Dyslexia Diagnosis by EEG Temporal and Spectral Descriptors: An Anomaly Detection Approach

Directed Weighted EEG Connectogram Insights of One-to-One Causality for Identifying Developmental Dyslexia

Developmental dyslexia (DD) affects approximately 5-12% of learners, posing persistent challenges in reading and writing. This study presents a novel electroencephalography (EEG)-based methodology for identifying DD using two auditory stimuli modulated at 4.8[Formula: see text]Hz (prosodic) and 40[Formula: see text]Hz (phonemic). EEG signals were processed to estimate one-to-one Granger causality, yielding directed and weighted connectivity matrices. A novel Mutually Informed Correlation Coefficient (MICC) feature selection method was employed to identify the most relevant causal links, which were visualized using connectograms. Under the 4.8[Formula: see text]Hz stimulus, altered theta-band connectivity between frontal and occipital regions indicated compensatory frontal activation for prosodic processing and visual-auditory integration difficulties, while gamma-band anomalies between occipital and temporal regions suggested impaired visual-prosodic integration. Classification analysis under the 4.8[Formula: see text]Hz stimulus yielded area under the ROC curve (AUC) values of 0.92 (theta) and 0.91 (gamma band). Under the 40[Formula: see text]Hz stimulus, theta abnormalities reflected dysfunctions in integrating auditory phoneme signals with executive and motor regions, and gamma alterations indicated difficulties coordinating visual and auditory inputs for phonological decoding, with AUC values of 0.84 (theta) and 0.89 (gamma). These results support both the Temporal Sampling Framework and the Phonological Core Deficit Hypothesis. Future research should extend the range of stimuli frequencies and include more diverse cohorts to further validate these potential biomarkers.

Multimodal Integration of EEG and Near-Infrared Spectroscopy for Robust Cross-Frequency Coupling Estimation

Neuroimaging techniques have had a major impact on medical science, allowing advances in the research of many neurological diseases and improving their diagnosis. In this context, multimodal neuroimaging approaches, based on the neurovascular coupling phenomenon, exploit their individual strengths to provide complementary information on the neural activity of the brain cortex. This work proposes a novel method for combining electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) to explore the functional activity of the brain processes related to low-level language processing of skilled and dyslexic seven-year-old readers. We have transformed EEG signals into image sequences considering the interaction between different frequency bands by means of cross-frequency coupling (CFC), and applied an activation mask sequence obtained from the local functional brain activity inferred from simultaneously recorded fNIRS signals. Thus, the resulting image sequences preserve spatial and temporal information of the communication and interaction between different neural processes and provide discriminative information that allows differentiation between controls and dyslexic subjects with an AUC of 77.1%. Finally, explainability is improved by introducing an easily comprehensible representation of the SHAP values obtained for the classification method in the brainSHAP maps.

hvEEGNet: a novel deep learning model for high-fidelity EEG reconstruction

Introduction

Modeling multi-channel electroencephalographic (EEG) time-series is a challenging tasks, even for the most recent deep learning approaches. Particularly, in this work, we targeted our efforts to the high-fidelity reconstruction of this type of data, as this is of key relevance for several applications such as classification, anomaly detection, automatic labeling, and brain-computer interfaces.

Methods

We analyzed the most recent works finding that high-fidelity reconstruction is seriously challenged by the complex dynamics of the EEG signals and the large inter-subject variability. So far, previous works provided good results in either high-fidelity reconstruction of single-channel signals, or poor-quality reconstruction of multi-channel datasets. Therefore, in this paper, we present a novel deep learning model, called hvEEGNet, designed as a hierarchical variational autoencoder and trained with a new loss function. We tested it on the benchmark Dataset 2a (including 22-channel EEG data from 9 subjects).

Results

We show that it is able to reconstruct all EEG channels with high-fidelity, fastly (in a few tens of epochs), and with high consistency across different subjects. We also investigated the relationship between reconstruction fidelity and the training duration and, using hvEEGNet as an anomaly detector, we spotted some data in the benchmark dataset that are corrupted and never highlighted before.

Discussion

Thus, hvEEGNet could be very useful in several applications where automatic labeling of large EEG dataset is needed and time-consuming. At the same time, this work opens new fundamental research questions about (1) the effectiveness of deep learning models training (for EEG data) and (2) the need for a systematic characterization of the input EEG data to ensure robust modeling.

Unraveling Brain Synchronisation Dynamics by Explainable Neural Networks using EEG Signals: Application to Dyslexia Diagnosis

The electrical activity of the neural processes involved in cognitive functions is captured in EEG signals, allowing the exploration of the integration and coordination of neuronal oscillations across multiple spatiotemporal scales. We have proposed a novel approach that combines the transformation of EEG signal into image sequences, considering cross-frequency phase synchronisation (CFS) dynamics involved in low-level auditory processing, with the development of a two-stage deep learning model for the detection of developmental dyslexia (DD). This deep learning model exploits spatial and temporal information preserved in the image sequences to find discriminative patterns of phase synchronisation over time achieving a balanced accuracy of up to 83%. This result supports the existence of differential brain synchronisation dynamics between typical and dyslexic seven-year-old readers. Furthermore, we have obtained interpretable representations using a novel feature mask to link the most relevant regions during classification with the cognitive processes attributed to normal reading and those corresponding to compensatory mechanisms found in dyslexia.

A Hardware-Efficient Novelty-Aware Spike Sorting Approach for Brain-Implantable Microsystems

Unsupervised spike sorting, a vital processing step in real-time brain-implantable microsystems, is faced with the prominent challenge of managing nonstationarity in neural signals. In long-term recordings, spike waveforms gradually change and new source neurons are likely to become activated. Adaptive spike sorters combined with on-implant training units effectively process the nonstationary signals at the cost of high hardware resource utilization. On the other hand, static approaches, while being hardware-friendly, are subjected to decreased processing performance in such recordings where the neural signal characteristics gradually change. To strike a balance between the hardware cost and processing performance, this study proposes a hardware-efficient novelty-aware spike sorting approach that is capable of dealing with both variated spike waveforms and spike waveforms generated from new source neurons. Its improved hardware efficiency compared to adaptive ones and capability of dealing with nonstationary signals make it attractive for implantable applications. The proposed novelty-aware spike sorting especially would be a good fit for brain-computer interfaces where long-term, real-time interaction with the brain is required, and the available on-implant hardware resources are limited. Our unsupervised spike sorting benefits from a novelty detection process to deal with neural signal variations. It tracks the spike features so that in case of detecting an unexpected change (novelty detection) both on and off-implant parameters are updated to preserve the performance in new state. To make the proposed approach agile enough to be suitable for brain implants, the on-implant computations are reduced while the computational burden is realized off-implant. The performance of our proposed approach is evaluated using both synthetic and real datasets. The results demonstrate that, in the mean, it is capable of detecting 94.31% of novel spikes (wave-drifted or emerged spikes) with a classification accuracy (CA) of 96.31%. Moreover, an FPGA prototype of the on-implant circuit is implemented and tested. It is shown that in comparison to the OSORT algorithm, a pivotal spike sorting method, our spike sorting provides a higher CA at significantly lower hardware resources. The proposed circuit is also implemented in a 180-nm standard CMOS process, achieving a power consumption of 1.78[Formula: see text][Formula: see text] per channel and a chip area of 0.07[Formula: see text]mm2 per channel.

Atypical low-frequency cortical encoding of speech identifies children with developmental dyslexia

Slow cortical oscillations play a crucial role in processing the speech amplitude envelope, which is perceived atypically by children with developmental dyslexia. Here we use electroencephalography (EEG) recorded during natural speech listening to identify neural processing patterns involving slow oscillations that may characterize children with dyslexia. In a story listening paradigm, we find that atypical power dynamics and phase-amplitude coupling between delta and theta oscillations characterize dyslexic versus other child control groups (typically-developing controls, other language disorder controls). We further isolate EEG common spatial patterns (CSP) during speech listening across delta and theta oscillations that identify dyslexic children. A linear classifier using four delta-band CSP variables predicted dyslexia status (0.77 AUC). Crucially, these spatial patterns also identified children with dyslexia when applied to EEG measured during a rhythmic syllable processing task. This transfer effect (i.e., the ability to use neural features derived from a story listening task as input features to a classifier based on a rhythmic syllable task) is consistent with a core developmental deficit in neural processing of speech rhythm. The findings are suggestive of distinct atypical neurocognitive speech encoding mechanisms underlying dyslexia, which could be targeted by novel interventions.

Probing a neural unreliability account of auditory sensory processing atypicalities in Rett Syndrome

BACKGROUND

In the search for objective tools to quantify neural function in Rett Syndrome (RTT), which are crucial in the evaluation of therapeutic efficacy in clinical trials, recordings of sensory-perceptual functioning using event-related potential (ERP) approaches have emerged as potentially powerful tools. Considerable work points to highly anomalous auditory evoked potentials (AEPs) in RTT. However, an assumption of the typical signal-averaging method used to derive these measures is "stationarity" of the underlying responses - i.e. neural responses to each input are highly stereotyped. An alternate possibility is that responses to repeated stimuli are highly variable in RTT. If so, this will significantly impact the validity of assumptions about underlying neural dysfunction, and likely lead to overestimation of underlying neuropathology. To assess this possibility, analyses at the single-trial level assessing signal-to-noise ratios (SNR), inter-trial variability (ITV) and inter-trial phase coherence (ITPC) are necessary.

METHODS

AEPs were recorded to simple 100 Hz tones from 18 RTT and 27 age-matched controls (Ages: 6-22 years). We applied standard AEP averaging, as well as measures of neuronal reliability at the single-trial level (i.e. SNR, ITV, ITPC). To separate signal-carrying components from non-neural noise sources, we also applied a denoising source separation (DSS) algorithm and then repeated the reliability measures.

RESULTS

Substantially increased ITV, lower SNRs, and reduced ITPC were observed in auditory responses of RTT participants, supporting a "neural unreliability" account. Application of the DSS technique made it clear that non-neural noise sources contribute to overestimation of the extent of processing deficits in RTT. Post-DSS, ITV measures were substantially reduced, so much so that pre-DSS ITV differences between RTT and TD populations were no longer detected. In the case of SNR and ITPC, DSS substantially improved these estimates in the RTT population, but robust differences between RTT and TD were still fully evident.

CONCLUSIONS

To accurately represent the degree of neural dysfunction in RTT using the ERP technique, a consideration of response reliability at the single-trial level is highly advised. Non-neural sources of noise lead to overestimation of the degree of pathological processing in RTT, and denoising source separation techniques during signal processing substantially ameliorate this issue.

Self-Supervised Learning for Electroencephalography

Decades of research have shown machine learning superiority in discovering highly nonlinear patterns embedded in electroencephalography (EEG) records compared with conventional statistical techniques. However, even the most advanced machine learning techniques require relatively large, labeled EEG repositories. EEG data collection and labeling are costly. Moreover, combining available datasets to achieve a large data volume is usually infeasible due to inconsistent experimental paradigms across trials. Self-supervised learning (SSL) solves these challenges because it enables learning from EEG records across trials with variable experimental paradigms, even when the trials explore different phenomena. It aggregates multiple EEG repositories to increase accuracy, reduce bias, and mitigate overfitting in machine learning training. In addition, SSL could be employed in situations where there is limited labeled training data, and manual labeling is costly. This article: 1) provides a brief introduction to SSL; 2) describes some SSL techniques employed in recent studies, including EEG; 3) proposes current and potential SSL techniques for future investigations in EEG studies; 4) discusses the cons and pros of different SSL techniques; and 5) proposes holistic implementation tips and potential future directions for EEG SSL practices.

Probing a neural unreliability account of auditory sensory processing atypicalities in Rett Syndrome

Background In the search for objective tools to quantify neural function in Rett Syndrome (RTT), which are crucial in the evaluation of therapeutic efficacy in clinical trials, recordings of sensory-perceptual functioning using event-related potential (ERP) approaches have emerged as potentially powerful tools. Considerable work points to highly anomalous auditory evoked potentials (AEPs) in RTT. However, an assumption of the typical signal-averaging method used to derive these measures is "stationarity" of the underlying responses - i.e. neural responses to each input are highly stereotyped. An alternate possibility is that responses to repeated stimuli are highly variable in RTT. If so, this will significantly impact the validity of assumptions about underlying neural dysfunction, and likely lead to overestimation of underlying neuropathology. To assess this possibility, analyses at the single-trial level assessing signal-to-noise ratios (SNR), inter-trial variability (ITV) and inter-trial phase coherence (ITPC) are necessary. Methods AEPs were recorded to simple 100Hz tones from 18 RTT and 27 age-matched controls (Ages: 6-22 years). We applied standard AEP averaging, as well as measures of neuronal reliability at the single-trial level (i.e. SNR, ITV, ITPC). To separate signal-carrying components from non-neural noise sources, we also applied a denoising source separation (DSS) algorithm and then repeated the reliability measures. Results Substantially increased ITV, lower SNRs, and reduced ITPC were observed in auditory responses of RTT participants, supporting a "neural unreliability" account. Application of the DSS technique made it clear that non-neural noise sources contribute to overestimation of the extent of processing deficits in RTT. Post-DSS, ITV measures were substantially reduced, so much so that pre-DSS ITV differences between RTT and TD populations were no longer detected. In the case of SNR and ITPC, DSS substantially improved these estimates in the RTT population, but robust differences between RTT and TD were still fully evident. Conclusions To accurately represent the degree of neural dysfunction in RTT using the ERP technique, a consideration of response reliability at the single-trial level is highly advised. Non-neural sources of noise lead to overestimation of the degree of pathological processing in RTT, and denoising source separation techniques during signal processing substantially ameliorate this issue.

Developmental Dyslexia: Insights from EEG-Based Findings and Molecular Signatures-A Pilot Study

Developmental dyslexia (DD) is a learning disorder. Although risk genes have been identified, environmental factors, and particularly stress arising from constant difficulties, have been associated with the occurrence of DD by affecting brain plasticity and function, especially during critical neurodevelopmental stages. In this work, electroencephalogram (EEG) findings were coupled with the genetic and epigenetic molecular signatures of individuals with DD and matched controls. Specifically, we investigated the genetic and epigenetic correlates of key stress-associated genes (NR3C1, NR3C2, FKBP5, GILZ, SLC6A4) with psychological characteristics (depression, anxiety, and stress) often included in DD diagnostic criteria, as well as with brain EEG findings. We paired the observed brain rhythms with the expression levels of stress-related genes, investigated the epigenetic profile of the stress regulator glucocorticoid receptor (GR) and correlated such indices with demographic findings. This study presents a new interdisciplinary approach and findings that support the idea that stress, attributed to the demands of the school environment, may act as a contributing factor in the occurrence of the DD phenotype.

Probing a neural unreliability account of auditory sensory processing atypicalities in Rett Syndrome

Background

In the search for objective tools to quantify neural function in Rett Syndrome (RTT), which are crucial in the evaluation of therapeutic efficacy in clinical trials, recordings of sensory-perceptual functioning using event-related potential (ERP) approaches have emerged as potentially powerful tools. Considerable work points to highly anomalous auditory evoked potentials (AEPs) in RTT. However, an assumption of the typical signal-averaging method used to derive these measures is "stationarity" of the underlying responses - i.e. neural responses to each input are highly stereotyped. An alternate possibility is that responses to repeated stimuli are highly variable in RTT. If so, this will significantly impact the validity of assumptions about underlying neural dysfunction, and likely lead to overestimation of underlying neuropathology. To assess this possibility, analyses at the single-trial level assessing signal-to-noise ratios (SNR), inter-trial variability (ITV) and inter-trial phase coherence (ITPC) are necessary.

Methods

AEPs were recorded to simple 100Hz tones from 18 RTT and 27 age-matched controls (Ages: 6-22 years). We applied standard AEP averaging, as well as measures of neuronal reliability at the single-trial level (i.e. SNR, ITV, ITPC). To separate signal-carrying components from non-neural noise sources, we also applied a denoising source separation (DSS) algorithm and then repeated the reliability measures.

Results

Substantially increased ITV, lower SNRs, and reduced ITPC were observed in auditory responses of RTT participants, supporting a "neural unreliability" account. Application of the DSS technique made it clear that non-neural noise sources contribute to overestimation of the extent of processing deficits in RTT. Post-DSS, ITV measures were substantially reduced, so much so that pre-DSS ITV differences between RTT and TD populations were no longer detected. In the case of SNR and ITPC, DSS substantially improved these estimates in the RTT population, but robust differences between RTT and TD were still fully evident.

Conclusions

To accurately represent the degree of neural dysfunction in RTT using the ERP technique, a consideration of response reliability at the single-trial level is highly advised. Non-neural sources of noise lead to overestimation of the degree of pathological processing in RTT, and denoising source separation techniques during signal processing substantially ameliorate this issue.

A machine learning-based classification model to support university students with dyslexia with personalized tools and strategies

Dyslexia is a specific learning disorder that causes issues related to reading, which affects around 10% of the worldwide population. This can compromise comprehension and memorization skills, and result in anxiety and lack of self-esteem, if no support is provided. Moreover, this support should be highly personalized, to be actually helpful. In this paper, a model to classify the most useful methodologies to support students with dyslexia has been created, with a focus on university alumni. The prediction algorithm is based on supervised machine learning techniques; starting from the issues that dyslexic students experience during their career, it is capable of suggesting customized support digital tools and learning strategies for each of them. The algorithm was trained and tested on data acquired through a self-evaluation questionnaire, which was designed and then spread to more than 1200 university students. It allowed 17 useful tools and 22 useful strategies to be detected. The results of the testing showed an average prediction accuracy higher than 90%, which rises to 94% by renouncing to guess the less-predictable 8 tools/strategies. In the light of this, it is possible to state that the implemented algorithm can achieve the set goal and, thus, reduce the gap between dyslexic and non-dyslexic students. This achievement paves the way for a new modality of facing the problem of dyslexia by university institutions, which aims at modifying teaching activities toward students' needs, instead of simply reducing their study load or duties. This complies with the definition and the aims of inclusivity.

EEG-based classification of individuals with neuropsychiatric disorders using deep neural networks: A systematic review of current status and future directions

The use of deep neural networks for electroencephalogram (EEG) classification has rapidly progressed and gained popularity in recent years, but automatic feature extraction from EEG signals remains a challenging task. The classification of neuropsychiatric disorders demands the extraction of neuro-markers for use in automated EEG classification. Numerous advanced deep learning algorithms can be used for this purpose. In this article, we present a comprehensive review of the main factors and parameters that affect the performance of deep neural networks in classifying different neuropsychiatric disorders using EEG signals. We also analyze the EEG features used for improving classification performance. Our analysis includes 82 scientific journal papers that applied deep neural networks for subject-wise classification based on EEG signals. We extracted information on the EEG dataset and types of disorders, deep neural network structures, performance, and hyperparameters. The results show that most studies have focused on clinical classification, achieving an average accuracy of 91.83 ± 7.34, with convolutional neural networks (CNNs) being the most frequently used network architecture and resting-state EEG signals being the most commonly used data type. Additionally, the review reveals that depression (N = 18), Alzheimer's (N = 11), and schizophrenia (N = 11) were studied more frequently than other types of neuropsychiatric disorders. Our review provides insight into the performance of deep neural networks in EEG classification and highlights the importance of EEG feature extraction in improving classification accuracy. By identifying the main factors and parameters that affect deep neural network performance in EEG classification, our review can guide future research in this area. We hope that our findings will encourage further exploration of deep learning methods for EEG classification and contribute to the development of more accurate and effective methods for diagnosing and monitoring neuropsychiatric disorders using EEG signals.

Hybrid Genetic Algorithm for Clustering IC Topographies of EEGs

Clustering of independent component (IC) topographies of Electroencephalograms (EEG) is an effective way to find brain-generated IC processes associated with a population of interest, particularly for those cases where event-related potential features are not available. This paper proposes a novel algorithm for the clustering of these IC topographies and compares its results with the most currently used clustering algorithms. In this study, 32-electrode EEG signals were recorded at a sampling rate of 500 Hz for 48 participants. EEG signals were pre-processed and IC topographies computed using the AMICA algorithm. The algorithm implements a hybrid approach where genetic algorithms are used to compute more accurate versions of the centroids and the final clusters after a pre-clustering phase based on spectral clustering. The algorithm automatically selects the optimum number of clusters by using a fitness function that involves local-density along with compactness and separation criteria. Specific internal validation metrics adapted to the use of the absolute correlation coefficient as the similarity measure are defined for the benchmarking process. Assessed results across different ICA decompositions and groups of subjects show that the proposed clustering algorithm significantly outperforms the (baseline) clustering algorithms provided by the software EEGLAB, including CORRMAP.

Extraction of discriminative features from EEG signals of dyslexic children; before and after the treatment

Dyslexia is a neurological disorder manifested as difficulty reading and writing. It can occur despite adequate instruction, intelligence, and intact sensory abilities. Different electroencephalogram (EEG) patterns have been demonstrated between dyslexic and healthy subjects in previous studies. This study focuses on the difference between patients before and after treatment. The main goal is to identify the subset of features that adequately discriminate subjects before and after a specific treatment plan. The treatment consists of Transcranial Direct Current Stimulation (tDCS) and occupational therapy using the BrainWare SAFARI software. The EEG signals of sixteen dyslexic children were recorded during the eyes-closed resting state before and after treatment. The preprocessing step was followed by the extraction of a wide range of features to investigate the differences related to the treatment. An optimal subset of features extracted from recorded EEG signals was determined using Principal Component Analysis (PCA) in conjunction with the Sequential Floating Forward Selection (SFFS) algorithm. The results showed that treatment leads to significant changes in EEG features like spectral and phase-related EEG features, in various regions. It has been demonstrated that the extracted subset of discriminative features can be useful for classification applications in treatment assessment. The most discriminative subset of features could classify the data with an accuracy of 92% with SVM classifier. The above result confirms the efficacy of the treatment plans in improving dyslexic children's cognitive skills.

Tiled Sparse Coding in Eigenspaces for Image Classification

The automation in the diagnosis of medical images is currently a challenging task. The use of Computer Aided Diagnosis (CAD) systems can be a powerful tool for clinicians, especially in situations when hospitals are overflowed. These tools are usually based on artificial intelligence (AI), a field that has been recently revolutionized by deep learning approaches. blackThese alternatives usually obtain a large performance based on complex solutions, leading to a high computational cost and the need of having large databases. In this work, we propose a classification framework based on sparse coding. Images are blackfirst partitioned into different tiles, and a dictionary is built after applying PCA to these tiles. The original signals are then transformed as a linear combination of the elements of the dictionary. blackThen, they are reconstructed by iteratively deactivating the elements associated with each component. Classification is finally performed employing as features the subsequent reconstruction errors. Performance is evaluated in a real context where distinguishing between four different pathologies: control versus bacterial pneumonia versus viral pneumonia versus COVID-19. blackOur system differentiates between pneumonia patients and controls with an accuracy of 97.74%, whereas in the 4-class context the accuracy is 86.73%. The excellent results and the pioneering use of sparse coding in this scenario evidence that our proposal can assist clinicians when their workload is high.

Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms

Electroencephalography (EEG) signal classification is a challenging task due to the low signal-to-noise ratio and the usual presence of artifacts from different sources. Different classification techniques, which are usually based on a predefined set of features extracted from the EEG band power distribution profile, have been previously proposed. However, the classification of EEG still remains a challenge, depending on the experimental conditions and the responses to be captured. In this context, the use of deep neural networks offers new opportunities to improve the classification performance without the use of a predefined set of features. Nevertheless, Deep Learning architectures include a vast number of hyperparameters on which the performance of the model relies. In this paper, we propose a method for optimizing Deep Learning models, not only the hyperparameters, but also their structure, which is able to propose solutions that consist of different architectures due to different layer combinations. The experimental results corroborate that deep architectures optimized by our method outperform the baseline approaches and result in computationally efficient models. Moreover, we demonstrate that optimized architectures improve the energy efficiency with respect to the baseline models.