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

• Published in: PloS one Vol. 16; no. 6; p. e0253094
• Main Authors: Tawhid, Md. Nurul Ahad, Siuly, Siuly, Wang, Hua, Whittaker, Frank, Wang, Kate, Zhang, Yanchun
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 25.06.2021; Public Library of Science (PLoS)
• Subjects: Accuracy; Artificial neural networks; Autism; Biology and Life Sciences; Biomarkers; Classification; Communication; Computer and Information Sciences; Datasets; Deep learning; Developmental disabilities; Diagnosis; EEG; Electroencephalography; Engineering and Technology; Evaluation; Feature extraction; Feature selection; Fourier analysis; Fourier transforms; Fractals; Learning algorithms; Machine learning; Magnetic resonance imaging; Medical imaging; Medicine and Health Sciences; Model accuracy; Neural networks; Neurological diseases; Physical Sciences; Principal components analysis; Research and Analysis Methods; Signal processing; Social factors; Social Sciences; Support vector machines; Temporal resolution; Wavelet transforms; Australia; Victoria Australia
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0253094

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.