Goal: To develop a high-performance and robust solution for neonatal sleep staging that incorporates spatial topological information and functional connectivity of the brain, which are often overlooked in existing approaches. Methods: We propose MVBNSleepNet, a multi-view brain network-based convolutional neural network. The framework integrates a multi-view brain network (MVBN) to characterize brain functional connectivity from linear temporal correlation, information-theoretic, and phase-dynamics perspectives, providing comprehensive spatial topological information. A masking mechanism is employed to enhance model robustness by simulating random dropout or low-quality signal conditions. Additionally, an attention mechanism focuses on key regions of the brain network and reveals structural brain connectivity during sleep, while a CNN module extracts spatial features from brain networks and classifies them into specific sleep stages. The model was validated on a clinical dataset of 64 neonatal EEG recordings using a leave-one-subject-out validation strategy. Results: MVBNSleepNet achieved an accuracy of 83.9% in the two-stage sleep task (sleep and wakefulness) and 76.4% in the three-stage task (active sleep, quiet sleep, and wakefulness), outperforming state-of-the-art methods. Conclusions: The proposed MVBNSleepNet provides a robust and accurate solution for neonatal sleep staging and offers valuable insights into the functional connectivity of the early neural system.
4 February 2026 in Biomedical Signal Processing and Control
Background: Accurate assessment of neonatal sleep is critical for monitoring brain development and identifying potential neurological disorders, yet manual scoring of multi-channel EEG recordings is labor-intensive and prone to variability. Methods: To address this, we propose a lightweight temporal–spatial feature fusion network for automatic neonatal sleep staging. The model employs a dual-branch architecture to separately capture temporal dependencies and spatial correlations in EEG signals, which are then integrated through feature concatenation and a compact classifier to obtain comprehensive feature representations while maintaining low computational complexity. Results: The framework was evaluated on a clinical neonatal dataset (CHFD) for tasks including sleep–wake classification, quiet sleep detection, and three-stage sleep staging, achieving superior performance compared with several state-of-the-art methods. Additional evaluation on the MASS-S3 adult dataset demonstrate that the model retains competitive accuracy and F1-score, indicating strong generalization across populations. Conclusions: These results suggest that jointly modeling temporal and spatial features enables robust and efficient automatic sleep staging. The proposed approach offers a practical solution for clinical applications and edge deployment, providing reliable, multi-dimensional assessment of neonatal brain activity and laying the groundwork for future studies integrating larger datasets or multimodal physiological signals.
Currently, deep learning-based methods for automatic sleep staging are thriving and gaining significant traction due to the advanced pattern recognition and feature extraction inherent as compared to machine learning-based methods. However, most of the existing approaches only consider the informative features of raw signals, while neglecting the connectivity characteristics among multi-channel electroencephalogram (EEG) data. In this study, a hybrid framework for neonatal sleep staging by combining Convolutional Neural Network (CNN) and Graph Neural Network (GNN) is proposed. It not only considers brain connections among multi-channel EEG through various perspectives (such as linear temporal correlation, information-theoretic, and phase-dynamics information, etc.) but also involves the high-order structural features that originate from graphs. The method potentially enhances the feature representation, thus significantly improving neonatal sleep staging performance. The proposed method is validated on a clinical neonatal sleep dataset, demonstrating superior performance, especially with CNN+Graph Attention Network (GAT) achieving an accuracy of 74.8% and an f1-score of 0.747. The results highlight the potential of leveraging both CNN for feature learning on connectivity matrices and GNN for attention between nodes to enhance neonatal sleep staging.