Neonates spend most of their life sleeping. During sleep, their brain experiences fast changes in its functional organization. Microstate analysis permits to capture the rapid dynamical changes occurring in the functional organization of the brain by representing the changing spatio-temporal features of the electroencephalogram (EEG) as a sequence of short-lasting scalp topographies—the microstates. In this study, we modeled the ongoing neonatal EEG into sequences of a limited number of microstates and investigated whether the extracted microstate features are altered in REM and NREM sleep (usually known as active and quiet sleep states—AS and QS—in the newborn) and depend on the EEG frequency band. 19-channel EEG recordings from 60 full-term healthy infants were analyzed using a modified version of the k-means clustering algorithm. The results show that ~ 70% of the variance in the datasets can be described using 7 dominant microstate templates. The mean duration and mean occurrence of the dominant microstates were significantly different in the two sleep states. Microstate syntax analysis demonstrated that the microstate sequences characterizing AS and QS had specific non-casual structures that differed in the two sleep states. Microstate analysis of the neonatal EEG in specific frequency bands showed a clear dependence of the explained variance on frequency. Overall, our findings demonstrate that (1) the spatio-temporal dynamics of the neonatal EEG can be described by non-casual sequences of a limited number of microstate templates; (2) the brain dynamics described by these microstate templates depends on frequency; (3) the features of the microstate sequences can well differentiate the physiological conditions characterizing AS and QS.
Seizures are the most prevalent clinical indication of neurological disorders in neonates. In this study, a class-imbalance aware and explainable deep learning approach based on Convolutional Neural Networks (CNNs) and Graph Attention Networks (GATs) is proposed for the accurate automated detection of neonatal seizures. The proposed model integrates the temporal information of EEG signals with the spatial information on the EEG channels through the graph representation of the multi-channel EEG segments. One-dimensional CNNs are used to automatically develop a feature set that accurately represents the differences between seizure and nonseizure epochs in the time domain. By employing GAT, the attention mechanism is utilized to emphasize the critical channel pairs and information flow among brain regions. GAT coefficients were then used to empirically visualize the important regions during the seizure and nonseizure epochs, which can provide valuable insight into the location of seizures in the neonatal brain. Additionally, to tackle the severe class imbalance in the neonatal seizure dataset using under-sampling and focal loss techniques are used. Overall, the final Spatio-Temporal Graph Attention Network (ST-GAT) outperformed previous benchmarked methods with a mean AUC of 96.6% and Kappa of 0.88, demonstrating its high accuracy and potential for clinical applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.