Search Results (20)

Wearable electroencephalography (EEG) enables brain monitoring in real-world environments beyond clinical settings; however, the relaxed constraints of the acquisition setup often compromise signal quality. This review examines methods for artifact detection and for the identification of artifact categories (e.g., ocular) and specific sources (e.g., eye blink) in wearable EEG. A systematic search was conducted across six databases using the query: (“electroencephalographic” OR “electroencephalography” OR “EEG”) AND (“Artifact detection” OR “Artifact identification” OR “Artifact removal” OR “Artifact rejection”) AND “wearable”. Following PRISMA guidelines, 58 studies were included. Artifacts in wearable EEG exhibit specific features due to dry electrodes, reduced scalp coverage, and subject mobility, yet only a few studies explicitly address these peculiarities. Most pipelines integrate detection and removal phases but rarely separate their impact on performance metrics, mainly accuracy (71%) when the clean signal is the reference and selectivity (63%), assessed with respect to physiological signal. Wavelet transforms and ICA, often using thresholding as a decision rule, are among the most frequently used techniques for managing ocular and muscular artifacts. ASR-based pipelines are widely applied for ocular, movement, and instrumental artifacts. Deep learning approaches are emerging, especially for muscular and motion artifacts, with promising applications in real-time settings. Auxiliary sensors (e.g., IMUs) are still underutilized despite their potential in enhancing artifact detection under ecological conditions. Only two studies addressed artifact category identification. A mapping of validated pipelines per artifact type and a survey of public datasets are provided to support benchmarking and reproducibility. Full article

Purpose: To systematically review the evidence regarding the characteristics of Optical Coherence Tomography Angiography (OCTA) in acute retinal arterial occlusion (RAO), with a particular focus on vascular alterations across the superficial and deep capillary plexuses, choroid, and peripapillary regions. Methods: A comprehensive literature search was performed across PubMed, Web of Science, Scopus, EMBASE, Google Scholar, and the Cochrane Database up to April 2025. The search terms included “Optical coherence tomography angiography,” “OCTA,” “Retinal arterial occlusion,” “Central retinal artery occlusion,” and “Branch retinal artery occlusion.” Studies were included if they evaluated the role of OCTA in diagnosing or assessing acute RAO. Case reports, conference abstracts, and non-English articles were excluded. Two reviewers independently conducted the study selection and data extraction. The methodological quality of the included studies was assessed using the Risk of Bias in Non-randomized Studies of Interventions (ROBINS-I) tool. Results: The initial search yielded 457 articles, from which 10 studies were ultimately included in the final analysis after a rigorous screening process excluding duplicates, non-English publications, and ineligible articles based on title, abstract, or full-text review. The included studies consistently demonstrated that OCTA is a valuable, noninvasive modality for evaluating microvascular changes in RAO. Key OCTA findings in acute RAO include significant perfusion deficits and reduced vessel density in both the superficial capillary plexus (SCP) and deep capillary plexus (DCP). Several studies noted more pronounced involvement of the SCP compared to the DCP. OCTA parameters, such as vessel density in the macular region, have been found to correlate with visual acuity, suggesting a prognostic value. While findings regarding the foveal avascular zone (FAZ) were mixed, the peripapillary area frequently showed reduced vessel density. Conclusion: Acute RAO is an ocular emergency that causes microvascular ischemic changes detectable by OCTA. This review establishes OCTA as a significant noninvasive tool for diagnosing, monitoring, and prognosticating RAO. It effectively visualizes perfusion deficits that correlate with clinical outcomes. However, limitations such as susceptibility to motion artifacts, segmentation errors, and the lack of standardized normative data must be considered. Future standardization of OCTA protocols and analysis is essential to enhance its clinical application in managing RAO. Full article

The assessment of ocular surface temperature (OST) plays a pivotal role in the diagnosis and management of various ocular diseases. This paper introduces significant enhancements to the ThermOcular system, initially developed for precise OST measurement using infrared (IR) thermography. These advancements focus on accuracy improvements that reduce user dependency and increase the system’s diagnostic capabilities. A novel addition to the system includes the use of EyeTags, which assist clinicians in selecting control points more easily, thus reducing errors associated with manual selection. Furthermore, the integration of state-of-the-art semantic segmentation models trained on the newest dataset is explored. Among these, the OCRNet-HRNet-w18 model achieved a segmentation accuracy of 96.21% MIOU, highlighting the effectiveness of the improved pipeline. Additionally, the challenge of eliminating eyelashes in IR frames, which cause artifactual measurement errors in OST assessments, is addressed. Through a newly developed method, the influence of eyelashes is eliminated, thereby enhancing the precision of temperature readings. Moreover, an algorithm for blink detection and elimination is implemented, significantly improving upon the basic methods previously utilized. These innovations not only enhance the reliability of OST measurements, but also contribute to the system’s efficiency and diagnostic accuracy, marking a significant step forward in ocular health monitoring and diagnostics. Full article

Whilst balance disturbances are common in people with advanced Parkinson’s disease, it has not previously been possible to record vestibular evoked myogenic potentials (VEMPs), and thus otolithic function, during monopolar deep brain stimulation (DBS) due to an overwhelming number of signal artifacts. A µVEMP device has been developed with parameters to allow VEMP recording during monopolar DBS. The aim of this proof-of-concept study was to ascertain whether, during DBS, VEMP responses could be accurately identified after signal filtering recordings from the µVEMP device. Both cervical and ocular VEMP responses to taps and clicks were recorded with the µVEMP device in five Parkinson’s disease patients with monopolar deep brain stimulation. Additionally, VEMP responses were recorded in one patient whose deep brain stimulation was switched ON and OFF to allow a direct comparison of the signals. Customised post-filtering analysis allowed successful VEMP response extraction from signal noise in all five patients with deep brain stimulation ON. VEMP responses with deep brain stimulation ON after filtering were similar to VEMP responses with deep brain stimulation OFF, validating the filtering analysis. We present the first study to record VEMP signals with monopolar deep brain stimulation using a µVEMP device coupled with customised post-filtering. This finding will allow patients to be assessed without requiring adjustment of their therapeutic deep brain stimulation. Full article

Electroencephalography (EEG) is a non-invasive technique with high temporal resolution and cost-effective, portable, and easy-to-use features. Motor imagery EEG (MI-EEG) data classification is one of the key applications within brain–computer interface (BCI) systems, utilizing EEG signals from motor imagery tasks. BCI is very useful for people with severe mobility issues like quadriplegics, spinal cord injury patients, stroke patients, etc., giving them the freedom to a certain extent to perform activities without the need for a caretaker, like driving a wheelchair. However, motion artifacts can significantly affect the quality of EEG recordings. The conventional EEG enhancement algorithms are effective in removing ocular and muscle artifacts for a stationary subject but not as effective when the subject is in motion, e.g., a wheelchair user. In this research study, we propose an empirical error model-based artifact removal approach for the cross-subject classification of motor imagery (MI) EEG data using a modified CNN-based deep learning algorithm, designed to assist wheelchair users with severe mobility issues. The classification method applies to real tasks with measured EEG data, focusing on accurately interpreting motor imagery signals for practical application. The empirical error model evolved from the inertial sensor-based acceleration data of the subject in motion, the weight of the wheelchair, the weight of the subject, and the surface friction of the terrain under the wheelchair. Three different wheelchairs and five different terrains, including road, brick, concrete, carpet, and marble, are used for artifact data recording. After evaluating and benchmarking the proposed CNN and empirical model, the classification accuracy achieved is 94.04% for distinguishing between four specific classes: left, right, front, and back. This accuracy demonstrates the model’s effectiveness compared to other state-of-the-art techniques. The comparative results show that the proposed approach is a potentially effective way to raise the decoding efficiency of motor imagery BCI. Full article

Electroencephalography (EEG) is a non-invasive technique widely used in neuroscience to diagnose neural disorders and analyse brain activity. However, ocular and myogenic artifacts from eye movements and facial muscle activity often contaminate EEG signals, compromising signal analysis accuracy. While deep learning models are a popular choice for denoising EEG signals, most focus on removing either ocular or myogenic artifacts independently. This paper introduces a novel EEG denoising model capable of handling the simultaneous occurrence of both artifacts. The model uses convolutional layers to extract spatial features and a fully connected layer to reconstruct clean signals from learned features. The model integrates the Adam optimiser, average pooling, and ReLU activation to effectively capture and restore clean EEG signals. It demonstrates superior performance, achieving low training and validation losses with a significantly reduced $RRMSE$ value of 0.35 in both the temporal and spectral domains. A high cross-correlation coefficient of 0.94 with ground-truth EEG signals confirms the model’s fidelity. Compared to the existing architectures and models (FPN, UNet, MCGUNet, LinkNet, MultiResUNet3+, Simple CNN, Complex CNN) across a range of signal-to-noise ratio values, the model shows superior performance for artifact removal. It also mitigates overfitting, underscoring its robustness in artifact suppression. Full article

Objectives: Naturally, there are several challenges, such as muscular artifacts, ocular movements and electrical interferences that depend on precise diagnosis and classification, which hamper exact epileptic seizure detection. This study has been conducted to improve seizure detection accuracy in epilepsy patients using an advanced preprocessing technique that could remove such noxious artifacts. Methods: In the frame of this paper, the core tool in the area of epilepsy, EEG, will be applied to record and analyze the electrical patterns of the brain. The dataset includes recordings of seven epilepsy patients taken by the Unit of Neurology and Neurophysiology, University of Siena. The preprocessing techniques employed include advanced artifact removal and signal enhancement methods. We introduced Peak-to-Peak Amplitude Fluctuation (PPAF) to assess amplitude variability within Event-Related Potential (ERP) waveforms. This approach was applied to data from patients experiencing 3–5 seizures, categorized into three distinct groups. Results: The results indicated that the frontal and parietal regions, particularly the electrode areas Cz, Pz and Fp2, are the main contributors to epileptic seizures. Additionally, the implementation of the PPAF metric enhanced the effectiveness of seizure detection and classification algorithms, achieving accuracy rates of 99%, 98% and 95% for datasets with three, four and five seizures, respectively. Conclusions: The present research extends the epilepsy diagnosis with clues on brain activity during seizures and further demonstrates the effectiveness of advanced preprocessing techniques. The introduction of PPAF as a metric could have promising potential in improving both the accuracy and reliability of epilepsy seizure detection algorithms. These observations provide important implications for control and treatment both in focal and in generalized epilepsy. Full article

Ocular artifacts, including blinks and saccades, pose significant challenges in the analysis of electroencephalographic (EEG) data, often obscuring crucial neural signals. This tutorial provides a comprehensive guide to the most effective methods for correcting these artifacts, with a focus on algorithms designed for both laboratory and real-world settings. We review traditional approaches, such as regression-based techniques and Independent Component Analysis (ICA), alongside more advanced methods like Artifact Subspace Reconstruction (ASR) and deep learning-based algorithms. Through detailed step-by-step instructions and comparative analysis, this tutorial equips researchers with the tools necessary to maintain the integrity of EEG data, ensuring accurate and reliable results in neurophysiological studies. The strategies discussed are particularly relevant for wearable EEG systems and real-time applications, reflecting the growing demand for robust and adaptable solutions in applied neuroscience. Full article

(1) Background: The electroencephalogram (EEG) is frequently corrupted by ocular artifacts such as saccades and blinks. Methods for correcting these artifacts include independent component analysis (ICA) and recursive-least-squares (RLS) adaptive filtering (-AF). Here, we introduce a new method, AFFiNE, that applies Bayesian adaptive regression spline (BARS) fitting to the adaptive filter’s reference noise input to address the known limitations of both ICA and RLS-AF, and then compare the performance of all three methods. (2) Methods: Artifact-corrected P300 morphologies, topographies, and measurements were compared between the three methods, and to known truth conditions, where possible, using real and simulated blink-corrupted event-related potential (ERP) datasets. (3) Results: In both simulated and real datasets, AFFiNE was successful at removing the blink artifact while preserving the underlying P300 signal in all situations where RLS-AF failed. Compared to ICA, AFFiNE resulted in either a practically or an observably comparable error. (4) Conclusions: AFFiNE is an ocular artifact correction technique that is implementable in online analyses; it can adapt to being non-stationarity and is independent of channel density and recording duration. AFFiNE can be utilized for the removal of blink artifacts in situations where ICA may not be practically or theoretically useful. Full article

Nonmydriatic retinal fundus images often suffer from quality issues and artifacts due to ocular or systemic comorbidities, leading to potential inaccuracies in clinical diagnoses. In recent times, deep learning methods have been widely employed to improve retinal image quality. However, these methods often require large datasets and lack robustness in clinical settings. Conversely, the inherent stability and adaptability of traditional unsupervised learning methods, coupled with their reduced reliance on extensive data, render them more suitable for real-world clinical applications, particularly in the limited data context of high noise levels or a significant presence of artifacts. However, existing unsupervised learning methods encounter challenges such as sensitivity to noise and outliers, reliance on assumptions like cluster shapes, and difficulties with scalability and interpretability, particularly when utilized for retinal image enhancement. To tackle these challenges, we propose a novel robust PCA (RPCA) method with low-rank sparse decomposition that also integrates affine transformations ${\tau }_i$, weighted nuclear norm, and the $L_{2,1}$ norms, aiming to overcome existing method limitations and to achieve image quality improvement unseen by these methods. We employ the weighted nuclear norm $\left(L_{w,\ast }\right)$ to assign weights to singular values to each retinal images and utilize the $L_{2,1}$ norm to eliminate correlated samples and outliers in the retinal images. Moreover, ${\tau }_i$ is employed to enhance retinal image alignment, making the new method more robust to variations, outliers, noise, and image blurring. The Alternating Direction Method of Multipliers (ADMM) method is used to optimally determine parameters, including ${\tau }_i$, by solving an optimization problem. Each parameter is addressed separately, harnessing the benefits of ADMM. Our method introduces a novel parameter update approach and significantly improves retinal image quality, detecting cataracts, and diabetic retinopathy. Simulation results confirm our method’s superiority over existing state-of-the-art methods across various datasets. Full article

The electroencephalogram (EEG) has recently emerged as a pivotal tool in brain imaging analysis, playing a crucial role in accurately interpreting brain functions and states. To address the problem that the presence of ocular artifacts in the EEG signals of patients with obstructive sleep apnea syndrome (OSAS) severely affects the accuracy of sleep staging recognition, we propose a method that integrates a support vector machine (SVM) with genetic algorithm (GA)-optimized variational mode decomposition (VMD) and second-order blind identification (SOBI) for the removal of ocular artifacts from single-channel EEG signals. The SVM is utilized to identify artifact-contaminated segments within preprocessed single-channel EEG signals. Subsequently, these signals are decomposed into variational modal components across different frequency bands using the GA-optimized VMD algorithm. These components undergo further decomposition via the SOBI algorithm, followed by the computation of their approximate entropy. An approximate entropy threshold is set to identify and remove components laden with ocular artifacts. Finally, the signal is reconstructed using the inverse SOBI and VMD algorithms. To validate the efficacy of our proposed method, we conducted experiments utilizing both simulated data and real OSAS sleep EEG data. The experimental results demonstrate that our algorithm not only effectively mitigates the presence of ocular artifacts but also minimizes EEG signal distortion, thereby enhancing the precision of sleep staging recognition based on the EEG signals of OSAS patients. Full article

This manuscript describes an implementation of scripts of code aimed at reducing the influence of artifacts, specifically focused on ocular artifacts, in the measurement and processing of electroencephalogram (EEG) signals. This process is of importance because it benefits the analysis and study of long trial samples when the appearance of ocular artifacts cannot be avoided by simply discarding trials. The implementations provided to the reader illustrate, with slight modifications, previously proposed methods aimed at the partial or complete elimination of EEG channels or components obtained after independent component analysis (ICA) of EEG signals. These channels or components are those that resemble the electro-oculogram (EOG) signals in which artifacts are detected. In addition to the description of each of the provided functions, examples of utilization and illustrative figures will be included to show the expected results and processing pipeline. Full article

Eye diseases can result in various challenges and visual impairments. These diseases can affect an individual’s quality of life and general health and well-being. The symptoms of eye diseases vary widely depending on the nature and severity of the disease. Early diagnosis can protect individuals from visual impairment. Artificial intelligence (AI)-based eye disease classification (EDC) assists physicians in providing effective patient services. However, the complexities of the fundus image affect the classifier’s performance. There is a demand for a practical EDC for identifying eye diseases in the earlier stages. Thus, the author intends to build an EDC model using the deep learning (DL) technique. Denoising autoencoders are used to remove the noises and artifacts from the fundus images. The single-shot detection (SSD) approach generates the key features. The whale optimization algorithm (WOA) with Levy Flight and Wavelet search strategy is followed for selecting the features. In addition, the Adam optimizer (AO) is applied to fine-tune the ShuffleNet V2 model to classify the fundus images. Two benchmark datasets, ocular disease intelligent recognition (ODIR) and EDC datasets, are utilized for performance evaluation. The proposed EDC model achieved accuracy and Kappa values of 99.1 and 96.4, and 99.4 and 96.5, in the ODIR and EDC datasets, respectively. It outperformed the recent EDC models. The findings highlight the significance of the proposed EDC model in classifying eye diseases using complex fundus images. Healthcare centers can implement the proposed model to improve their standards and serve a more significant number of patients. In the future, the proposed model can be extended to identify a comprehensive range of eye diseases. Full article

Anticipatory event-related potentials (ERPs) precede upcoming events such as stimuli or actions. These ERPs are usually obtained in cued sensory–motor tasks employing a warning stimulus that precedes a probe stimulus as in the contingent negative variation (CNV) paradigms. The CNV wave has been widely studied, from clinical to brain–computer interface (BCI) applications, and has been shown to emerge in medial frontoparietal areas, localized in the cingulate and supplementary motor areas. Several dated studies also suggest the existence of a prefrontal CNV, although this component was not confirmed by later studies due to the contamination of ocular artifacts. Another lesser-known anticipatory ERP is the prefrontal negativity (pN) that precedes the uncued probe stimuli in discriminative response tasks and has been localized in the inferior frontal gyrus. This study aimed to characterize the pN by comparing it with the CNV in cued and uncued tasks and test if the pN could be associated with event preparation, temporal preparation, or both. To achieve these aims, high-density electroencephalographic recording and advanced ERP analysis controlling for ocular activity were obtained in 25 volunteers who performed 4 different visuomotor tasks. Our results showed that the pN amplitude was largest in the condition requiring both time and event preparation, medium in the condition requiring event preparation only, and smallest in the condition requiring temporal preparation only. We concluded that the prefrontal CNV could be associated with the pN, and this activity emerges in complex tasks requiring the anticipation of both the category and timing of the upcoming stimulus. The proposed method can be useful in BCI studies investigating the endogenous neural signatures triggered by different sensorimotor paradigms. Full article

Drowsiness is one of the main causes of road accidents and endangers the lives of road users. Recently, there has been considerable interest in utilizing features extracted from electroencephalography (EEG) signals to detect driver drowsiness. However, in most of the work performed in this area, the eyeblink or ocular artifacts present in EEG signals are considered noise and are removed during the preprocessing stage. In this study, we examined the possibility of extracting features from the EEG ocular artifacts themselves to perform classification between alert and drowsy states. In this study, we used the BLINKER algorithm to extract 25 blink-related features from a public dataset comprising raw EEG signals collected from 12 participants. Different machine learning classification models, including the decision tree, the support vector machine (SVM), the K-nearest neighbor (KNN) method, and the bagged and boosted tree models, were trained based on the seven selected features. These models were further optimized to improve their performance. We were able to show that features from EEG ocular artifacts are able to classify drowsy and alert states, with the optimized ensemble-boosted trees yielding the highest accuracy of 91.10% among all classic machine learning models. Full article