Table 7.

SISS challenge leaderboard after evaluating the 14 participating methods on the testing dataset. The rank is the final measure for ordering the algorithms’ performances relative to each other. The cases column denotes the number of successfully (i.e., all DC> 0) segmented cases. All evaluation measures are given in mean±STD. Please note that the ASSD and HD values were computed excluding the failed cases (they do, however, incur the lowest vacant rank for these cases). The three next-to-last rows display the results obtained with different fusion approaches. The last row shows the inter-observer results for comparison.

Rank	Method	Cases	ASSD (mm)	DC [0,1]	HD (mm)
3.25	UK-Imp2	34/36	05.96 ± 09.38	0.59 ± 0.31	37.88 ± 30.06
3.82	CN-Neu	32/36	03.27 ± 03.62	0.55 ± 0.30	19.78 ± 15.65
5.63	FI-Hus	31/36	08.05 ± 09.57	0.47 ± 0.32	40.23 ± 33.17
6.40	US-Odu	33/36	06.24 ± 05.21	0.43 ± 0.27	41.76 ± 25.11
6.67	BE-Kul2	33/36	11.27 ± 10.17	0.43 ± 0.30	60.79 ± 31.14
6.70	DE-UzL	31/36	10.21 ± 09.44	0.42 ± 0.33	49.17 ± 29.6
7.07	US-Jhu	33/36	11.54 ± 11.14	0.42 ± 0.32	62.43 ± 28.64
7.54	UK-Imp 1	34/36	11.71 ± 10.12	0.44 ± 0.30	70.61 ± 24.59
7.66	CA-USher	27/36	09.25 ± 09.79	0.35 ± 0.32	44.91 ± 32.53
7.92	BE-Kul1	30/36	12.24 ± 13.49	0.37 ± 0.33	58.65 ± 29.99
7.97	CA-McGill	31/36	11.04 ± 13.68	0.32 ± 0.26	40.42 ± 26.98
9.18	SE-Cth	30/36	10.00 ± 06.61	0.38 ± 0.28	72.16 ± 17.32
9.21	DE-Dkfz	35/36	14.20 ± 10.41	0.33 ± 0.28	77.95 ± 22.13
10.99	TW-Ntust	15/36	07.59 ± 06.24	0.16 ± 0.26	38.54 ± 20.36
	majority vote	34/36	11.47 ± 19.89	0.51 ± 0.30	38.11 ± 30.45
	STAPLE	36/36	12.90 ± 10.64	0.44 ± 0.32	71.08 ± 25.03
	SIMPLE	34/36	07.83 ± 14.97	0.57 ± 0.29	29.40 ± 28.11
	inter-observer	36/36	02.02 ± 02.17	0.70 ± 0.20	15.46 ± 13.56