A combination of 3-D discrete wavelet transform and 3-D local binary pattern for classification of mild cognitive impairment

Table 3 Comparison of performance of the proposed method with existing works

	Method	Accuracy (%)	Sensitivity (%)	Specificity (%)
MCI-C vs. MCI-NC	Colliot et al. 2008 [13]	66	66	65
	Chupin et al. 2009 [15]		65	68
	Andrea Chincarini et.al., 2011 [16]	_	72	65
	Chong-Yaw Wee et.al., 2013 [19].	75.05	63.52	84.41
	Tong Tong et al., 2014 [20].	72	69	74
	Suk et al. 2014 [21]	72.42	36.70	90.98
	Liu et al. 2018 [24]	72.08	75.11	71.05
	3D-DWT + LBP12	0.8877	0.8916	0.9016
MCI vs. CN	Pennanen et al.2004 [12]	65.9	66.2	65.5
	Chupin et al. 2009 [15]		75	74
	Carlton Chu et al., 2011 [17]	67.3	_	_
	Chong-Yaw Wee et.al., 2013 [19].	92.33	83.55	83.95
	Suk et al. 2014 [21]	84.24	99.58	53.79
	Ahmed et al. 2015 [23]	78.22	70.73	83.34
	Khedher et al. 2015 [22]	80.27	73.51	82.70
	Liu et al. 2018 [24]	85.79	88.91	80.34
	Proposed Model	0.9031	0.9015	0.9022

ISSN: 1472-6947