Detection of early stages of Alzheimer's disease based on MEG activity with a randomized convolutional neural network

The early detection of Alzheimer's disease can potentially make eventual treatments more effective. This work presents a deep learning model to detect early symptoms of Alzheimer's disease using synchronization measures obtained with magnetoencephalography. The proposed model is a novel deep learning architecture based on an ensemble of randomized blocks formed by a sequence of 2D-convolutional, batch-normalization and pooling layers. An important challenge is to avoid overfitting, as the number of features is very high (25755) compared to the number of samples (132 patients). To address this issue the model uses an ensemble of identical sub-models all sharing weights, with a final stage that performs an average across sub-models. To facilitate the exploration of the feature space, each sub-model receives a random permutation of features. The features correspond to magnetic signals reflecting neural activity and are arranged in a matrix structure interpreted as a 2D image that is processed by 2D convolutional networks. The proposed detection model is a binary classifier (disease/non-disease), which compared to other deep learning architectures and classic machine learning classifiers, such as random forest and support vector machine, obtains the best classification performance results with an average F1-score of 0.92. To perform the comparison a strict validation procedure is proposed, and a thorough study of results is provided.