A spectrogram image based intelligent technique for automatic detection of autism spectrum disorder from EEG

Autism spectrum disorder (ASD) is a developmental disability characterized by persistent impairments in social interaction, speech and nonverbal communication, and restricted or repetitive behaviors. Currently Electroencephalography (EEG) is the most popular tool to inspect the existence of neurological disorders like autism biomarkers due to its low setup cost, high temporal resolution and wide availability. Generally, EEG recordings produce vast amount of data with dynamic behavior, which are visually analyzed by professional clinician to detect autism. It is laborious, expensive, subjective, error prone and has reliability issue. Therefor this study intends to develop an efficient diagnostic framework based on time-frequency spectrogram images of EEG signals to automatically identify ASD. In the proposed system, primarily, the raw EEG signals are pre-processed using re-referencing, filtering and normalization. Then, Short-Time Fourier Transform is used to transform the pre-processed signals into two-dimensional spectrogram images. Afterward those images are evaluated by machine learning (ML) and deep learning (DL) models, separately. In the ML process, textural features are extracted, and significant features are selected using principal component analysis, and feed them to six different ML classifiers for classification. In the DL process, three different convolutional neural network models are tested. The proposed DL based model achieves higher accuracy (99.15%) compared to the ML based model (95.25%) on an ASD EEG dataset and also outperforms existing methods. The findings of this study suggest that the DL based structure could discover important biomarkers for efficient and automatic diagnosis of ASD from EEG and may assist to develop computer-aided diagnosis system.

[1]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[2]  Marco Boeri,et al.  The STARTEC Decision Support Tool for Better Tradeoffs between Food Safety, Quality, Nutrition, and Costs in Production of Advanced Ready-to-Eat Foods , 2017, BioMed research international.

[3]  Yanchun Zhang,et al.  Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating , 2016, Comput. Methods Programs Biomed..

[4]  Guido Pasquini,et al.  Testing the Performance of an Innovative Markerless Technique for Quantitative and Qualitative Gait Analysis , 2020, Sensors.

[5]  C. Nelson,et al.  EEG Analytics for Early Detection of Autism Spectrum Disorder: A data-driven approach , 2018, Scientific Reports.

[6]  Yasith Jayawardana,et al.  Electroencephalogram (EEG) for Delineating Objective Measure of Autism Spectrum Disorder (ASD) (Extended Version) , 2019, Computational Models for Biomedical Reasoning and Problem Solving.

[7]  Mohammad Reza Mohammadi,et al.  Detection of Abnormalities for Diagnosing of Children with Autism Disorders Using of Quantitative Electroencephalography Analysis , 2012, Journal of Medical Systems.

[8]  Paolo Massimo Buscema,et al.  Diagnosis of autism through EEG processed by advanced computational algorithms: A pilot study , 2017, Comput. Methods Programs Biomed..

[9]  Hojjat Adeli,et al.  Fuzzy Synchronization Likelihood-wavelet methodology for diagnosis of autism spectrum disorder , 2012, Journal of Neuroscience Methods.

[10]  C. Nelson,et al.  EEG complexity as a biomarker for autism spectrum disorder risk , 2011, BMC medicine.

[11]  James M. Rehg,et al.  CENTRIST: A Visual Descriptor for Scene Categorization , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Khalil AlSharabi,et al.  EEG Signal Analysis for Diagnosing Neurological Disorders Using Discrete Wavelet Transform and Intelligent Techniques † , 2020, Sensors.

[13]  Wanzhong Chen,et al.  Classification Epileptic Seizures in EEG Using Time-Frequency Image and Block Texture Features , 2020, IEEE Access.

[14]  Zülfikar Aslan,et al.  Automatic Detection of Schizophrenia by Applying Deep Learning over Spectrogram Images of EEG Signals , 2020, Traitement du Signal.

[15]  Md. Nurul Ahad Tawhid,et al.  A Gender Recognition System from Facial Image , 2018 .

[16]  H. Adeli,et al.  Improved visibility graph fractality with application for the diagnosis of Autism Spectrum Disorder , 2012 .

[17]  Md. Nurul Ahad Tawhid,et al.  Diagnosis of autism spectrum disorder from EEG using a time–frequency spectrogram image‐based approach , 2020, Electronics Letters.

[18]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[19]  Yan Li,et al.  Clustering technique-based least square support vector machine for EEG signal classification , 2011, Comput. Methods Programs Biomed..

[20]  Debabrata Datta,et al.  Automatic sleep stage classification using time–frequency images of CWT and transfer learning using convolution neural network , 2020, Biocybernetics and Biomedical Engineering.

[21]  Yanchun Zhang,et al.  Multi-category EEG signal classification developing time-frequency texture features based Fisher Vector encoding method , 2016, Neurocomputing.

[22]  Ridha Djemal,et al.  EEG-Based Computer Aided Diagnosis of Autism Spectrum Disorder Using Wavelet, Entropy, and ANN , 2017, BioMed research international.

[23]  Nur Alisa Ali,et al.  Autism spectrum disorder classification on electroencephalogram signal using deep learning algorithm , 2020, IAES International Journal of Artificial Intelligence (IJ-AI).

[24]  Jinli Cao,et al.  An Integrated MCI Detection Framework Based on Spectral-temporal Analysis , 2019, International Journal of Automation and Computing.

[25]  Hojjat Adeli,et al.  Fractality and a Wavelet-Chaos-Neural Network Methodology for EEG-Based Diagnosis of Autistic Spectrum Disorder , 2010, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[26]  Hua Wang,et al.  Automated epilepsy detection techniques from electroencephalogram signals: a review study , 2020, Health Inf. Sci. Syst..

[27]  Abdulkadir Sengur,et al.  Exploring Hermite transformation in brain signal analysis for the detection of epileptic seizure , 2019, IET Science, Measurement & Technology.

[28]  Longhao Yuan,et al.  Patients' EEG Data Analysis via Spectrogram Image with a Convolution Neural Network , 2017, KES-IDT.

[29]  Mohammad Shoyaib,et al.  An Automated System for Garment Texture Design Class Identification , 2015, Comput..

[30]  Mohammed J. Alhaddad,et al.  Diagnosis Autism by Fisher Linear Discriminant Analysis FLDA via EEG , 2012 .

[31]  Yanchun Zhang,et al.  EEG Signal Analysis and Classification , 2016, Health Information Science.

[32]  Hoo-Chang Hoo-Chang Shin Shin,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, Ieee Transactions on Medical Imaging.

[33]  Sampath Jayarathna,et al.  An EEG based Channel Optimized Classification Approach for Autism Spectrum Disorder , 2019, 2019 Moratuwa Engineering Research Conference (MERCon).

[34]  Y. S. Kim,et al.  Global Prevalence of Autism and Other Pervasive Developmental Disorders , 2012, Autism research : official journal of the International Society for Autism Research.

[35]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[36]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[37]  Yanchun Zhang,et al.  Classification of THz pulse signals using two-dimensional cross-correlation feature extraction and non-linear classifiers , 2016, Comput. Methods Programs Biomed..

[38]  Min Hong,et al.  Deep Learning in Physiological Signal Data: A Survey , 2020, Sensors.

[39]  H. Behnam,et al.  Connectivity Analysis of Quantitative Electroencephalogram Background Activity in Autism Disorders with Short Time Fourier Transform and Coherence Values , 2008, 2008 Congress on Image and Signal Processing.

[40]  Yanchun Zhang,et al.  Exploring Sampling in the Detection of Multicategory EEG Signals , 2015, Comput. Math. Methods Medicine.

[41]  Yanchun Zhang,et al.  A framework for cardiac arrhythmia detection from IoT-based ECGs , 2020, World Wide Web.

[42]  S. Jeste,et al.  Recurrence quantification analysis of resting state EEG signals in autism spectrum disorder – a systematic methodological exploration of technical and demographic confounders in the search for biomarkers , 2018, BMC Medicine.

[43]  Sampath Jayarathna,et al.  Integration of Facial Thermography in EEG-based Classification of ASD , 2020, Int. J. Autom. Comput..

[44]  S. Bhosale,et al.  Dynamic multistimuli-responsive reversible chiral transformation in supramolecular helices , 2018, Scientific Reports.

[45]  Mohammad Hossein Moattar,et al.  A robust method for early diagnosis of autism spectrum disorder from EEG signals based on feature selection and DBSCAN method , 2020 .

[46]  Mikhail Belkin,et al.  Robust features for the automatic identification of autism spectrum disorder in children , 2014, Journal of Neurodevelopmental Disorders.

[47]  Jeffrey Braithwaite,et al.  When complexity science meets implementation science: a theoretical and empirical analysis of systems change , 2018, BMC Medicine.