Automated Diagnosis of Major Depressive Disorder Using Brain Effective Connectivity and 3D Convolutional Neural Network

Major depressive disorder (MDD), which is also known as unipolar depression, is one of the leading sources of functional frailty. MDD is mostly a chronic disorder that requires a long duration of treatment and clinical management. One of the critical issues in MDD treatment is the need for it’s early diagnosis. Conventional tools in MDD diagnosis are based on questionnaires and other forms of psychiatric evaluations. However, the subjective nature of these tools may lead to misleading inferences. Recently, brain electroencephalography (EEG) signals have been used for the quantitative diagnosis of MDD. Nevertheless, a further improvement of the proposed methods in terms of accuracy and clinical utility is required. In this study, EEG signals from 30 MDD and 30 healthy control (HC) are used to estimate the effective connectivity within the brain default mode network (DMN). Then, effective connections between the major six regions of the DMN are used to train and test a three-dimensional (3D) convolutional neural network. Here, connectivity samples generated from half of the subjects are used for training while the rest are used for testing. The results show that the proposed MDD diagnosis algorithm achieved 100% accuracy,sensitivity and specificity in classifying MDD and HC test subjects.

[1]  Hanna Damasio,et al.  Impairment of social and moral behavior related to early damage in human prefrontal cortex , 1999, Nature Neuroscience.

[2]  Morris Moscovitch,et al.  Cognitive contributions of the ventral parietal cortex: an integrative theoretical account , 2012, Trends in Cognitive Sciences.

[3]  G. Huston.  The Hospital Anxiety and Depression Scale. , 1987, The Journal of rheumatology.

[4]  Katarzyna J. Blinowska,et al.  A new method of the description of the information flow in the brain structures , 1991, Biological Cybernetics.

[5]  A. Aleman,et al.  Lateral parietal cortex in the generation of behavior: implications for apathy , 2019, Progress in Neurobiology.

[6]  Sanchita Paul,et al.  Classification of Depression Patients and Normal Subjects Based on Electroencephalogram (EEG) Signal Using Alpha Power and Theta Asymmetry , 2019, Journal of Medical Systems.

[7]  M. Oscar-Berman.  Function and Dysfunction of Prefrontal Brain Circuitry in Alcoholic Korsakoff’s Syndrome , 2012, Neuropsychology Review.

[8]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[9]  W. Hesse,et al.  The use of time-variant EEG Granger causality for inspecting directed interdependencies of neural assemblies , 2003, Journal of Neuroscience Methods.

[10]  P. Skudlarski,et al.  Brain Connectivity Related to Working Memory Performance , 2006, The Journal of Neuroscience.

[11]  A. Cavanna,et al.  The precuneus: a review of its functional anatomy and behavioural correlates. , 2006, Brain : a journal of neurology.

[12]  B. Mwangi,et al.  The impact of machine learning techniques in the study of bipolar disorder: A systematic review , 2017, Neuroscience & Biobehavioral Reviews.

[13]  Peter Fransson,et al.  The precuneus/posterior cingulate cortex plays a pivotal role in the default mode network: Evidence from a partial correlation network analysis , 2008, NeuroImage.

[14]  Vinod Menon,et al.  Functional connectivity in the resting brain: A network analysis of the default mode hypothesis , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[15]  C. Rosazza,et al.  Resting-state brain networks: literature review and clinical applications , 2011, Neurological Sciences.

[16]  Arnaud Delorme,et al.  EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis , 2004, Journal of Neuroscience Methods.

[17]  Gina F. Humphreys,et al.  Fusion and Fission of Cognitive Functions in the Human Parietal Cortex , 2014, Cerebral cortex.

[18]  Aamir Saeed Malik,et al.  A wavelet-based technique to predict treatment outcome for Major Depressive Disorder , 2017, PloS one.

[19]  Marta López,et al.  Brainwaves Oscillations as a Potential Biomarker for Major Depression Disorder Risk , 2020, Clinical EEG and neuroscience.

[20]  Jian Shen,et al.  EEG-based Depression Detection Using Convolutional Neural Network with Demographic Attention Mechanism , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[21]  Karl J. Friston,et al.  Dynamic causal modelling , 2003, NeuroImage.

[22]  Karl J. Friston,et al.  Analysing connectivity with Granger causality and dynamic causal modelling , 2013, Current Opinion in Neurobiology.

[23]  Koichi Sameshima,et al.  Using partial directed coherence to describe neuronal ensemble interactions , 1999, Journal of Neuroscience Methods.

[24]  Aamir Saeed Malik,et al.  A machine learning framework involving EEG-based functional connectivity to diagnose major depressive disorder (MDD) , 2018, Medical & Biological Engineering & Computing.

[25]  M. Corbetta,et al.  Control of goal-directed and stimulus-driven attention in the brain , 2002, Nature Reviews Neuroscience.

[26]  Mario F. Juruena,et al.  Genetic biomarkers for differential diagnosis of major depressive disorder and bipolar disorder: A systematic and critical review , 2019, Behavioural Brain Research.

[27]  M. Desmurget,et al.  Movement Intention After Parietal Cortex Stimulation in Humans , 2009, Science.

[28]  Tzyy-Ping Jung,et al.  Real-time neuroimaging and cognitive monitoring using wearable dry EEG , 2015, IEEE Transactions on Biomedical Engineering.

[29]  N. Fogelson,et al.  Functional connectivity abnormalities during processing of predictive stimuli in patients with major depressive disorder , 2019, Brain Research.

[30]  Firas H. Kobeissy,et al.  Psychiatric Disorders , 2012, Methods in Molecular Biology.

[31]  Joel E. W. Koh,et al.  A Novel Depression Diagnosis Index Using Nonlinear Features in EEG Signals , 2015, European Neurology.

[32]  Gokben Hizli Sayar,et al.  Major Depressive Disorder Classification Based on Different Convolutional Neural Network Models: Deep Learning Approach , 2020, Clinical EEG and neuroscience.

[33]  Aamir Saeed Malik,et al.  Review on EEG and ERP predictive biomarkers for major depressive disorder , 2015, Biomed. Signal Process. Control..

[34]  U. Rajendra Acharya,et al.  Automated EEG-based screening of depression using deep convolutional neural network , 2018, Comput. Methods Programs Biomed..

[35]  J. Grafman,et al.  Human prefrontal cortex: processing and representational perspectives , 2003, Nature Reviews Neuroscience.

[36]  Julius Georgiou,et al.  EEG-Based Automatic Classification of ‘Awake’ versus ‘Anesthetized’ State in General Anesthesia Using Granger Causality , 2012, PloS one.

[37]  Abraham Z. Snyder,et al.  A default mode of brain function: A brief history of an evolving idea , 2007, NeuroImage.

[38]  Yuzo Hosoya.  Elimination of Third‐series Effect and Defining Partial Measures of Causality , 2001 .

[39]  Xiaowei Li,et al.  A Deep Learning Approach for Mild Depression Recognition Based on Functional Connectivity Using Electroencephalography , 2020, Frontiers in Neuroscience.

[40]  J. Geweke,et al.  Measurement of Linear Dependence and Feedback between Multiple Time Series , 1982 .

[41]  Tobias Grossmann,et al.  The role of medial prefrontal cortex in early social cognition , 2013, Front. Hum. Neurosci..

[42]  Lijuan Duan,et al.  Machine Learning Approaches for MDD Detection and Emotion Decoding Using EEG Signals , 2020, Frontiers in Human Neuroscience.

[43]  Yingjie Li,et al.  Anxiety and Depression Diagnosis Method Based on Brain Networks and Convolutional Neural Networks , 2020, 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC).

[44]  G. Arbanas.  Diagnostic and Statistical Manual of Mental Disorders (DSM-5) , 2015 .

[45]  Sanchita Paul,et al.  Electroencephalogram (EEG) Signal Analysis for Diagnosis of Major Depressive Disorder (MDD): A Review , 2018, Nanoelectronics, Circuits and Communication Systems.

[46]  G L Shulman,et al.  INAUGURAL ARTICLE by a Recently Elected Academy Member:A default mode of brain function , 2001 .

[47]  J. Geweke,et al.  Measures of Conditional Linear Dependence and Feedback between Time Series , 1984 .

[48]  O. Sporns,et al.  Mapping the Structural Core of Human Cerebral Cortex , 2008, PLoS biology.

[49]  Sanchita Paul,et al.  Detection of major depressive disorder using linear and non-linear features from EEG signals , 2018, Microsystem Technologies.

[50]  S. Olbrich,et al.  Functional connectivity in major depression: Increased phase synchronization between frontal cortical EEG-source estimates , 2014, Psychiatry Research: Neuroimaging.

[51]  Wajid Mumtaz,et al.  A deep learning framework for automatic diagnosis of unipolar depression , 2019, Int. J. Medical Informatics.

[52]  Karl J. Friston,et al.  A systematic framework for functional connectivity measures , 2014, Front. Neurosci..