Best regions for predicting True Positives (TP, i.e. true diagnosis of Autism).

Each row is for one region, each column is for one model (R42 for ResNet50 trained on 42 epochs, D32 for DenseNet121 trained on 32 epochs, D70 for DenseNet121 trained on 70 epochs) and one combination of datasets considered (training+validation+testing 1 sets (“no comorb” for no comorbidity), or all these sets + testing set 2 (“with comorb” for containing subjects with comorbidities), each case returns the number of datasets where the region was important for predicting TP for the model considered. (CSV)