0.62, 0.45	0.57, 0.63	0.51, 0.63	0.52, 1.47	0.32, 0.21	0.32, 0.34	0.79, 0.95	0.31, 0.37	0.37, 0.46	0.29, 0.32	0.21, 0.37	0.06, 0.08	0.07, 0.07	0.17, 0.52	0.05, 0.03
	206.36,0.06	0.74,0.02	0.98,0.02	0.74, 0.00	1.77, 0.16	1.90,0.12	2.15, 0.15	2.96, 0.00	3.52, 0.10	8.63, 0.06	0.93, 0.10	1.86, 0.00	3.54, 0.08	1.25, 0.04	1.97, 0.05	1.24, 0.00	2.08, 0.01	0.37, 0.01	0.28, 0.01	2.83, 0.00	0.17, 0.02
PDV	12	4	3.8	3	12	11	12.0	9	5	4	5.8	4	6	5	4.6	4	3	2	1.9	1	1.3
	17, 23	6, 5	6.2, 5.7	6, 6	15, 15	14, 16	15.3, 18.8	14, 20	7, 8	7, 7	6.8, 4.2	7, 8	14, 21	9, 13	10.6, 15.2	7, 11	4, 3	2, 2	2.3, 2.0	3, 5	1.9, 1.8
	133, 0	24, 0	26.7, 0.0	26, 0	89, 1	95, 0	110.3, 0.9	118, 0	36, 0	35, 1	18.0, 0.5	37, 0	92, 0	54, 0	64.9, 0.7	47, 0	15, 0	9, 0	9.2, 0.1	25, 0	7.6, 0.0

¹Data in each cell is organized as row 1 = Median, row 2 = Mean, Standard deviation, row 3 = Max, Min; ¹M_nnUnet = model trained with segments only, M_seg+spleen = Model trained with Segments and Spleen as labels, M_vess = Model trained with segments as label and vessel as color channel; ^2aIntraMD = Intra-observer mean dice,^2bIntrerMD = Inter-observer mean dice, ³HD = Hausdorff distance (95 = 95th percentile and A = Average) in mm; PDV = percent difference in volume.