Multilayer brain network combined with deep convolutional neural network for detecting major depressive disorder

Dang, Weidong; Gao, Zhong-Ke; Sun, Xinlin; Li, Rumei; Cai, Qing; Grebogi, Celso

doi:10.1007/s11071-020-05665-9

Cited by 22 publications

(20 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[51] Visual [52] N/A [53], [54], [55], [56], [57], [58], [59], [60], [61], [45], [33], [62], [63], [64], [65], [66] Depression both mild and severe stages Emotional Note reading [67] Audio [68] Emotional Picture [69], [70], [71], [72] Distractor and target [73] N/A [74], [75], [76], [77], [78], [79], [80], [81], [82], [83], [84], [85], [86], [87], [88] Depression for other reasons (stress/ epilepsy) Audio [89], [90] N/A [91], [92], [93] This…”

Section: Mild Depressionmentioning

confidence: 99%

“…It provides the possible necessary information at a given point of time to have the right prediction through the demonstrated model [86]. Wenya et al and Weidong et al segmented the EEG data into non-overlapping epochs by a time window of 10s [49] and 2s [54] respectively. However, uses of sliding windows without overlapping can lead a devasting problem into functional connectivity or topological mapping.…”

Section: ) Signal Acquisition and Electrode Placementmentioning

confidence: 99%

“…T-test [68], [86] Genetic Algorithm [101], [56], [100], [120], [113], [50], [87], [72] RankSearch Algorithm [61], [113], [72] Others (MRMR, LFS) [71], [113] Uses of deep learning Method [99], [54], [116], [121], [122], [33] 7) CLINICAL QUESTIONNAIRE BASED ASSESSMENTS Many well-known questionnaire assessments have been used to detect the depression category. According to the score calculated through the patient's interview, psychiatrists can detect depression by the degree of severity (mild, moderate, or severe).…”

Section: Feature Selection Technique Research Articlesmentioning

confidence: 99%

See 2 more Smart Citations

Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Depression is the most common mental illness, which has become the major cause of fear and suicidal mortality or tendencies. Currently, about 10% of the world population has been suffering from depression. The classical approach for detecting depression relies on the clinical questionnaire, which depends on the patients' responses as well as observing their behavioral activities. However, there is no established method to detect depression from EEG biomarkers. Therefore, exploration of EEG biomarkers for depression assessments is vital and has a great potential to improve our understanding and clinical interventions. In this study, we have conducted a systematic review of 52 research articles using the PRISMA-P systematic review protocol, where we analyzed their research methodologies and outcomes. We categorized the experimentations in these articles according to their physical and psychological aspects scaled by the commonly used clinical questionnaire-based assessments. This study finds that the negative stimuli are the better identification strategies for evaluating depression through EEG signals. From this exploration, researchers observed that the Neural Connectivity Analysis and Brain Topological Mapping have huge potentials for finding depression biomarkers, and it is evident that the right-side hemisphere and frontal and parietal-occipital cortex are distinct regions to detect depression using EEG signals. For this mechanism, researchers are using many signal processing and machine learning approaches. In the case of filtering, Independent Component Analysis (ICA) is commonly used to eliminate physiological and non-physiological artifacts. Among machine learning approaches, Convolutional Neural Network (CNN) and Support Vector Machine (SVM) showed better performance for classifying healthy and depressed brains. The authors hope, this study will create an opportunity to explore more in the future for EEG as diagnostic tools by analyzing brain functional connectivity for focusing on clinical interventions.

show abstract

Section: Mild Depressionmentioning

confidence: 99%

Section: ) Signal Acquisition and Electrode Placementmentioning

confidence: 99%

Section: Feature Selection Technique Research Articlesmentioning

confidence: 99%

See 1 more Smart Citation

Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…According to this approach, new drugs as well as treatments can be discovered. Moreover, these researches can provide a new perspective for the study of the pathogenesis of some psychiatric disorders and neurodegenerative diseases such as depression, Parkinson's disease and Alzheimer's disease [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear computational models of dynamical coding patterns in depression and normal rats: from electrophysiology to energy consumption

Wang

Zhang

2022

Nonlinear Dyn

View full text Add to dashboard Cite

Major depressive disorder (MDD) is one of the most serious neuropsychiatric disorders. Exploring the pathogenesis and dynamical coding patterns of MDD can provide new targets for clinical drug treatment and new ideas for the research of other neuropsychiatric and neurodegenerative diseases. We selected the medium spiny neuron (MSN) of nucleus accumbens (NAc) as the research objective. NAc is located in the dopaminergic pathway, regulating rewards, emotions and other behaviors. Abnormalities in these behaviors are considered as the main clinical symptoms of MDD. We simulated the different spike patterns of MSNs in MDD group and control group by dynamical Hodgkin–Huxley model. The simulated results can match the electrophysiological experiments, which occurred due to following reasons: (1) The external stimulus current of MDD group was amplified by the local neural microcircuit; (2) the selective permeability to sodium was abnormally decreased; and (3) the dopamine D2 receptor signaling pathway was abnormal in the MDD group. Furthermore, we proposed a dynamical energy model, and the energy results demonstrated that the energy cost in MDD group was lower, which led to persistent depression in patients with MDD. Simultaneously, the negative-to-total energy ratio of MSN in MDD group was higher than that in control group, and the delay time of the power peak and the potential peak in MDD group was shorter than that in the control group. The results showed that the abnormal firing patterns were the direct cause of abnormal behaviors of MDD and indicated that subthreshold activities of MDD group were more intense.

show abstract

“…The difference of deep learning from the traditional machine learning algorithms is that deep learning makes automatic learning from a database (image, audio, video etc.) possible instead of using predetermined rules [10]- [12]. To the best of the author knowledge, there is no deep learning-based classi cation study on the images of chaotic systems.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Classification of Time Series of Chaotic Systems over Graphic Images

Uzun¹,

Kaçar²,

Arıcıoğlu³

2021

Preprint

View full text Add to dashboard Cite

In this study, for the first time in the literature, identification of different chaotic systems by classifying graphic images of their time series with deep learning methods is aimed. For this purpose, a data set is generated that consists of the graphic images of time series of the most known three chaotic systems: Lorenz, Chen, and Rossler systems. The time series are obtained for different parameter values, initial conditions, step size and time lengths. After generating the data set, a high-accuracy classification is performed by using transfer learning method. In the study, the most accepted deep learning models of the transfer learning methods are employed. These models are SqueezeNet, VGG-19, AlexNet, ResNet50, ResNet101, DenseNet201, ShuffleNet and GoogLeNet. As a result of the study, classification accuracy is found between 96% and 97% depending on the problem. Thus, this study makes association of real time random signals with a mathematical system possible.

show abstract

Multilayer brain network combined with deep convolutional neural network for detecting major depressive disorder

Cited by 22 publications

References 48 publications

Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review

Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review

Nonlinear computational models of dynamical coding patterns in depression and normal rats: from electrophysiology to energy consumption

Deep Learning Based Classification of Time Series of Chaotic Systems over Graphic Images

Contact Info

Product

Resources

About