Major Depressive Disorder Classification Based on Different Convolutional Neural Network Models: Deep Learning Approach

Abstract

<jats:p> The human brain is characterized by complex structural, functional connections that integrate unique cognitive characteristics. There is a fundamental hurdle for the evaluation of both structural and functional connections of the brain and the effects in the diagnosis and treatment of neurodegenerative diseases. Currently, there is no clinically specific diagnostic biomarker capable of confirming the diagnosis of major depressive disorder (MDD). Therefore, exploring translational biomarkers of mood disorders based on deep learning (DL) has valuable potential with its recently underlined promising outcomes. In this article, an electroencephalography (EEG)-based diagnosis model for MDD is built through advanced computational neuroscience methodology coupled with a deep convolutional neural network (CNN) approach. EEG recordings are analyzed by modeling 3 different deep CNN structure, namely, ResNet-50, MobileNet, Inception-v3, in order to dichotomize MDD patients and healthy controls. EEG data are collected for 4 main frequency bands (Δ, θ, α, and β, accompanying spatial resolution with location information by collecting data from 19 electrodes. Following the pre-processing step, different DL architectures were employed to underline discrimination performance by comparing classification accuracies. The classification performance of models based on location data, MobileNet architecture generated 89.33% and 92.66% classification accuracy. As to the frequency bands, delta frequency band outperformed compared to other bands with 90.22% predictive accuracy and area under curve (AUC) value of 0.9 for ResNet-50 architecture. The main contribution of the study is the delineation of distinctive spatial and temporal features using various DL architectures to dichotomize 46 MDD subjects from 46 healthy subjects. Exploring translational biomarkers of mood disorders based on DL perspective is the main focus of this study and, though it is challenging, with its promising potential to improve our understanding of the psychiatric disorders, computational methods are highly worthy for the diagnosis process and valuable in terms of both speed and accuracy compared with classical approaches. </jats:p>

Discriminative Power of EEG-Based Biomarkers in Major Depressive Disorder: A Systematic Review

“…However, it is worth noting that recent reviews are specifically dedicated to this field of research [9], [157] and suggest that these approaches would be a useful methodology to implement in the MDD diagnosis process. As pointed out by some authors [158], [159], the use of both machine and deep learning techniques can provide valuable biomarkers in discriminating MDD from other mood disorders, and can also be adapted to the computer-aided diagnosis of depression. Overall, the present work has also some strengths.…”

Depression Diagnosis by Deep Learning Using EEG Signals: A Systematic Review

“…C. Uyulan et al [44] suggested three convolutional neural network-based models which were integrated with advanced computational neuroscience methodology named ResNet-50, MobileNet, and Inception-v3 to apply to the EEG recorded signals from both left and right hemispheres with eye closed states. The produced artifacts as a result of eye and muscle activities were removed by the wavelet transform method.…”

Depression Diagnosis by Deep Learning Using EEG Signals: A Systematic Review

“…C. Uyulan et al [45] suggested three convolutional neural network-based models which integrated with advanced computational neuroscience methodology named ResNet-50, MobileNet, and Inception-v3 to apply to the EEG recorded signals from both left and right hemispheres with eye closed states. The produced artifacts as a result of eye and muscle activities were removed by the wavelet transform method.…”