Fig. 6.

The DL model trained on the HCP cohort generalizes well to the PNC. (a) Personalized FNs of three randomly selected PNC subjects, identified by the DL model trained on HCP cohort, in sagittal view (the second, third, and fourth rows), isolines of the FNs at a value of 0.15 in different colors (the fifth row), and their corresponding average FNs of all testing HCP subjects (the first row). (b) Personalized FNs computed using the DL model had significantly higher functional within-network homogeneity than those computed using the spatially-regularized NMF ($p<{10}^{-5}$, Wilcoxon signed rank test). (c) Age prediction performance (partial correlation coefficients) of the personalized FNs, obtained with one run of the 2-fold cross-validation. Data points in different colors represent the prediction results of different folds in the 2-fold cross-validation. (d, e) Prediction accuracy measured with partial correlation coefficients and MAE of 100 runs of the 2-fold cross-validation and the null distribution of prediction accuracy from permutation test (1000 runs of 2-fold cross-validation using permuted data).