Detection of schizophrenia using hybrid of deep learning and brain effective connectivity image from electroencephalogram signal

• Published in: Computers in biology and medicine Vol. 146; p. 105570
• Main Authors: Bagherzadeh, Sara, Shahabi, Mohsen Sadat, Shalbaf, Ahmad
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.07.2022; Elsevier Limited
• Subjects: Algorithms; Alzheimer's disease; Artificial neural networks; Brain; Causality; Convolutional neural network (CNN); Deep learning; EEG; Effective connectivity; Electroencephalogram (EEG); Electroencephalography; Entropy; Feature extraction; Information flow; Internal Medicine; Long short-term memory; Long short-term memory (LSTM); Medical imaging; Memory; Mental disorders; Nervous system; Neural networks; Neuroimaging; Other; Probability; Schizophrenia; Schizophrenia (SZ); Signal detection; Signal processing; Spatial data; Time series; Transfer entropy (TE); Transfer learning; Wavelet transforms; Electroencephalogram (EEG); Convolutional neural network (CNN); Schizophrenia (SZ); Long short-term memory (LSTM); Effective connectivity; Transfer entropy (TE)
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.105570

Detection of mental disorders such as schizophrenia (SZ) through investigating brain activities recorded via Electroencephalogram (EEG) signals is a promising field in neuroscience. This study presents a hybrid brain effective connectivity and deep learning framework for SZ detection on multichannel EEG signals. First, the effective connectivity matrix is measured based on the Transfer Entropy (TE) method that estimates directed causalities in terms of brain information flow from 19 EEG channels for each subject. Then, TE effective connectivity elements were represented by colors and formed a 19 × 19 connectivity image which, simultaneously, represents the time and spatial information of EEG signals. Created images are used to be fed into the five pre-trained Convolutional Neural Networks (CNN) models named VGG-16, ResNet50V2, InceptionV3, EfficientNetB0, and DenseNet121 as Transfer Learning (TL) models. Finally, deep features from these TL models equipped with the Long Short-Term Memory (LSTM) model for the extraction of most discriminative spatiotemporal features are used to classify 14 SZ patients from 14 healthy controls. Results show that the hybrid framework of pre-trained CNN-LSTM models achieved higher accuracy than pre-trained CNN models. The highest average accuracy and F1-score were achieved using the EfficientNetB0-LSTM model through the 10-fold cross-validation method equal to 99.90% and 99.93%, respectively. Therefore, the superior performance of the hybrid framework of brain effective connectivity images from EEG signals and pre-trained CNN-LSTM models show that the proposed method is highly capable of detecting SZ patients from healthy controls. •Detection of schizophrenia from EEG signals are appropriate technique in neuroscience domain.•A hybrid framework based on two deep learning methods, Convolutional Neural Network and Long Short-Term Memory are proposed to detect schizophrenia.•Novel images based on the effective connectivity measure named Transfer Entropy (TE) were created from EEG signals of schizophrenic patients and healthy subjects.•The highest average accuracy and F1-score were achieved using the EfficientNetB0-LSTM model through the 10-fold Cross-Validation method equal to 99.90% and 99.93%, respectively.