Automated detection of artefacts in neonatal EEG with residual neural networks

Advances in Electroencephalographic Biomarkers of Neonatal Hypoxic Ischemic Encephalopathy

Electroencephalography (EEG) is a key objective biomarker of newborn brain function, delivering critical, cotside insights to aid the management of encephalopathy. Access to continuous EEG is limited, forcing reliance on subjective clinical assessments. In hypoxia ischaemia, the primary cause of encephalopathy, alterations in EEG patterns correlate with. injury severity and evolution. As HIE evolves, causing secondary neuronal death, EEG can track injury progression, informing neuroprotective strategies, seizure management and prognosis. Despite its value, challenges with interpretation and lack of on site expertise has limited its broader adoption. Technological advances, particularly in digital EEG and machine learning, are enhancing real-time analysis. This will allow EEG to expand its role in HIE diagnosis, management and outcome prediction.

Prognostic value of quantitative EEG in early hours of life for neonatal encephalopathy and neurodevelopmental outcomes

BACKGROUND

The ability to determine severity of encephalopathy is crucial for early neuroprotective therapies and for predicting neurodevelopmental outcome. The objective of this study was to assess a novel brain state of newborn (BSN) trend to distinguish newborns with presence of hypoxic ischemic encephalopathy (HIE) within hours after birth and predict neurodevelopmental outcomes at 2 years of age.

METHOD

This is a prospective cohort study of newborns at 36 weeks' gestation or later with and without HIE at birth. The Total Sanart Score (TSS) was calculated based on a modified Sarnat exam within 6 h of life. BSN was calculated from electroencephalogram (EEG) measurements initiated after birth. The primary outcome at 2 year of age was a diagnosis of death or disability using the Bayley Scales of Infant Development III.

RESULTS

BSN differentiated between normal and abnormal neurodevelopmental outcomes throughout the entire recording period from 6 h of life. Additionally, infants with lower BSN values had higher odds of neurodevelopmental impairment and HIE. BSN distinguished between normal (n = 86) and HIE (n = 46) and showed a significant correlation with the concomitant TSS.

CONCLUSION

BSN is a sensitive real-time marker for monitoring dynamic progression of encephalopathy and predicting neurodevelopmental impairment.

IMPACT

This is a prospective cohort study to investigate the ability of brain state of newborn (BSN) trend to predict neurodevelopmental outcome within the first day of life and identify severity of encephalopathy. BSN predicts neurodevelopmental outcomes at 2 years of age and the severity of encephalopathy severity. It also correlates with the Total Sarnat Score from the modified Sarnat exam. BSN could serve as a promising bedside trend aiding in accurate assessment and identification of newborns who may benefit from additional neuroprotection therapies.

Clinical outcome prediction with an automated EEG trend, Brain State of the Newborn, after perinatal asphyxia

OBJECTIVE

To evaluate the utility of a fully automated deep learning -based quantitative measure of EEG background, Brain State of the Newborn (BSN), for early prediction of clinical outcome at four years of age.

METHODS

The EEG monitoring data from eighty consecutive newborns was analyzed using the automatically computed BSN trend. BSN levels during the first days of life (a of total 5427 hours) were compared to four clinical outcome categories: favorable, cerebral palsy (CP), CP with epilepsy, and death. The time dependent changes in BSN-based prediction for different outcomes were assessed by positive/negative predictive value (PPV/NPV) and by estimating the area under the receiver operating characteristic curve (AUC).

RESULTS

The BSN values were closely aligned with four visually determined EEG categories (p < 0·001), as well as with respect to clinical milestones of EEG recovery in perinatal Hypoxic Ischemic Encephalopathy (HIE; p < 0·003). Favorable outcome was related to a rapid recovery of the BSN trend, while worse outcomes related to a slow BSN recovery. Outcome predictions with BSN were accurate from 6 to 48 hours of age: For the favorable outcome, the AUC ranged from 95 to 99% (peak at 12 hours), and for the poor outcome the AUC ranged from 96 to 99% (peak at 12 hours). The optimal BSN levels for each PPV/NPV estimate changed substantially during the first 48 hours, ranging from 20 to 80.

CONCLUSIONS

We show that the BSN provides an automated, objective, and continuous measure of brain activity in newborns.

SIGNIFICANCE

The BSN trend discloses the dynamic nature that exists in both cerebral recovery and outcome prediction, supports individualized patient care, rapid stratification and early prognosis.

Quantitative EEG features during the first day correlate to clinical outcome in perinatal asphyxia

OBJECTIVE

To assess whether computational electroencephalogram (EEG) measures during the first day of life correlate to clinical outcomes in infants with perinatal asphyxia with or without hypoxic-ischemic encephalopathy (HIE).

METHODS

We analyzed four-channel EEG monitoring data from 91 newborn infants after perinatal asphyxia. Altogether 42 automatically computed amplitude- and synchrony-related EEG features were extracted as 2-hourly average at very early (6 h) and early (24 h) postnatal age; they were correlated to the severity of HIE in all infants, and to four clinical outcomes available in a subcohort of 40 newborns: time to full oral feeding (nasogastric tube NGT), neonatal brain MRI, Hammersmith Infant Neurological Examination (HINE) at three months, and Griffiths Scales at two years.

RESULTS

At 6 h, altogether 14 (33%) EEG features correlated significantly to the HIE grade ([r]= 0.39-0.61, p < 0.05), and one feature correlated to NGT ([r]= 0.50). At 24 h, altogether 13 (31%) EEG features correlated significantly to the HIE grade ([r]= 0.39-0.56), six features correlated to NGT ([r]= 0.36-0.49) and HINE ([r]= 0.39-0.61), while no features correlated to MRI or Griffiths Scales.

CONCLUSIONS

Our results show that the automatically computed measures of early cortical activity may provide outcome biomarkers for clinical and research purposes.

IMPACT

The early EEG background and its recovery after perinatal asphyxia reflect initial severity of encephalopathy and its clinical recovery, respectively. Computational EEG features from the early hours of life show robust correlations to HIE grades and to early clinical outcomes. Computational EEG features may have potential to be used as cortical activity biomarkers in early hours after perinatal asphyxia.

Microstate Analysis Reflects Maturation of the Preterm Brain

Preterm neonates are at risk of long-term neurodevelopmental impairments due to disruption of natural brain development. Electroencephalography (EEG) analysis can provide insights into brain development of preterm neonates. This study aims to explore the use of microstate (MS) analysis to evaluate global brain dynamics changes during maturation in preterm neonates with normal neurodevelopmental outcome.The dataset included 135 EEGs obtained from 48 neonates at varying postmenstrual ages (26.4 to 47.7 weeks), divided into four age groups. For each recording we extracted a 5-minute epoch during quiet sleep (QS) and during non-quiet sleep (NQS), resulting in eight groups (4 age group x 2 sleep states). We compared MS maps and corresponding (map-specific) MS metrics across groups using group-level maps. Additionally, we investigated individual map metrics.Four group-level MS maps accounted for approximately 70% of the global variance and showed non-random syntax. MS topographies and transitions changed significantly when neonates reached 37 weeks. For both sleep states and all MS maps, MS duration decreased and occurrence increased with age. The same relationships were found using individual maps, showing strong correlations (Pearson coefficients up to 0.74) between individual map metrics and post-menstrual age. Moreover, the Hurst exponent of the individual MS sequence decreased with age.The observed changes in MS metrics with age might reflect the development of the preterm brain, which is characterized by formation of neural networks. Therefore, MS analysis is a promising tool for monitoring preterm neonatal brain maturation, while our study can serve as a valuable reference for investigating EEGs of neonates with abnormal neurodevelopmental outcomes.

Neonatal cortical activity organizes into transient network states that are affected by vigilance states and brain injury

Early neurodevelopment is critically dependent on the structure and dynamics of spontaneous neuronal activity; however, the natural organization of newborn cortical networks is poorly understood. Recent adult studies suggest that spontaneous cortical activity exhibits discrete network states with physiological correlates. Here, we studied newborn cortical activity during sleep using hidden Markov modeling to determine the presence of such discrete neonatal cortical states (NCS) in 107 newborn infants, with 47 of them presenting with a perinatal brain injury. Our results show that neonatal cortical activity organizes into four discrete NCSs that are present in both cardinal sleep states of a newborn infant, active and quiet sleep, respectively. These NCSs exhibit state-specific spectral and functional network characteristics. The sleep states exhibit different NCS dynamics, with quiet sleep presenting higher fronto-temporal activity and a stronger brain-wide neuronal coupling. Brain injury was associated with prolonged lifetimes of the transient NCSs, suggesting lowered dynamics, or flexibility, in the cortical networks. Taken together, the findings suggest that spontaneously occurring transient network states are already present at birth, with significant physiological and pathological correlates; this NCS analysis framework can be fully automatized, and it holds promise for offering an objective, global level measure of early brain function for benchmarking neurodevelopmental or clinical research.

A Modified Aquila-Based Optimized XGBoost Framework for Detecting Probable Seizure Status in Neonates

Electroencephalography (EEG) is increasingly being used in pediatric neurology and provides opportunities to diagnose various brain illnesses more accurately and precisely. It is thought to be one of the most effective tools for identifying newborn seizures, especially in Neonatal Intensive Care Units (NICUs). However, EEG interpretation is time-consuming and requires specialists with extensive training. It can be challenging and time-consuming to distinguish between seizures since they might have a wide range of clinical characteristics and etiologies. Technological advancements such as the Machine Learning (ML) approach for the rapid and automated diagnosis of newborn seizures have increased in recent years. This work proposes a novel optimized ML framework to eradicate the constraints of conventional seizure detection techniques. Moreover, we modified a novel meta-heuristic optimization algorithm (MHOA), named Aquila Optimization (AO), to develop an optimized model to make our proposed framework more efficient and robust. To conduct a comparison-based study, we also examined the performance of our optimized model with that of other classifiers, including the Decision Tree (DT), Random Forest (RF), and Gradient Boosting Classifier (GBC). This framework was validated on a public dataset of Helsinki University Hospital, where EEG signals were collected from 79 neonates. Our proposed model acquired encouraging results showing a 93.38% Accuracy Score, 93.9% Area Under the Curve (AUC), 92.72% F1 score, 65.17% Kappa, 93.38% sensitivity, and 77.52% specificity. Thus, it outperforms most of the present shallow ML architectures by showing improvements in accuracy and AUC scores. We believe that these results indicate a major advance in the detection of newborn seizures, which will benefit the medical community by increasing the reliability of the detection process.

A multi-task and multi-channel convolutional neural network for semi-supervised neonatal artefact detection

Objective. Automated artefact detection in the neonatal electroencephalogram (EEG) is crucial for reliable automated EEG analysis, but limited availability of expert artefact annotations challenges the development of deep learning models for artefact detection. This paper proposes a semi-supervised deep learning approach for artefact detection in neonatal EEG that requires few labelled data by training a multi-task convolutional neural network (CNN).Approach. An unsupervised and a supervised objective were jointly optimised by combining an autoencoder and an artefact classifier in one multi-output model that processes multi-channel EEG inputs. The proposed semi-supervised multi-task training strategy was compared to a classical supervised strategy and other existing state-of-the-art models. The models were trained and tested separately on two different datasets, which contained partially annotated multi-channel neonatal EEG. Models were evaluated using the F1-statistic and the relevance of the method was investigated in the context of a functional brain age (FBA) prediction model.Main results. The proposed multi-task and multi-channel CNN methods outperformed state-of-the-art methods, reaching F1 scores of 86.2% and 95.7% on two separate datasets. The proposed semi-supervised multi-task training strategy was shown to be superior to a classical supervised training strategy when the amount of labels in the dataset was artificially reduced. Finally, we found that the error of a brain age prediction model correlated with the amount of automatically detected artefacts in the EEG segment.Significance. Our results show that the proposed semi-supervised multi-task training strategy can train CNNs successfully even when the amount of labels in the dataset is limited. Therefore, this method is a promising semi-supervised technique for developing deep learning models with scarcely labelled data. Moreover, a correlation between the error of FBA estimates and the amount of detected artefacts in the corresponding EEG segments indicates the relevance of artefact detection for robust automated EEG analysis.

Real-time noise cancellation with deep learning

Biological measurements are often contaminated with large amounts of non-stationary noise which require effective noise reduction techniques. We present a new real-time deep learning algorithm which produces adaptively a signal opposing the noise so that destructive interference occurs. As a proof of concept, we demonstrate the algorithm's performance by reducing electromyogram noise in electroencephalograms with the usage of a custom, flexible, 3D-printed, compound electrode. With this setup, an average of 4dB and a maximum of 10dB improvement of the signal-to-noise ratio of the EEG was achieved by removing wide band muscle noise. This concept has the potential to not only adaptively improve the signal-to-noise ratio of EEG but can be applied to a wide range of biological, industrial and consumer applications such as industrial sensing or noise cancelling headphones.

Developing Disposable EEG Cap for Infant Recordings at the Neonatal Intensive Care Unit

Long-term EEG monitoring in neonatal intensive care units (NICU) is challenged with finding solutions for setting up and maintaining a sufficient recording quality with limited technical experience. The current study evaluates different solutions for the skin-electrode interface and develops a disposable EEG cap for newborn infants. Several alternative materials for the skin-electrode interface were compared to the conventional gel and paste: conductive textiles (textured and woven), conductive Velcro, sponge, super absorbent hydrogel (SAH), and hydro fiber sheets (HF). The comparisons included the assessment of dehydration and recordings of signal quality (skin interphase impedance and powerline (50 Hz) noise) for selected materials. The test recordings were performed using snap electrodes integrated into a forearm sleeve or a forehead band along with skin-electrode interfaces to mimic an EEG cap with the aim of long-term biosignal recording on unprepared skin. In the hydration test, conductive textiles and Velcro performed poorly. While the SAH and HF remained sufficiently hydrated for over 24 h in an incubator-mimicking environment, the sponge material was dehydrated during the first 12 h. Additionally, the SAH was found to have a fragile structure and was electrically prone to artifacts after 12 h. In the electrical impedance and recording comparisons of muscle activity, the results for thick-layer HF were comparable to the conventional gel on unprepared skin. Moreover, the mechanical instability measured by 1-2 Hz and 1-20 Hz normalized relative power spectrum density was comparable with clinical EEG recordings using subdermal electrodes. The results together suggest that thick-layer HF at the skin-electrode interface is an effective candidate for a preparation-free, long-term recording, with many advantages, such as long-lasting recording quality, easy use, and compatibility with sensitive infant skin contact.

EEG artifact removal using sub-space decomposition, nonlinear dynamics, stationary wavelet transform and machine learning algorithms

Blind source separation (BSS) methods have received a great deal of attention in electroencephalogram (EEG) artifact elimination as they are routine and standard signal processing tools to remove artifacts and reserve desired neural information. On the other hand, a classifier should follow BSS methods to automatically identify artifactual sources and remove them in the following steps. In addition, removing all detected artifactual components leads to loss of information since some desired information related to neural activity leaks to these sources. So, an approach should be employed to detect and suppress the artifacts and reserve neural activity. This study introduces a novel method based on EEG and Poincare planes in the phase space to detect artifactual components estimated by second-order blind identification (SOBI). Artifacts are detected using a mixture of well-known conventional classifiers and were removed employing stationary wavelet transform (SWT) to reserve neural information. The proposed method is a combination of signal processing techniques and machine learning algorithms, including multi-layer perceptron (MLP), K-nearest neighbor (KNN), naïve Bayes, and support vector machine (SVM) which have significant results while applying our proposed method to different scenarios. Simulated, semi-simulated, and real EEG signals are employed to evaluate the proposed method, and several evaluation criteria are calculated. We achieved acceptable results, for example, 98% average accuracy and 97% average sensitivity in artifactual EEG component detection or about 2% as mean square error in EEG reconstruction after artifact removal. Results showed that the proposed method is effective and can be used in future studies as we have considered different real-world scenarios to evaluate it.

Automated detection and removal of flat line segments and large amplitude fluctuations in neonatal electroencephalography

Background

Artefact removal in neonatal electroencephalography (EEG) by visual inspection generally depends on the expertise of the operator, is time consuming and is not a consistent pre-processing step to the pipeline for the automated EEG analysis. Therefore, there is the need for the automated detection and removal of artefacts in neonatal EEG, especially of distinct and predominant artefacts such as flat line segments (mainly caused by instrumental error where contact between electrodes and head box is lost) and large amplitude fluctuations (related to neonatal movements).

Method

A threshold-based algorithm for the automated detection and removal of flat line segments and large amplitude fluctuations in neonatal EEG of infants at term-equivalent age is developed. The algorithm applies thresholds to the absolute second difference, absolute amplitude, absolute first difference and the ratio between the frequency content above 50 Hz and the frequency content across all frequencies.

Results

The algorithm reaches a median accuracy of 0.91, a median hit rate of 0.91 and a median false discovery rate of 0.37. Also, a significant improvement (≈10%) in the performance of a four-stage sleep classifier is observed after artefact removal with the proposed algorithm as compared to before its application.

Significance

An automated artefact removal method contributes to the pipeline of automated EEG analysis. The proposed algorithm has shown to have good performance and to be effective in neonatal EEG applications.

Automated Detection and Removal of Cardiac and Pulse Interferences from Neonatal EEG Signals

Electrical cardiac and pulsatile interference is very difficult to remove from electroencephalographic (EEG) signals, especially if recorded in neonates, for which a small number of EEG channels is used. Several methods were proposed, including Blind Source Separation (BSS) methods that required the use of artificial cardiac-related signals to improve the separation of artefactual components. To optimize the separation of cardiac-related artefactual components, we propose a method based on Independent Component Analysis (ICA) that exploits specific features of the real electrocardiographic (ECG) signals that were simultaneously recorded with the neonatal EEG. A total of forty EEG segments from 19-channel neonatal EEG recordings with and without seizures were used to test and validate the performance of our method. We observed a significant reduction in the number of independent components (ICs) containing cardiac-related interferences, with a consequent improvement in the automated classification of the separated ICs. The comparison with the expert labeling of the ICs separately containing electrical cardiac and pulsatile interference led to an accuracy = 0.99, a false omission rate = 0.01 and a sensitivity = 0.93, outperforming existing methods. Furthermore, we verified that true brain activity was preserved in neonatal EEG signals reconstructed after the removal of artefactual ICs, demonstrating the effectiveness of our method and its safe applicability in a clinical context.