MyMedR

Displaying all 4 publications

Abstract:

Sort:

Fulltext Identification of Autism Subtypes Based on Wavelet Coherence of BOLD FMRI Signals Using Convolutional Neural Network

Al-Hiyali MI, Yahya N, Faye I, Hussein AF

Sensors (Basel), 2021 Aug 04;21(16).
PMID: 34450699 DOI: 10.3390/s21165256

The functional connectivity (FC) patterns of resting-state functional magnetic resonance imaging (rs-fMRI) play an essential role in the development of autism spectrum disorders (ASD) classification models. There are available methods in literature that have used FC patterns as inputs for binary classification models, but the results barely reach an accuracy of 80%. Additionally, the generalizability across multiple sites of the models has not been investigated. Due to the lack of ASD subtypes identification model, the multi-class classification is proposed in the present study. This study aims to develop automated identification of autism spectrum disorder (ASD) subtypes using convolutional neural networks (CNN) using dynamic FC as its inputs. The rs-fMRI dataset used in this study consists of 144 individuals from 8 independent sites, labeled based on three ASD subtypes, namely autistic disorder (ASD), Asperger's disorder (APD), and pervasive developmental disorder not otherwise specified (PDD-NOS). The blood-oxygen-level-dependent (BOLD) signals from 116 brain nodes of automated anatomical labeling (AAL) atlas are used, where the top-ranked node is determined based on one-way analysis of variance (ANOVA) of the power spectral density (PSD) values. Based on the statistical analysis of the PSD values of 3-level ASD and normal control (NC), putamen_R is obtained as the top-ranked node and used for the wavelet coherence computation. With good resolution in time and frequency domain, scalograms of wavelet coherence between the top-ranked node and the rest of the nodes are used as dynamic FC feature input to the convolutional neural networks (CNN). The dynamic FC patterns of wavelet coherence scalogram represent phase synchronization between the pairs of BOLD signals. Classification algorithms are developed using CNN and the wavelet coherence scalograms for binary and multi-class identification were trained and tested using cross-validation and leave-one-out techniques. Results of binary classification (ASD vs. NC) and multi-class classification (ASD vs. APD vs. PDD-NOS vs. NC) yielded, respectively, 89.8% accuracy and 82.1% macro-average accuracy, respectively. Findings from this study have illustrated the good potential of wavelet coherence technique in representing dynamic FC between brain nodes and open possibilities for its application in computer aided diagnosis of other neuropsychiatric disorders, such as depression or schizophrenia.
Fulltext Machine learning for the detection of social anxiety disorder using effective connectivity and graph theory measures

Al-Ezzi A, Kamel N, Al-Shargabi AA, Al-Shargie F, Al-Shargabi A, Yahya N, et al.

Front Psychiatry, 2023;14:1155812.
PMID: 37255678 DOI: 10.3389/fpsyt.2023.1155812

INTRODUCTION: The early diagnosis and classification of social anxiety disorder (SAD) are crucial clinical support tasks for medical practitioners in designing patient treatment programs to better supervise the progression and development of SAD. This paper proposes an effective method to classify the severity of SAD into different grading (severe, moderate, mild, and control) by using the patterns of brain information flow with their corresponding graphical networks.
METHODS: We quantified the directed information flow using partial directed coherence (PDC) and the topological networks by graph theory measures at four frequency bands (delta, theta, alpha, and beta). The PDC assesses the causal interactions between neuronal units of the brain network. Besides, the graph theory of the complex network identifies the topological structure of the network. Resting-state electroencephalogram (EEG) data were recorded for 66 patients with different severities of SAD (22 severe, 22 moderate, and 22 mild) and 22 demographically matched healthy controls (HC).
RESULTS: PDC results have found significant differences between SAD groups and HCs in theta and alpha frequency bands (p < 0.05). Severe and moderate SAD groups have shown greater enhanced information flow than mild and HC groups in all frequency bands. Furthermore, the PDC and graph theory features have been used to discriminate three classes of SAD from HCs using several machine learning classifiers. In comparison to the features obtained by PDC, graph theory network features combined with PDC have achieved maximum classification performance with accuracy (92.78%), sensitivity (95.25%), and specificity (94.12%) using Support Vector Machine (SVM).
DISCUSSION: Based on the results, it can be concluded that the combination of graph theory features and PDC values may be considered an effective tool for SAD identification. Our outcomes may provide new insights into developing biomarkers for SAD diagnosis based on topological brain networks and machine learning algorithms.
Fulltext Corrigendum: Machine learning for the detection of social anxiety disorder using effective connectivity and graph theory measures

Al-Ezzi A, Kamel N, Al-Shargabi AA, Al-Shargie F, Al-Shargabi A, Yahya N, et al.

Front Psychiatry, 2023;14:1257713.
PMID: 37555003 DOI: 10.3389/fpsyt.2023.1257713

[This corrects the article DOI: 10.3389/fpsyt.2023.1155812.].
Fulltext Cortical signals analysis to recognize intralimb mobility using modified RNN and various EEG quantities

Al-Quraishi MS, Tan WH, Elamvazuthi I, Ooi CP, Saad NM, Al-Hiyali MI, et al.

Heliyon, 2024 May 15;10(9):e30406.
PMID: 38726180 DOI: 10.1016/j.heliyon.2024.e30406

Electroencephalogram (EEG) signals are critical in interpreting sensorimotor activities for predicting body movements. However, their efficacy in identifying intralimb movements, such as the dorsiflexion and plantar flexion of the foot, remains suboptimal. This study aims to explore whether various EEG signal quantities can effectively recognize intralimb movements to facilitate the development of Brain-Computer Interface (BCI) devices for foot rehabilitation. This research involved twenty-two healthy, right-handed participants. EEG data were collected using 21 electrodes positioned over the motor cortex, while two electromyography (EMG) electrodes recorded the onset of ankle joint movements. The study focused on analyzing slow cortical potential (SCP) and sensorimotor rhythms (SMR) in alpha and beta bands from the EEG. Five key features-fourth-order Autoregressive feature, variance, waveform length, standard deviation, and permutation entropy-were extracted. A modified Recurrent Neural Network (RNN) including Long Short-term Memory (LSTM) and Gated Recurrent Unit (GRU) algorithms was developed for movement recognition. These were compared against conventional machine learning algorithms, including nonlinear Support Vector Machine (SVM) and k Nearest Neighbourhood (kNN) classifiers. The performance of the proposed models was assessed using two data schemes: within-subject and across-subjects. The findings demonstrated that the GRU and LSTM models significantly outperformed traditional machine learning algorithms in recognizing different EEG signal quantities for intralimb movement. The study indicates that deep learning models, particularly GRU and LSTM, hold superior potential over standard machine learning techniques in identifying intralimb movements using EEG signals. Where the accuracies of LSTM for within and across subjects were 98.87 ± 1.80 % and 87.38 ± 0.86 % respectively. Whereas the accuracy of GRU within and across subjects were 99.18 ± 1.28 % and 86.44 ± 0.69 % respectively. This advancement could significantly benefit the development of BCI devices aimed at foot rehabilitation, suggesting a new avenue for enhancing physical therapy outcomes.