Diagnosis of mild Alzheimer's disease by EEG and ERP signals using linear and nonlinear classifiers

Rad, Elias Mazrooei; Azarnoosh, Mahdi; Ghoshuni, Majid; Khalilzadeh, Mohammad

doi:10.1016/j.bspc.2021.103049

Cited by 21 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multi-channel deep convolutional neural network (MC-DCNN) 17 which learns features from individual univariate time series in each channel was used in the diagnosis of mild Alzheimer's disease in the study. 41 The results proved that the CNN achieved the highest accuracy compared with LDA. Saman Fouladi 18 got a similar conclusion that the deep learning architectures had the potential to be a good tool to handle EEG analysis when they use a CNN to classify Alzheimer's disease and mild cognitive impairment.…”

Section: Related Workmentioning

confidence: 89%

“…As an important branch of artificial intelligence, deep learning had been employed to cope with the task of dementia recognition. A multi‐channel deep convolutional neural network (MC‐DCNN) 17 which learns features from individual univariate time series in each channel was used in the diagnosis of mild Alzheimer's disease in the study 41 . The results proved that the CNN achieved the highest accuracy compared with LDA.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

D‐Unet: A symmetric architecture of convolutional neural network with two auxiliary outputs for dementia recognition

Li,

Xia,

Zou

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Dementia‐associated disorders cause damage to the brains of patients and bring huge burdens to individuals and families. Electroencephalogram (EEG) monitoring is friendly to patients on account of low cost, non‐invasion, and objective. Event‐related potential (ERP) is a component of EEG that has huge potential to evaluate the cognitive function of the brain. In this study, we recorded the ERP from patients with dementia and healthy people, then proposed an ERP‐based deep learning method to realize dementia recognition via the model Dementia‐Unet (D‐Unet). To improve the performance of the model, on the base of the decoder and the primary classifier, we added new structures including a symmetric decoder and two auxiliary outputs. One of the auxiliary outputs was input reconstruction, and the other one was aimed at working like the primary classifier with the same task. The results of the experiment of four‐fold cross‐validation demonstrated the two auxiliary outputs improved the performance of the model effectively. When compared with some other machine learning methods and deep learning methods, our model obtained the best performance with an accuracy of 0.815, a precision of 0.829, a recall of 0.797, and an f1‐score of 0.812. Besides, we put up a complex training strategy with all outputs involved, but a simple testing strategy with only a primary classifier working to keep high performance but cut down the complexity burden during testing.

show abstract

Section: Related Workmentioning

confidence: 89%

Section: Related Workmentioning

confidence: 99%

D‐Unet: A symmetric architecture of convolutional neural network with two auxiliary outputs for dementia recognition

Li,

Xia,

Zou

et al. 2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…Similarly, Rad et al ( 2021 ) performed EEG experiments on 63 AD subjects, 63 subjects with MCI, and 63 NC subjects. They innovatively transformed the EEG signals into two-dimensional grayscale images, incorporating AD lesion features.…”

Section: Related Workmentioning

confidence: 99%

“…Another approach was taken by Rad et al ( 2021 ), who augmented the data with three distinct modal features: frequency features, zero-domain signal features, and triggering event signal features. These three features were then input into a multi-channel deep convolutional neural network, achieving a noteworthy 75.50% accuracy in AD classification.…”

Section: Related Workmentioning

confidence: 99%

Multi-feature fusion learning for Alzheimer's disease prediction using EEG signals in resting state

Chen,

Wang,

Zhang

et al. 2023

Front. Neurosci.

View full text Add to dashboard Cite

IntroductionDiagnosing Alzheimer's disease (AD) lesions via visual examination of Electroencephalography (EEG) signals poses a considerable challenge. This has prompted the exploration of deep learning techniques, such as Convolutional Neural Networks (CNNs) and Visual Transformers (ViTs), for AD prediction. However, the classification performance of CNN-based methods has often been deemed inadequate. This is primarily attributed to CNNs struggling with extracting meaningful lesion signals from the complex and noisy EEG data.MethodsIn contrast, ViTs have demonstrated proficiency in capturing global signal patterns. In light of these observations, we propose a novel approach to enhance AD risk assessment. Our proposition involves a hybrid architecture, merging the strengths of CNNs and ViTs to compensate for their respective feature extraction limitations. Our proposed Dual-Branch Feature Fusion Network (DBN) leverages both CNN and ViT components to acquire texture features and global semantic information from EEG signals. These elements are pivotal in capturing dynamic electrical signal changes in the cerebral cortex. Additionally, we introduce Spatial Attention (SA) and Channel Attention (CA) blocks within the network architecture. These attention mechanisms bolster the model's capacity to discern abnormal EEG signal patterns from the amalgamated features. To make well-informed predictions, we employ a two-factor decision-making mechanism. Specifically, we conduct correlation analysis on predicted EEG signals from the same subject to establish consistency.ResultsThis is then combined with results from the Clinical Neuropsychological Scale (MMSE) assessment to comprehensively evaluate the subject's susceptibility to AD. Our experimental validation on the publicly available OpenNeuro database underscores the efficacy of our approach. Notably, our proposed method attains an impressive 80.23% classification accuracy in distinguishing between AD, Frontotemporal dementia (FTD), and Normal Control (NC) subjects.DiscussionThis outcome outperforms prevailing state-of-the-art methodologies in EEG-based AD prediction. Furthermore, our methodology enables the visualization of salient regions within pathological images, providing invaluable insights for interpreting and analyzing AD predictions.

show abstract

“…One of the most important tools used to understand the behavior and dynamics of time series, especially time series of vital signals that are mainly extracted from nonlinear systems, is the phase diagram. 15 Figure 6 shows the two-dimensional phase curve and Figure 7 shows the three-dimensional phase curve of the Fz, Cz, and Pz channels. The EEG signal of the healthy subject is shown with the eyes closed.…”

Section: Nonlinear Features Of Eegmentioning

confidence: 99%

Early Detection of Alzheimer’s Disease With Nonlinear Features of EEG Signal and MRI Images by Convolutional Neural Network

Rad

Azarnoosh

Ghoshuni

et al. 2022

Int Clin Neurosci J

Self Cite

View full text Add to dashboard Cite

Background: The main purpose of this study is to provide a method for early diagnosis of Alzheimer’s disease. This disease reduces memory function by destroying neurons in the nervous system and reducing connections and neural interactions. Alzheimer’s disease is on the rise and there is no cure for it. With the help of medical image processing, Alzheimer’s disease is determined and the similarity of the characteristics of brain signals with medical images is determined. Methods: Then, by presenting the characteristics of effective brain signals, the mild Alzheimer’s group is determined. The level of this disease should be diagnosed according to the relationship between this disease and different features in the brain signal and medical images. Results: For 40 participants brain signals and MRI images were recorded during 4 phase protocol and after appropriate preprocessing, nonlinear properties such as phase diagram, correlation dimension, entropy, and Lyapunov exponential are extracted and classification is done using a convolutional neural network (CNN). The use of this deep learning method can have more appropriate and accurate results among other classification methods. Conclusions: The accuracy of the results in the reminding phase is 97.5% for the brain signal and 99% for the MRI images, which is an acceptable result.

show abstract

Diagnosis of mild Alzheimer's disease by EEG and ERP signals using linear and nonlinear classifiers

Cited by 21 publications

References 33 publications

D‐Unet: A symmetric architecture of convolutional neural network with two auxiliary outputs for dementia recognition

D‐Unet: A symmetric architecture of convolutional neural network with two auxiliary outputs for dementia recognition

Multi-feature fusion learning for Alzheimer's disease prediction using EEG signals in resting state

Early Detection of Alzheimer’s Disease With Nonlinear Features of EEG Signal and MRI Images by Convolutional Neural Network

Contact Info

Product

Resources

About