An automatic segmentation and classification framework for anti-nuclear antibody images

Table 6 Comparisons of number of segmented cells and classification performance between proposed method and CellProfiler evaluated based on PVO, PVD, RAE, and MHD.

Pattern	Detected Cell Number			PVO (%)		PVD (%)		RAE ± Std.		MHD ± Std.
	G. Truth	Proposed	CellProfiler	Proposed	CellProfiler	Proposed	CellProfiler	Proposed	CellProfiler	Proposed	CellProfiler
Diffuse	251	157	107	87.89	84.75	24.23	30.50	0.6386 ± 0.42	0.5248 ± 0.36	250.90 ± 228.42	510.69 ± 250.56
Peripheral	191	153	97	93.47	72.43	13.06	55.15	0.3039 ± 0.35	0.5120 ± 0.31	87.15 ± 182.86	602.36 ± 267.78
Nucleolar	285	175	101	91.94	84.90	16.12	30.20	0.4777 ± 0.41	0.6445 ± 0.33	157.99 ± 208.70	560.73 ± 225.77
Coarse speckled	363	260	150	92.35	87.84	15.31	24.32	0.3506 ± 0.36	0.7038 ± 0.21	101.90 ± 199.74	556.02 ± 261.51
Fine speckled	117	67	36	91.27	91.22	17.46	17.55	0.5423 ± 0.41	0.8637 ± 0.13	173.20 ± 13.16	458.46 ± 21.41
Discrete speckled	216	195	125	78.03	69.64	43.95	60.71	0.5457 ± 0.37	0.7277 ± 0.18	143.99 ± 202.59	504.55 ± 242.68

ISSN: 1475-925X