. Author manuscript; available in PMC: 2023 Jul 10.

Published in final edited form as: Int J Comput Assist Radiol Surg. 2023 Apr 20;18(6):1025–1032. doi: 10.1007/s11548-023-02893-3

Table 1.

Evaluation of our LiverMatch against Predator network according to the IR and MS evaluation metrics (mean ± std dev.) for different inlier radii $σ$ . *p < 0.05 indicates a statistically significant difference between the LiverMatch and Predator results.

$σ (m m)$	0	1	2	3	4	5
IR%
*Predator[12]	26.82 ± 4.99	26.94 ± 5.01	27.89 ± 5.10	30.61 ± 5.39	35.36 ± 5.93	41.76 ± 6.60
LiverMatch	37.68 ± 5.91	37.91 ± 5.94	39.58 ± 6.13	43.46 ± 6.61	49.21 ± 7.29	55.69 ± 8.04
MS%
*Predator[12]	6.90 ± 1.84	6.93 ± 1.84	7.17 ± 1.87	7.85 ± 1.95	9.04 ± 2.11	10.65 ± 2.32
LiverMatch	16.95 ± 3.74	17.05 ± 3.75	17.79 ± 3.83	19.50 ± 4.02	22.04 ± 4.30	24.91 ± 4.64