Skip to main content
. Author manuscript; available in PMC: 2019 Sep 1.
Published in final edited form as: IEEE Trans Biomed Eng. 2017 Jun 15;65(9):1975–1984. doi: 10.1109/TBME.2017.2715281

Fig. 2.

Fig. 2.

Overview of the computational steps in the 3D CNN framework. All the obtained maps from Fig. 1 are evaluated manually with 10 RSN labels. Then the whole dataset is divided into a training set and testing set. Training module uses the training set to train the weights of the constructed CNN structure and then is applied to the testing set the get the predicted labels.