# Neonatal Seizure Detection Based on Spatiotemporal Feature Decoupling and Domain-Adversarial Learning

## TL;DR

This paper introduces a new AI model for detecting neonatal seizures that works well even with different patients, using advanced signal processing and domain-adversarial learning.

## Contribution

The novel contribution is the Domain-Adversarial Spatiotemporal Network (DA-STNet) that improves cross-subject seizure detection by decoupling features from subject-specific identity.

## Key findings

- DA-STNet achieves state-of-the-art performance with an AUC of 0.9998 and F1-score of 0.9952.
- Optimal generalization is attainable using only 80% of source data, showing high data efficiency.
- The model reduces reliance on extensive clinical annotations while maintaining high diagnostic precision.

## Abstract

Neonatal seizures are a critical early indicator of neurological injury, yet effective automated detection is challenged by significant inter-subject variability in electroencephalogram (EEG) signals. To address this generalization gap, this study introduces the Domain-Adversarial Spatiotemporal Network (DA-STNet) for robust cross-subject seizure detection. Utilizing Short-Time Fourier Transform (STFT) spectrograms, the architecture employs a hierarchical backbone comprising a Channel-Independent CNN (CI-CNN) for local texture extraction, a Spatial Bidirectional Long Short-Term Memory (Bi-LSTM) for modeling topological dependencies, and Attention Pooling to dynamically prioritize pathological channels while suppressing noise. Crucially, a Gradient Reversal Layer (GRL) is integrated to enforce domain-adversarial training, decoupling pathological features from subject-specific identity to ensure domain invariance. Under rigorous 5-fold cross-validation, the model achieves State-of-the-Art performance with an average Area Under the Curve (AUC) of 0.9998 and an F1-score of 0.9952. Data scaling experiments further reveal that optimal generalization is attainable using only 80% of source data, highlighting the model’s superior data efficiency. These findings demonstrate the proposed method’s capability to reduce reliance on extensive clinical annotations while maintaining high diagnostic precision in complex clinical scenarios.