Skip to main content

View full-text article in PMC

. Author manuscript; available in PMC: 2024 Jul 8.

Published in final edited form as: Med Image Anal. 2023 Aug 25;90:102939. doi: 10.1016/j.media.2023.102939

Table 11.

Single model performance for the whole brain segmentation task. Models are trained with the same training/validation data.

Method	Colin		CANDI
Method	DSC	HD	DSC	HD
nnUNet (Isensee et al., 2021)	0.7062	14.0101	0.3930	inf
TransBTS (Wang et al., 2021a)	0.6542	inf	0.5991	inf
nnFormer (Zhou et al., 2021a)	0.7007	10.423	0.6420	inf
CoTr (Xie et al., 2021b)	0.7268	10.2561	0.6923	inf
UNETR (Hatamizadeh et al., 2022)	0.7328	10.216	0.6810	13.3172
SwinUNETR (Tang et al., 2022)	0.6853	21.4812	0.6536	34.5212
SLANT (Huo et al., 2019)	0.7301	9.9470	0.6977	9.5000

UNesT	0.7467	11.0358	0.7022	8.8902