No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Detection of Alzheimer's Dementia Using Intrinsic Time Scale Decomposition of EEG Signals and Deep Learning
Dementia arises from various brain-affecting diseases and injuries, with Alzheimer’s disease being the most prevalent, impacting around 55 million people globally. Current clinical diagnosis often relies on biomarkers indicative of Alzheimer’s distinctive features. Electroencephalography (EEG) serves as a cost-effective, user-friendly, and safe biomarker for early Alzheimer’s detection. This study utilizes EEG signals processed with Short-Time Fourier Transform (STFT) to generate spectrograms, facilitating visualization of EEG signal properties. Leveraging the Brainlat database, we propose SpectroCVT-Net, a novel convolutional vision transformer architecture incorporating channel attention mechanisms. SpectroCVT-Net integrates convolutional and attention mechanisms to capture local and global dependencies within spectrograms. Comprising feature extraction and classification stages, the model enhances Alzheimer’s disease classification accuracy compared to transfer learning methods, achieving 92.59 ± 2.3% accuracy across Alzheimer’s, healthy controls, and behavioral variant frontotemporal dementia (bvFTD). This article introduces a new architecture and evaluates its efficacy with unconventional data for Alzheimer’s diagnosis, contributing: SpectroCVT-Net, tailored for EEG spectrogram classification without reliance on transfer learning; a convolutional vision transformer (CVT) module in the classification stage, integrating local feature extraction with attention heads for global context analysis; Grad-CAM analysis for network decision insight, identifying critical layers, frequencies, and electrodes influencing classification; and enhanced interpretability through spectrograms, illuminating key brain wave contributions to Alzheimer’s, frontotemporal dementia, and healthy control classifications, potentially aiding clinical diagnosis and management.
Electroencephalographic (EEG) signals are electrical signals generated in the brain due to cognitive activities. They are non-invasive and are widely used to assess neurodegenerative conditions, mental load, and sleep patterns. In this work, we explore the utility of representing the inherently single dimensional time-series in different dimensions such as 1D-feature vector, 2D-feature maps, and 3D-videos. The proposed methodology is applied to four diverse datasets: 1) EEG baseline, 2) mental arithmetic, 3) Parkinson’s disease, and 4) emotion dataset. For a 1D analysis, popular 1D features hand-crafted from the time-series are utilized for classification. This performance is compared against the data-driven approach of using raw time-series as the input to the deep learning framework. To assess the efficacy of 2D representation, 2D feature maps that utilize a combination of the Feature Pyramid Network (FPN) and Atrous Spatial Pyramid Pooling (ASPP) is proposed. This is compared against an approach utilizing a composite feature set consisting of 2D feature maps and 1D features. However, these approaches do not exploit spatial, spectral, and temporal characteristics simultaneously. To address this, 3D EEG videos are created by stacking spectral feature maps obtained from each sub-band per time frame in a temporal domain. The EEG videos are the input to a combination of the Convolution Neural Network (CNN) and Long–Short Term Memory (LSTM) for classification. Performances obtained using the proposed methodologies have surpassed the state-of-the-art for three of the classification scenarios considered in this work, namely, EEG baselines, mental arithmetic, and Parkinson’s disease. The video analysis resulted in 92.5% and 98.81% peak mean accuracies for the EEG baseline and EEG mental arithmetic, respectively. On the other hand, for distinguishing Parkinson’s disease from controls, a peak mean accuracy of 88.51% is achieved using traditional methods on 1D feature vectors. This illustrates that 3D and 2D feature representations are effective for those EEG data where topographical changes in brain activation regions are observed. However, in scenarios where topographical changes are not consistent across subjects of the same class, these methodologies fail. On the other hand, the 1D analysis proves to be significantly effective in the case involving changes in the overall activation of the brain due to varying degrees of deterioration.
As the world is experiencing population growth, the portion of the older people, aged 65 and above, is also growing at a faster rate. As a result, the dementia with Alzheimer’s disease is expected to increase rapidly in the next few years. Currently, healthcare systems require an accurate detection of the disease for its treatment and prevention. Therefore, it has become essential to develop a framework for early detection of Alzheimer’s disease to avoid complications. To this end, a novel framework, based on machine-learning (ML) and deep-learning (DL) methods, is proposed to detect Alzheimer’s disease. In particular, the performance of different ML and DL algorithms has been evaluated against their detection accuracy. The experimental results state that bidirectional long short-term memory (BiLSTM) outperforms the ML methods with a detection accuracy of 91.28%. Furthermore, the comparison with the state-of-the-art indicates the superiority of the our framework over the other proposed approaches in the literature.KeywordsMachine learningDeep learningDetecting Alzheimer
Using strategies that obtain biomarkers where early symptoms coincide, the early detection of Alzheimer's disease and its complications is essential. Electroencephalogram is a technology that allows thousands of neurons with equal spatial orientation of the duration of cerebral cortex electrical activity to be registered by postsynaptic potential. Therefore, in this paper, the time-dependent power spectrum descriptors are used to diagnose the electroencephalogram signal function from three groups: mild cognitive impairment, Alzheimer's disease, and healthy control test samples. The final feature used in three modes of traditional classification methods is recorded: k-nearest neighbors, support vector machine, linear discriminant analysis approaches, and documented results. Finally, for Alzheimer's disease patient classification, the convolutional neural network architecture is presented. The results are indicated using output assessment. For the convolutional neural network approach, the accurate meaning of accuracy is 82.3%. 85% of mild cognitive impairment cases are accurately detected in-depth, but 89.1% of the Alzheimer's disease and 75% of the healthy population are correctly diagnosed. The presented convolutional neural network outperforms other approaches because performance and the k-nearest neighbors' approach is the next target. The linear discriminant analysis and support vector machine were at the low area under the curve values.
Multiscale entropy (MSE) was used to analyze electroencephalography (EEG) signals to differentiate patients with Alzheimer’s disease (AD) from healthy subjects. It was found that the MSE values of the EEG signals from the heathy subjects are higher than those of the AD ones at small time scale factors in the MSE algorithm, while lower than those of the AD patients at large time scale factors. Based on the finding, we applied the linear discriminant analysis (LDA) to optimize the differentiating performance by comparing the resulting weighted sum of the MSE values under some specific time scales of each subject. The EEG data from 15 healthy subjects, 69 patients with mild AD, and 15 patients with moderate to severe AD were recorded. As a result, the weighted sum values are significantly higher for the healthy than the patients with moderate to severe AD groups. The optimal testing accuracy under five specific scales is 100% based on the EEG signals acquired from the T4 electrode. The resulting weighted sum value for the mild AD group is in the middle of those for the healthy and the moderate to severe AD groups. Therefore, the MSE-based weighted sum value can potentially be an index of severity of Alzheimer’s disease.
In the last two decades, both Empirical Mode Decomposition (EMD) and Intrinsic Time-Scale Decomposition (ITD) algorithms deserved a variety of applications in various fields of science and engineering due to their obvious advantages compared to conventional (e.g. correlation-or spectral-based analysis) approaches like the ability of their direct application to non-stationary signal analysis. However, high computational complexity remains a common drawback of these otherwise universal and powerful algorithms. Here we compare similarly designed signal analysis algorithms utilizing either EMD or ITD as their core functions. Based on extensive computer simulations, we show explicitly that the replacement of EMD by ITD in several otherwise similar signal analysis scenarios leads to the increased noise robustness with simultaneous considerable reduction of the processing time. We also demonstrate that the proposed algorithms modifications could be successfully utilized in a series of emerging applications for processing of non-stationary signals.
We introduce a new algorithm, the intrinsic time-scale decomposition (ITD), for efficient and precise time–frequency–energy (TFE) analysis of signals. The ITD method overcomes many of the limitations of both classical (e.g. Fourier transform or wavelet transform based) and more recent (empirical mode decomposition based) approaches to TFE analysis of signals that are nonlinear and/or non-stationary in nature. The ITD method decomposes a signal into (i) a sum of proper rotation components, for which instantaneous frequency and amplitude are well defined, and (ii) a monotonic trend. The decomposition preserves precise temporal information regarding signal critical points and riding waves, with a temporal resolution equal to the time-scale of extrema occurrence in the input signal. We also demonstrate how the ITD enables application of single-wave analysis and how this, in turn, leads to a powerful new class of real-time signal filters, which extract and utilize the inherent instantaneous amplitude and frequency/phase information in combination with other relevant morphological features.
Dementia is one of the most common neurological disorders causing defection of cognitive functions, and seriously affects the quality of life. In this study, various methods have been proposed for the detection and follow-up of Alzheimer's dementia (AD) with advanced signal processing methods by using electroencephalography (EEG) signals. Signal decomposition-based approaches such as empirical mode decomposition (EMD), ensemble EMD (EEMD), and discrete wavelet transform (DWT) are presented to classify EEG segments of control subjects (CSs) and AD patients. Intrinsic mode functions (IMFs) are obtained from the signals using the EMD and EEMD methods, and the IMFs showing the most significant differences between the two groups are selected by applying previously suggested selection procedures. Five-time-domain and 5-spectral-domain features are calculated using selected IMFs, and five detail and approximation coefficients of DWT. Signal decomposition processes are conducted for both 1 min and 5 s EEG segment durations. For the 1 min segment duration, all the proposed approaches yield prominent classification performances. While the highest classification accuracies are obtained using EMD (91.8%) and EEMD (94.1%) approaches from the temporal/right brain cluster, the highest classification accuracy for the DWT (95.2%) approach is obtained from the temporal/left brain cluster for 1 min segment duration.
Background and objective
Alzheimer’s disease (AD) is characterized by cognitive, behavioral and intellectual deficits. The term mild cognitive impairment (MCI) is used to describe individuals whose cognitive impairment departing from their expectations for the age that does not interfere with daily activities. To diagnose these disorders, a combination of time-consuming, expensive tests that has difficulties for the target population are evaluated, moreover, the evaluation may yield subjective results. In the presented study, a novel methodology is developed for the automatic detection of AD and MCI using EEG signals.
Methods
This study analyzed the EEGs of 35 subjects (16 MCI, 8 AD, 11 healthy control) with the developed algorithm. The algorithm consists of 3 methods for analysis, discrete wavelet transform(DWT), power spectral density (PSD) and coherence. In the first approach, DWT is applied to the signals to obtain major EEG sub-bands, afterward, PSD of each sub-band is calculated using Burg’s method. In the second approach, interhemispheric coherence values are calculated. The variance and amplitude summation of each sub-bands’ PSD and the amplitude summation of the coherence values corresponding to the major sub-bands are determined as features. Bagged Trees is selected as a classifier among the other tested classification algorithms. Data set is used to train the classifier with 5-fold cross-validation.
Results
As a result, accuracy, sensitivity, and specificity of 96.5%, 96.21%, 97.96% are achieved respectively.
Conclusion
In this study, we have investigated whether EEG can provide efficient clues about the neuropathology of Alzheimer's Disease and mild cognitive impairment for early and accurate diagnosis. Accordingly, a decision support system that produces reproducible and objective results with high accuracy is developed.
Alzheimer's Disease (AD) is the most common type of dementia with world prevalence of more than 46 million people. The Mini-Mental State Examination (MMSE) score is used to categorize the severity and evaluate the disease progress. The electroencephalogram (EEG) is a cost-effective diagnostic tool and lately, new methods have developed for MMSE score correlation with EEG markers. In this paper, EEG recordings acquired from 14 patients with mild and moderate AD and 10 control subjects are analyzed in the five EEG rhythms (δ, θ, α, β, γ). Then, 38 linear and non-linear features are calculated. Multiregression linear analysis showed highly correlation of with MMSE score variation with Permutation Entropy of δ rhythm, Sample Entropy of θ rhythm and Relative θ power. Also, the best statistically significant regression models in terms of R ² are at O2 (0.542) and F4 (0.513) electrodes and at posterior (0.365) and left-temporal cluster (0.360).
This article presents a review of recent advances in neuroscience research in the specific area of brain connectivity as a potential biomarker of Alzheimer's disease with a focus on the application of graph theory. The review will begin with a brief overview of connectivity and graph theory. Then resent advances in connectivity as a biomarker for Alzheimer's disease will be presented and analyzed.
Computer aided diagnosis (CAD) constitutes an important tool for the early diagnosis of Alzheimer’s Disease (AD), which, in turn, allows the application of treatments that can be simpler and more likely to be effective. This paper explores the construction of classification methods based on deep learning architectures applied on brain regions defined by the Automated Anatomical Labelling (AAL). Gray Matter (GM) images from each brain area have been split into 3D patches according to the regions defined by the AAL atlas and these patches are used to train different deep belief networks. An ensemble of deep belief networks is then composed where the final prediction is determined by a voting scheme. Two deep learning based structures and four different voting schemes are implemented and compared, giving as a result a potent classification architecture where discriminative features are computed in an unsupervised fashion. The resulting method has been evaluated using a large dataset from the Alzheimer's disease Neuroimaging Initiative (ADNI). Classification results assessed by cross-validation prove that the proposed method is not only valid for differentiate between controls (NC) and AD images, but it also provides good performances when tested for the more challenging case of classifying Mild Cognitive Impairment Subjects (MCI). In particular, the classification architecture provides accuracy values up to 0.90 and AUC of 0.95 for NC/AD classification, 0.84 and AUC of 0.91 for stable MCI /AD classification and 0.83 and AUC of 0.95 for NC/MCI converters classification.
Intrinsic time-scale decomposition (ITD) is a new nonlinear method of time-frequency representation which can decipher the minute changes in the nonlinear EEG signals. In this work, we have automatically classified normal, interictal and ictal EEG signals using the features derived from the ITD representation. The energy, fractal dimension and sample entropy features computed on ITD representation coupled with decision tree classifier has yielded an average classification accuracy of 95.67%, sensitivity and specificity of 99% and 99.5%, respectively using 10-fold cross validation scheme. With application of the nonlinear ITD representation, along with conceptual advancement and improvement of the accuracy, the developed system is clinically ready for mass screening in resource constrained and emerging economy scenarios.
2019 alzheimer's disease facts and figures
Adaptive signal processing algorithms based on EMD and ITD
- A Voznesensky
- D Kaplun