FetalSleepNet: A Transfer Learning Framework with Spectral Equalisation Domain Adaptation for Fetal Sleep Stage Classification

2025-09-12

AI Summary

This study addresses the challenge of fetal sleep staging—which hinders early detection of pregnancy complications such as hypoxia and intrauterine growth restriction—by proposing the first lightweight deep learning framework specifically designed for fetal electroencephalography (EEG) sleep staging. Methodologically, it introduces a novel spectral-balanced domain adaptation strategy to mitigate spectral distribution shift during cross-domain transfer, enabling effective knowledge distillation from invasive intracranial EEG to clinical noninvasive signals. Validated on ovine fetal intracranial EEG data, the model achieves 86.6% accuracy and 62.5% macro-F1 under full fine-tuning, significantly outperforming baseline methods, while maintaining low parameter count and real-time inference capability. Key contributions include: (1) the first dedicated fetal EEG sleep staging architecture; (2) a new spectral-balanced domain adaptation paradigm; and (3) a clinically translatable label distillation pipeline bridging invasive and noninvasive modalities.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Introduction: This study presents FetalSleepNet, the first published deep learning approach to classifying sleep states from the ovine electroencephalogram (EEG). Fetal EEG is complex to acquire and difficult and laborious to interpret consistently. However, accurate sleep stage classification may aid in the early detection of abnormal brain maturation associated with pregnancy complications (e.g. hypoxia or intrauterine growth restriction). Methods: EEG electrodes were secured onto the ovine dura over the parietal cortices of 24 late gestation fetal sheep. A lightweight deep neural network originally developed for adult EEG sleep staging was trained on the ovine EEG using transfer learning from adult EEG. A spectral equalisation-based domain adaptation strategy was used to reduce cross-domain mismatch. Results: We demonstrated that while direct transfer performed poorly, full fine tuning combined with spectral equalisation achieved the best overall performance (accuracy: 86.6 percent, macro F1-score: 62.5), outperforming baseline models. Conclusions: To the best of our knowledge, FetalSleepNet is the first deep learning framework specifically developed for automated sleep staging from the fetal EEG. Beyond the laboratory, the EEG-based sleep stage classifier functions as a label engine, enabling large scale weak/semi supervised labeling and distillation to facilitate training on less invasive signals that can be acquired in the clinic, such as Doppler Ultrasound or electrocardiogram data. FetalSleepNet's lightweight design makes it well suited for deployment in low power, real time, and wearable fetal monitoring systems.

Problem

• Classifying fetal sleep stages from ovine EEG signals
• Reducing cross-domain mismatch using spectral equalisation
• Enabling automated sleep staging for fetal monitoring systems

Innovation

• Transfer learning from adult EEG data
• Spectral equalisation domain adaptation strategy
• Lightweight deep neural network architecture