Table 2:

Summary of 10-fold cross-validation^{^a}

	Optimized Image-Processing Condition		Optimal ROI	Likelihood Ratio χ² Test Statistic	P Value	AUC
	Modulation	Smoothing Kernel Size (mm)	Optimal ROI	Likelihood Ratio χ² Test Statistic	P Value	AUC
Test 1	−	Nonsmoothed	Hippocampus	111.92	<.001	0.830
Test 2	−	Nonsmoothed	Hippocampus	113.55	<.001	0.945
Test 2	−	Nonsmoothed	Precuneus	113.55	<.001	0.945
Test 3	−	Nonsmoothed	Hippocampus	120.76	<.001	0.869
Test 3	−	Nonsmoothed	Precuneus	120.76	<.001	0.869
Test 4	−	Nonsmoothed	Hippocampus	126.04	<.001	0.756
Test 4	−	Nonsmoothed	Precuneus	126.04	<.001	0.756
Test 5	−	4	Hippocampus	123.10	<.001	0.871
			Precuneus
			Parahippocampus
Test 6	+	8	Amygdala	118.83	<.001	0.738
			Frontal lobe
			Parietal lobe
Test 7	−	Nonsmoothed	Hippocampus	124.73	<.001	0.836
Test 7	−	Nonsmoothed	Precuneus	124.73	<.001	0.836
Test 8	−	Nonsmoothed	Hippocampus	119.94	<.001	0.871
Test 8	−	Nonsmoothed	Precuneus	119.94	<.001	0.871
Test 9	−	Nonsmoothed	Hippocampus	126.26	<.001	0.851
Test 9	−	Nonsmoothed	Precuneus	126.26	<.001	0.851
Test 10	−	Nonsmoothed	Hippocampus	127.45	<.001	0.787
Test 10	−	Nonsmoothed	Precuneus	127.45	<.001	0.787

↵a Likelihood ratio χ² test statistic and P values were determined by multivariate logistic regression analyses. Optimal image-processing condition and ROI and diagnostic performance are expressed as area under the curve for each validation group.