Table 1.

The homogeneity of datasets

Data	Purity B	Purity D
Lung1*2	0.081	0.6
Lung1*3	0.35	0.12
Lung1*4	0.27	0.34
Lung2*3	0.27	0.14
Lung2*4	0.34	0.64
Lung3*4	0.56	0.029

The homogeneity of each pair of independent datasets was measured and presented in terms of Purity _B and Purity _D. The low Purity _B and high Purity _D present the high compatibility of the two datasets for further cross-dataset validation