Liang Yanting, Liu Jingyuan, Zhang Xinzhou
Department of Nephrology, Shenzhen People's Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, China.
Children's Heart Center, The Second Affiliated Hospital and Yuying Children's Hospital, Zhejiang Provincial Clinical Research Center for Pediatric Disease, Wenzhou Medical University, Zhejiang, China.
Front Neurol. 2025 Jul 29;16:1631064. doi: 10.3389/fneur.2025.1631064. eCollection 2025.
Epilepsy is a neurological disorder characterized by sudden, abnormal discharges of neuronal activity in the brain. Electroencephalogram (EEG) analysis is the primary technique for detecting epileptic seizures, and accurate seizure detection is essential for clinical diagnosis, therapeutic intervention, and treatment planning. However, traditional methods rely heavily on manual feature extraction, and current deep learning-based approaches still face challenges in frequency adaptability, multi-scale feature integration, and phase alignment.
To address these limitations, we propose an Adaptive Multi-Scale Phase-Aware Fusion Network (AMS-PAFN). The framework integrates three novel components: (1) a Dynamic Frequency Selection (DFS) module employing Gumbel-SoftMax for adaptive spectral filtering to enhance seizure-related frequency bands; (2) a Multi-Scale Feature Extraction (MCFE) module using hierarchical downsampling and temperature-controlled multi-head attention to capture both macro-rhythmic and micro-transient EEG patterns; and (3) a Multi-Scale Phase-Aware Fusion (MCPA) module that aligns temporal features across scales through phase-sensitive weighting.
The AMS-PAFN was evaluated on the CHB-MIT dataset and achieved state-of-the-art performance, with 98.97% accuracy, 99.53% sensitivity, and 95.21% specificity (Subset 1). Compared to STFTormer, it showed a 1.58% absolute improvement in accuracy (97.39% → 98.97%) and a 2.66% increase in specificity (92.55% → 95.21%). Ablation studies validated the effectiveness of each module, with DFS improving specificity by 6.87% and MCPA enhancing cross-scale synchronization by 5.54%.
The AMS-PAFN demonstrates strong potential for clinical seizure recognition through its adaptability to spectral variability and spatiotemporal dynamics, making it well-suited for integration into real-time epilepsy monitoring and alert systems.
癫痫是一种神经系统疾病，其特征是大脑中神经元活动突然出现异常放电。脑电图（EEG）分析是检测癫痫发作的主要技术，准确的发作检测对于临床诊断、治疗干预和治疗计划至关重要。然而，传统方法严重依赖人工特征提取，当前基于深度学习的方法在频率适应性、多尺度特征整合和相位对齐方面仍面临挑战。
为解决这些局限性，我们提出了一种自适应多尺度相位感知融合网络（AMS-PAFN）。该框架集成了三个新颖的组件：（1）一个动态频率选择（DFS）模块，采用Gumbel-SoftMax进行自适应频谱滤波，以增强与癫痫发作相关的频带；（2）一个多尺度特征提取（MCFE）模块，使用分层下采样和温度控制的多头注意力来捕捉宏观节律和微观瞬态脑电图模式；（3）一个多尺度相位感知融合（MCPA）模块，通过相位敏感加权在不同尺度上对齐时间特征。
AMS-PAFN在CHB-MIT数据集上进行了评估，取得了领先的性能，准确率为98.97%，灵敏度为99.53%，特异性为95.21%（子集1）。与STFTormer相比，其准确率有1.58%的绝对提升（从97.39%提高到98.97%），特异性提高了2.66%（从92.55%提高到95.21%）。消融研究验证了每个模块的有效性，DFS使特异性提高了6.87%，MCPA使跨尺度同步提高了5.54%。
AMS-PAFN通过其对频谱变异性和时空动态的适应性，在临床癫痫发作识别方面显示出强大的潜力，非常适合集成到实时癫痫监测和警报系统中。
