Image-Based Early Detection of Alzheimer's Disease by Using Adaptive Structural Deep Learning

Deep learning has been a successful model which can effectively represent several features of input space and remarkably improve image recognition performance on the deep architectures. In our research, an adaptive structural learning method of restricted Boltzmann machine (adaptive RBM) and deep belief network (adaptive DBN) has been developed as a deep learning model. The models have a self-organize function which can discover an optimal number of hidden neurons for given input data in a RBM by neuron generation-annihilation algorithm and can obtain an appropriate number of RBMs as hidden layers. In this paper, the proposed model was applied to MRI and PET image datasets in ADNI digital archive for the early detection of mild cognitive impairment (MCI) and Alzheimer's disease (AD). Two kinds of deep learning models were constructed to classify the MRI and PET images. For the training set, our model showed 99.6 and 99.4% classification accuracy for MRI and PET images. For the test set, the model showed 87.6 and 98.5% accuracy for them. Our model achieved the highest classification accuracy among the other CNN models.