Adaptive multi-scale phase-aware fusion network for EEG seizure recognition

IntroductionEpilepsy 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, therapeut...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanting Liang, Jingyuan Liu, Xinzhou Zhang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Neurology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2025.1631064/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245718007513088
author Yanting Liang
Jingyuan Liu
Xinzhou Zhang
author_facet Yanting Liang
Jingyuan Liu
Xinzhou Zhang
author_sort Yanting Liang
collection DOAJ
description IntroductionEpilepsy 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.MethodsTo 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.ResultsThe 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%.DiscussionThe 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.
format Article
id doaj-art-0c1554c3e9d945dd8f9ab1205b283f6c
institution Kabale University
issn 1664-2295
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurology
spelling doaj-art-0c1554c3e9d945dd8f9ab1205b283f6c2025-08-20T03:58:44ZengFrontiers Media S.A.Frontiers in Neurology1664-22952025-07-011610.3389/fneur.2025.16310641631064Adaptive multi-scale phase-aware fusion network for EEG seizure recognitionYanting Liang0Jingyuan Liu1Xinzhou Zhang2Department of Nephrology, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, ChinaChildren’s Heart Center, The Second Affiliated Hospital and Yuying Children’s Hospital, Zhejiang Provincial Clinical Research Center for Pediatric Disease, Wenzhou Medical University, Zhejiang, ChinaDepartment of Nephrology, Shenzhen People’s Hospital (The Second Clinical Medical College, Jinan University, The First Affiliated Hospital, Southern University of Science and Technology), Shenzhen, ChinaIntroductionEpilepsy 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.MethodsTo 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.ResultsThe 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%.DiscussionThe 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.https://www.frontiersin.org/articles/10.3389/fneur.2025.1631064/fullEEG seizure recognitionadaptive multi-scale networkdynamic frequency selectionphase-aware fusiondeep learningGumbel-SoftMax
spellingShingle Yanting Liang
Jingyuan Liu
Xinzhou Zhang
Adaptive multi-scale phase-aware fusion network for EEG seizure recognition
Frontiers in Neurology
EEG seizure recognition
adaptive multi-scale network
dynamic frequency selection
phase-aware fusion
deep learning
Gumbel-SoftMax
title Adaptive multi-scale phase-aware fusion network for EEG seizure recognition
title_full Adaptive multi-scale phase-aware fusion network for EEG seizure recognition
title_fullStr Adaptive multi-scale phase-aware fusion network for EEG seizure recognition
title_full_unstemmed Adaptive multi-scale phase-aware fusion network for EEG seizure recognition
title_short Adaptive multi-scale phase-aware fusion network for EEG seizure recognition
title_sort adaptive multi scale phase aware fusion network for eeg seizure recognition
topic EEG seizure recognition
adaptive multi-scale network
dynamic frequency selection
phase-aware fusion
deep learning
Gumbel-SoftMax
url https://www.frontiersin.org/articles/10.3389/fneur.2025.1631064/full
work_keys_str_mv AT yantingliang adaptivemultiscalephaseawarefusionnetworkforeegseizurerecognition
AT jingyuanliu adaptivemultiscalephaseawarefusionnetworkforeegseizurerecognition
AT xinzhouzhang adaptivemultiscalephaseawarefusionnetworkforeegseizurerecognition