SchizoNET: a robust and accurate Margenau-Hill time-frequency distribution based deep neural network model for schizophrenia detection using EEG signals

被引:28
作者
Khare, Smith K. [1 ]
Bajaj, Varun [2 ]
Acharya, U. Rajendra [3 ,4 ,5 ,6 ,7 ]
机构
[1] Aarhus Univ, Elect & Comp Engn Dept, Aarhus, Denmark
[2] Indian Inst Informat Technol Design & Mfg IIITDM J, Discipline Elect & Commun Engn, Jabalpur, India
[3] Univ Southern Queensland, Sch Math Phys & Comp, Springfield, Australia
[4] Univ Social Sci, Sch Sci & Technol, Dept Biomed Engn, Singapore, Singapore
[5] Asia Univ, Dept Biomed Informat & Med Engn, Taichung, Taiwan
[6] Kumamoto Univ, Kumamoto, Japan
[7] Univ Malaya, Kuala Lumpur, Malaysia
关键词
electroencephalogram classification; schizophrenia detection; convolutional neural networks; decision support system; AUTOMATIC DETECTION; CLASSIFICATION;
D O I
10.1088/1361-6579/acbc06
中图分类号
Q6 [生物物理学];
学科分类号
071011 ;
摘要
Objective. Schizophrenia (SZ) is a severe chronic illness characterized by delusions, cognitive dysfunctions, and hallucinations that impact feelings, behaviour, and thinking. Timely detection and treatment of SZ are necessary to avoid long-term consequences. Electroencephalogram (EEG) signals are one form of a biomarker that can reveal hidden changes in the brain during SZ. However, the EEG signals are non-stationary in nature with low amplitude. Therefore, extracting the hidden information from the EEG signals is challenging. Approach. The time-frequency domain is crucial for the automatic detection of SZ. Therefore, this paper presents the SchizoNET model combining the Margenau-Hill time-frequency distribution (MH-TFD) and convolutional neural network (CNN). The instantaneous information of EEG signals is captured in the time-frequency domain using MH-TFD. The time-frequency amplitude is converted to two-dimensional plots and fed to the developed CNN model. Results. The SchizoNET model is developed using three different validation techniques, including holdout, five-fold cross-validation, and ten-fold cross-validation techniques using three separate public SZ datasets (Dataset 1, 2, and 3). The proposed model achieved an accuracy of 97.4%, 99.74%, and 96.35% on Dataset 1 (adolescents: 45 SZ and 39 HC subjects), Dataset 2 (adults: 14 SZ and 14 HC subjects), and Dataset 3 (adults: 49 SZ and 32 HC subjects), respectively. We have also evaluated six performance parameters and the area under the curve to evaluate the performance of our developed model. Significance. The SchizoNET is robust, effective, and accurate, as it performed better than the state-of-the-art techniques. To the best of our knowledge, this is the first work to explore three publicly available EEG datasets for the automated detection of SZ. Our SchizoNET model can help neurologists detect the SZ in various scenarios.
引用
收藏
页数:21
相关论文
共 70 条
[1]   Analysis of the Complexity Measures in the EEG of Schizophrenia Patients [J].
Akar, S. Akdemir ;
Kara, S. ;
Latifoglu, F. ;
Bilgic, V. .
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS, 2016, 26 (02)
[2]   Classification of Bipolar Disorder and Schizophrenia Using Steady-State Visual Evoked Potential Based Features [J].
Alimardani, Fatemeh ;
Cho, Jae-Hyun ;
Boostaniy, Reza ;
Hwang, Han-Jeong .
IEEE ACCESS, 2018, 6 :40379-40388
[3]   Automatic Detection of Schizophrenia by Applying Deep Learning over Spectrogram Images of EEG Signals [J].
Aslan, Zulfikar ;
Akin, Mehmet .
TRAITEMENT DU SIGNAL, 2020, 37 (02) :235-244
[4]   CGP17Pat: Automated Schizophrenia Detection Based on a Cyclic Group of Prime Order Patterns Using EEG Signals [J].
Aydemir, Emrah ;
Dogan, Sengul ;
Baygin, Mehmet ;
Ooi, Chui Ping ;
Barua, Prabal Datta ;
Tuncer, Turker ;
Acharya, U. Rajendra .
HEALTHCARE, 2022, 10 (04)
[5]   CCPNet136: automated detection of schizophrenia using carbon chain pattern and iterative TQWT technique with EEG signals [J].
Baygin, Mehmet ;
Barua, Prabal Datta ;
Chakraborty, Subrata ;
Tuncer, Ilknur ;
Dogan, Sengul ;
Palmer, Elizabeth ;
Tuncer, Turker ;
Kamath, Aditya P. ;
Ciaccio, Edward J. ;
Acharya, U. Rajendra .
PHYSIOLOGICAL MEASUREMENT, 2023, 44 (03)
[6]   An accurate automated schizophrenia detection using TQWT and statistical moment based feature extraction [J].
Baygin, Mehmet .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2021, 68
[7]  
Begic D, 2000, ACTA PSYCHIAT SCAND, V101, P307, DOI 10.1111/j.1600-0447.2000.tb10930.x
[8]  
Boashash B., 2016, Time-Frequency Signal Analysis and Processing, VSecond, P141, DOI 10.1016/B978-0-12-398499-9.00004-2
[9]  
Borisov S., 2005, Hum. Physiol, V31, P255
[10]   Epidemiology and natural history of schizophrenia [J].
Bromet, EJ ;
Fennig, S .
BIOLOGICAL PSYCHIATRY, 1999, 46 (07) :871-881