fMRI Feature Extraction Model for ADHD Classification Using Convolutional Neural Network

Biomedical intelligence provides a predictive mechanism for the automatic diagnosis of diseases and disorders. With the advancements of computational biology, neuroimaging techniques have been used extensively in clinical data analysis. Attention deficit hyperactivity disorder (ADHD) is a psychiatric disorder, with the symptomology of inattention, impulsivity, and hyperactivity, in which early diagnosis is crucial to prevent unwelcome outcomes. This study addresses ADHD identification using functional magnetic resonance imaging (fMRI) data for the resting state brain by evaluating multiple feature extraction methods. The features of seed-based correlation (SBC), fractional amplitude of low-frequency fluctuation (fALFF), and regional homogeneity (ReHo) are comparatively applied to obtain the specificity and sensitivity. This helps to determine the best features for ADHD classification using convolutional neural networks (CNN). The methodology using fALFF and ReHo resulted in an accuracy of 67%, while SBC gained an accuracy between 84% and 86% and sensitivity between 65% and 75%.

[1]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[2]  NeuroData,et al.  Towards Automated Analysis of Connectomes: The Configurable Pipeline for the Analysis of Connectomes , 2015 .

[3]  XiaoChengwei,et al.  Using Spearman's correlation coefficients for exploratory data analysis on big dataset , 2016 .

[4]  Michael P Milham,et al.  Toward systems neuroscience of ADHD: a meta-analysis of 55 fMRI studies. , 2012, The American journal of psychiatry.

[5]  Eric Achten,et al.  Dysfunctional modulation of default mode network activity in attention-deficit/hyperactivity disorder. , 2015, Journal of abnormal psychology.

[6]  Naixue Xiong,et al.  Spatio-temporal deep learning method for ADHD fMRI classification , 2019, Inf. Sci..

[7]  G. Glover.  Overview of functional magnetic resonance imaging. , 2011, Neurosurgery clinics of North America.

[8]  Dulani Meedeniya,et al.  A Review of Supportive Computational Approaches for Neurological Disorder Identification , 2020 .

[9]  Luc Van Gool,et al.  Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection , 2016 .

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

[11]  Boris Kovatchev,et al.  Calibration of ADHD Assessments Across Studies: A Meta-Analysis Tool , 2005, Applied psychophysiology and biofeedback.

[12]  Sung-Bae Cho,et al.  Machine learning approaches for cognitive state classification and brain activity prediction: A survey , 2015 .

[13]  Chunming Rong,et al.  Using Spearman's correlation coefficients for exploratory data analysis on big dataset , 2015, Concurr. Comput. Pract. Exp..

[14]  Yulin Zhang,et al.  A feature selection method for classification of ADHD , 2017, 2017 4th International Conference on Information, Cybernetics and Computational Social Systems (ICCSS).

[15]  I. D. Rubasinghe,et al.  Automated neuroscience decision support framework , 2020 .

[16]  Chunyan Miao,et al.  3D CNN Based Automatic Diagnosis of Attention Deficit Hyperactivity Disorder Using Functional and Structural MRI , 2017, IEEE Access.

[17]  Mario Quarantelli,et al.  Relationship between simultaneously acquired resting-state regional cerebral glucose metabolism and functional MRI: A PET/MR hybrid scanner study , 2015, NeuroImage.

[18]  Chaozhe Zhu,et al.  An improved approach to detection of amplitude of low-frequency fluctuation (ALFF) for resting-state fMRI: Fractional ALFF , 2008, Journal of Neuroscience Methods.

[19]  Agatha Lenartowicz,et al.  Use of EEG to Diagnose ADHD , 2014, Current Psychiatry Reports.

[20]  Yingli Lu,et al.  Regional homogeneity approach to fMRI data analysis , 2004, NeuroImage.

[21]  Daniel S. Margulies,et al.  The Neuro Bureau ADHD-200 Preprocessed repository , 2016, NeuroImage.

[22]  Huiguang He,et al.  Classification of ADHD children through multimodal magnetic resonance imaging , 2012, Front. Syst. Neurosci..

[23]  L. Rohde,et al.  Evaluation of Pattern Recognition and Feature Extraction Methods in ADHD Prediction , 2012, Front. Syst. Neurosci..

[24]  Jennifer M Walz,et al.  Dynamic regional phase synchrony (DRePS) , 2016, Human brain mapping.

[25]  Siti Nurulain Mohd Rum,et al.  Artificial Intelligence in Diagnosing Tuberculosis: A Review , 2019, International Journal on Advanced Science, Engineering and Information Technology.

[26]  B. Biswal,et al.  Network homogeneity reveals decreased integrity of default-mode network in ADHD , 2008, Journal of Neuroscience Methods.

[27]  Ming Zhang,et al.  Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs , 2019, Neurocomputing.

[28]  Tongsheng Zhang,et al.  Extreme Learning Machine-Based Classification of ADHD Using Brain Structural MRI Data , 2013, PloS one.

[29]  Xi-Nian Zuo,et al.  REST: A Toolkit for Resting-State Functional Magnetic Resonance Imaging Data Processing , 2011, PloS one.

[30]  Bogdan Wilamowski,et al.  Fully Connected Cascade Artificial Neural Network Architecture for Attention Deficit Hyperactivity Disorder Classification From Functional Magnetic Resonance Imaging Data , 2015, IEEE Transactions on Cybernetics.

[31]  B. Horta,et al.  The worldwide prevalence of ADHD: a systematic review and metaregression analysis. , 2007, The American journal of psychiatry.

[32]  Yanchun Zhang,et al.  Medical Big Data: Neurological Diseases Diagnosis Through Medical Data Analysis , 2016, Data Science and Engineering.

[33]  Sampath Jayarathna,et al.  A Survey of Attention Deficit Hyperactivity Disorder Identification Using Psychophysiological Data , 2019, Int. J. Online Biomed. Eng..

[34]  Rodolfo Abreu,et al.  EEG-Informed fMRI: A Review of Data Analysis Methods , 2018, Front. Hum. Neurosci..

[35]  Xu Zhang,et al.  Deep Learning Methods to Process fMRI Data and Their Application in the Diagnosis of Cognitive Impairment: A Brief Overview and Our Opinion , 2018, Front. Neuroinform..

[36]  Dulani Meedeniya,et al.  Ultrasound Nerve Segmentation Using Deep Probabilistic Programming , 2019 .