(b) Results using 28 test samples/class obtained by resampling

Index	Proposed method	Modified JIS with 3	TNM classification with 2	Tokyo score with 2
Accuracy	0.67 [0.66, 0.69]	0.70 [0.69, 0.71]	0.55 [0.54, 0.56]	0.57 [0.55, 0.58]
Sensitivity, recall	0.86	0.57	0.96	0.71
Specificity	0.49 [0.46, 0.52]	0.83 [0.81, 0.85]	0.14 [0.12, 0.16]	0.42 [0.39, 0.44]
F1 measure	0.73 [0.72, 0.73]	0.66 [0.65, 0.67]	0.68 [0.68, 0.69]	0.62 [0.62, 0.63]
Youden index	0.35 [0.32, 0.37]	0.40 [0.38, 0.42]	0.10 [0.08, 0.12]	0.13 [0.11, 0.16]
Diagnostic odds ratio	6.03 [5.39, 6.67]	7.88 [6.22, 9.53]	4.62 [3.86, 5.38]	1.95 [1.74, 2.15]