A deep learning approach for diagnosis of schizophrenia disorder via data augmentation based on convolutional neural network and long short-term memory

Abstract

Schizophrenia (SZ) is a severe, chronic mental disorder without specific treatment. Due to the increasing prevalence of SZ in societies and the similarity of the characteristics of this disease with other mental illnesses such as bipolar disorder, most people are not aware of having it in their daily lives. Therefore, early detection of this disease will allow the sufferer to seek treatment or at least control it. Previous SZ detection studies through machine learning methods, require the extraction and selection of features before the classification process. This study attempts to develop a novel, end-to-end approach based on a 15-layers convolutional neural network (CNN) and a 16-layers CNN- long short-term memory (LSTM) to help psychiatrists automatically diagnose SZ from electroencephalogram (EEG) signals. The deep model uses CNN layers to learn the temporal properties of the signals, while LSTM layers provide the sequence learning mechanism. Also, data augmentation method based on generative adversarial networks is employed over the training set to increase the diversity of the data. Results on a large EEG dataset show the high diagnostic potential of both proposed methods, achieving remarkable accuracy of 98% and 99%. This study shows that the proposed framework is able to accurately discriminate SZ from healthy subject and is potentially useful for developing diagnostic tools for SZ disorder.

Keywords: Convolutional neural networks; Deep learning; Generative adversarial networks; Long short-term memory; Schizophrenia disorder.

Fig. 1

Overview of the proposed framework for diagnosis of SZ

Fig. 2

Generative adversarial network training process [30]

Fig. 3

a Generator and b discriminator network structure

Fig. 4

Generator and discriminator networks loss

Fig. 5

Proposed a CNN and b CNN-LSTM structure

Fig. 6

Performance of CNN on training and validation data with and without DCGAN

Fig. 7

Performance of CNN-LSTM on training and validation data with and without DCGAN

Fig. 8

Confusion matrix in the a CNN and b CNN-LSTM methods for test set