Research on ARKFCM Algorithm Based on Membership Constraint and Bias Field Correction in Neonatal HIE Image Segmentation Method

Table 3

JS quantitative analysis result of the 80th layer of the brain image with a slice thickness of 1 mm, a noise level of 9%, and a gray unevenness level of 20% under the T1 modal and ICMB protocol.

Algorithm	MICO	ARKFCM	GM-ARKFCM (m = 1.8,  = 0.99)	GM-ARKFCM (m = 2.0,  = 0.99)	GM-ARKFCM (m = 2.2,  = 0.99)	GM-ARKFCM (m = 2.4,  = 0.99)
WM	0.764	0.816	0.880	0.883	0.887	0.881
GM	0.726	0.835	0.856	0.870	0.875	0.868
CSF	0.814	0.823	0.838	0.844	0.839	0.841
Average	0.768	0.824	0.858	0.865	0.867	0.863