Background
The convolutional neural network (CNN) is a mainstream deep learning (DL) algorithm, and it has gained great fame in solving problems from clinical examination and diagnosis, such as ...Alzheimer's disease (AD). AD is a degenerative disease difficult to clinical diagnosis due to its unclear underlying pathological mechanism. Previous studies have primarily focused on investigating structural abnormalities in the brain's functional networks related to the AD or proposing different deep learning approaches for AD classification.
Objective
The aim of this study is to leverage the advantages of combining brain topological features extracted from functional network exploration and deep features extracted by the CNN. We establish a novel fMRI-based classification framework that utilizes Resting-state functional magnetic resonance imaging (rs-fMRI) with the phase synchronization index (PSI) and 2D-CNN to detect abnormal brain functional connectivity in AD.
Methods
First, PSI was applied to construct the brain network by region of interest (ROI) signals obtained from data preprocessing stage, and eight topological features were extracted. Subsequently, the 2D-CNN was applied to the PSI matrix to explore the local and global patterns of the network connectivity by extracting eight deep features from the 2D-CNN convolutional layer.
Results
Finally, classification analysis was carried out on the combined PSI and 2D-CNN methods to recognize AD by using support vector machine (SVM) with 5-fold cross-validation strategy. It was found that the classification accuracy of combined method achieved 98.869%.
Conclusion
These findings show that our framework can adaptively combine the best brain network features to explore network synchronization, functional connections, and characterize brain functional abnormalities, which could effectively detect AD anomalies by the extracted features that may provide new insights into exploring the underlying pathogenesis of AD.
Epilepsy is a neurological disorder that is characterized by transient and unexpected electrical disturbance of the brain. Seizure detection by electroencephalogram (EEG) is associated with the ...primary interest of the evaluation and auxiliary diagnosis of epileptic patients. The aim of this study is to establish a hybrid model with improved particle swarm optimization (PSO) and a genetic algorithm (GA) to determine the optimal combination of features for epileptic seizure detection. First, the second-order difference plot (SODP) method was applied, and ten geometric features of epileptic EEG signals were derived in each frequency band (δ, θ, α and β), forming a high-dimensional feature vector. Secondly, an optimization algorithm, AsyLnCPSO-GA, combining a modified PSO with asynchronous learning factor (AsyLnCPSO) and the genetic algorithm (GA) was proposed for feature selection. Finally, the feature combinations were fed to a naïve Bayesian classifier for epileptic seizure and seizure-free identification. The method proposed in this paper achieved 95.35% classification accuracy with a tenfold cross-validation strategy when the interfrequency bands were crossed, serving as an effective method for epilepsy detection, which could help clinicians to expeditiously diagnose epilepsy based on SODP analysis and an optimization algorithm for feature selection.
Most patients with Alzheimer's disease (AD) have an insidious onset and frequently atypical clinical symptoms, which are considered a normal consequence of aging, making it difficult to diagnose AD ...medically. But then again, accurate diagnosis is critical to prevent degeneration and provide early treatment for AD patients.
This study aims to establish a novel EEG-based classification framework with deep learning methods for AD recognition.
First, considering the network interactions in different frequency bands (δ, θ, α, β, and γ), multiplex networks are reconstructed by the phase synchronization index (PSI) method, and fourteen topology features are extracted subsequently, forming a high-dimensional feature vector. However, in feature combination, not all features can provide effective information for recognition. Moreover, combining features by manual selection is time-consuming and laborious. Thus, a feature selection optimization algorithm called MOPSO-GDM was proposed by combining multi-objective particle swarm optimization (MOPSO) algorithm with Gaussian differential mutation (GDM) algorithm. In addition to considering the classification error rates of support vector machine, naive bayes, and discriminant analysis classifiers, our algorithm also considers distance measure as an optimization objective.
Finally, this method proposed achieves an excellent classification error rate of 0.0531 (5.31%) with the feature vector size of 8, by a ten-fold cross-validation strategy.
These findings show that our framework can adaptively combine the best brain network features to explore network synchronization, functional interactions, and characterize brain functional abnormalities, which can improve the recognition efficiency of diseases. While improving the classification accuracy of application algorithms, we aim to expand our understanding of the brain function of patients with neurological disorders through the analysis of brain networks.
To study the electroencephalograph (EEG) background activity in patients with Alzheimer's disease (AD), power spectrum density estimated by AR model and Lempel-Ziv (LZ) complexity are employed. EEG ...signals are recorded with 16-channel scalp electrodes in 15 patients with probable AD and 15 age-matched normal control subjects, in a relax state with eyes closed. Analysis results demonstrate that both relative PSD and LZ complexity of AD patients are increased in theta band and decreased in alpha band when compared with controls. Furthermore, specific to a particular frequency band, the topographical distribution of relative PSD and LZ complexity in the brain are matched. These preliminary results suggest that cognitive dysfunction in AD is associated with slowed power and decreased complexity in certain regions of the brain, though which we could differentiate AD patients from control subjects.
In order to explore the interaction mechanism between brain regions of Alzheimer's disease (AD), brain connectivity was constructed and analyzed by using background electroencephalogram (EEG) signals ...recorded from AD patients and the normal controls. In this work, a linear coherent network was constructed, and AD brain network showed the disconnected characteristics. Then eight network measures of each frequency band (delta, theta, alpha and beta) were extracted, which used as the input features for the support vector machine (SVM) classifier. In order to study the correlation between features under different frequency bands, the following three feature input schemes of SVM were applied, that are, (1) single feature of within-frequency band; (2) multi-features of within-frequency band and (3) multi-features of cross-frequency band. The experimental results showed that the highest accuracy of the scheme (1) was 0.8225, while the accuracy of the scheme (2) was 0.91, which was higher than that of the scheme (1). The final accuracy of the scheme (3) was 0.9545. The classification results showed that the combined features in the cross-frequency band could classify the AD group and the control group with high accuracy, which represents that frequency coupling in nervous system is associated with impaired and normal brain functions. These findings suggest that the feature extracted from the coherence network and the method of feature combination can be effectively distinguished AD and the control group, which can give us a deeper understanding of AD brains.
An Improved Agent-Based Genetic Algorithm is used to solve the multi-objective Network Optimization Problems. The Agent is used to the genetic algorithm and the specific encoding is used to encode ...the path of network. The Pareto competition classic ordering method is used for the calculation of Agent energy. The partial mapping crossover is used to deal with the conflict of genes in crossover process. Comparative experiments show that the algorithm is efficient when is used to solve network multi-objective optimization problems.
The improved algorithm based on objective layered approach is used to deal with the multi-objective network optimization problem. Based on the traditional non-dominated sorting genetic algorithm, an ...improved algorithm is given. In order to increase the computational efficiency, the objective layered approach is used sort the individuals of population and identify the non-inferior solution. Individuals are selected by method of loop from the first layer to the m*(1/2) layers(m is total number of layers). Two objectives, the cost and delay are considered. A few examples for the network optimization problems are used test the algorithm. The result shows the algorithm is succeed in finding Pareto solutions with higher computational efficiency.
In order to solve the function optimization problem, an adaptive genetic algorithm is proposed based on the structure of the chain agent. The algorithm adopts the structure of the chain agent to ...reduce the computational overhead. The mixing crossover strategy that includes the arithmetic crossover and two-point crossover is adopted in the crossover operator. In the crossover and mutation operator, the adaptive probabilities of crossover and mutation related to the generations are adopted. The simulations reveal that this algorithm has better convergence and the speed to get the optimal solution is very fast.
In this paper, in order to explore underlying the interaction mechanisms between brain regions, the cross entropy measures: cross sample entropy (C-SampEn) and cross fuzzy entropy (C-FuzzyEn) were ...used to measure the brain synchrony through analyzing the background electroencephalograph (EEG) signals in Alzheimer's disease (AD) patients. It was demonstrated that the values of both the two features in AD were lower than that of the normal controls, particularly in the alpha band, indicating that the synchrony strength and the information transferring efficiency between the corresponding brain regions were decreased in AD. Moreover, classification results showed that the two cross entropy features could classify AD Group and Control Group correctly. However, the C-FuzzyEn performed better, reflected in the higher classification accuracy. Thus, C-FuzzyEn revealed the abnormalities of brain activity for AD by evaluating the synchrony from EEG series, and it seemed to be an important auxiliary clinical method to diagnose AD early.
PDF