Table 3.

Comparison of parcellation performance as measured by Dice score on the 5 brain regions analyzed in this work.

	PC.L	LO.L	InP.L	EC.L	RMF.L	PC.R	LO.R	InP.R	EC.R	RMF.R	Average
node2vec	0.65	0.67	0.63	0.68	0.65	0.67	0.67	0.66	0.68	0.67	0.66
struc2vec	0.64	0.65	0.60	0.65	0.66	0.65	0.66	0.64	0.65	0.66	0.64
GCN	0.65	0.70	0.67	0.71	0.67	0.70	0.69	0.69	0.73	0.68	0.69
SGCN, Supervised non-CL	0.72	0.71	0.71	0.79	0.72	0.74	0.72	0.73	0.78	0.73	0.73
SGCN (2 layers) + CL + MLP (2 layers)	0.86	0.89	0.88	0.83	0.89	0.88	0.88	0.89	0.85	0.89	0.87
SGCN (3 layers)+ CL + MLP (2 layers)	0.88	0.87	0.84	0.80	0.85	0.85	0.86	0.89	0.87	0.89	0.86
SGCN (2 layers) + CL + MLP (3 layers)	0.89	0.86	0.87	0.84	0.86	0.89	0.88	0.88	0.87	0.87	0.87

node2vec: unsupervised node feature embedding by node2vec, followed by a 2-layer MLP. struct2vec: unsupervised node feature embedding by strct2vec, followed by a 2-layer MLP. GCN: substituting SGCN with traditional GCN, keeping all other components as the same. SGCN, supervised non-CL: the single stage, end-to-end, supervised framework for parcellation based on SGCN. SGCN (2 layers) + CL + MLP (2 layers): the current setting used by SGCP. SGCN (3 layers) + CL + MLP (2 layers) and SGCN (2 layers) + CL + MLP (3 layers): settings where the layers in SGCN, and stage 2 MLP are increased to 3 layers, all other components are kept the same. Best parcellation performance for each region among all methods is highlighted in bold text.