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...
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |