IESS-FusionNet: Physiologically Inspired EEG-EMG Fusion with Linear Recurrent Attention for Infantile Epileptic Spasms Syndrome Detection
Open Access
- 31 December 2025
- journal article
- research article
- Published by MDPI AG in Bioengineering
- Vol. 13 (1) , 57
Abstract
Infantile Epileptic Spasms Syndrome (IESS) is a devastating epileptic encephalopathy of infancy that carries a high risk of lifelong neurodevelopmental disability. Timely diagnosis is critical, as every week of delay in effective treatment is associated with worse cognitive outcomes. Although synchronized electroencephalogram (EEG) and surface electromyography (EMG) recordings capture both the electrophysiological and motor signatures of spasms, accurate automated detection remains challenging due to the non-stationary nature of the signals and the absence of physiologically plausible inter-modal fusion in current deep learning approaches. We introduce IESS-FusionNet, an end-to-end dual-stream framework specifically designed for accurate, real-time IESS detection from simultaneous EEG and EMG. Each modality is processed by a dedicated Unimodal Encoder that hierarchically integrates Continuous Wavelet Transform, Spatio-Temporal Convolution, and Bidirectional Mamba to efficiently extract frequency-specific, spatially structured, local and long-range temporal features within a compact module. A novel Cross Time-Mixing module, built upon the linear recurrent attention of the Receptance Weighted Key Value (RWKV) architecture, subsequently performs efficient, time-decaying, bidirectional cross-modal integration that explicitly respects the causal and physiological properties of cortico-muscular coupling during spasms. Evaluated on an in-house clinical dataset of synchronized EEG-EMG recordings from infants with confirmed IESS, IESS-FusionNet achieves 89.5% accuracy, 90.7% specificity, and 88.3% sensitivity, significantly outperforming recent unimodal and multimodal baselines. Comprehensive ablation studies validate the contribution of each component, while the proposed cross-modal fusion requires approximately 60% fewer parameters than equivalent quadratic cross-attention mechanisms, making it suitable for real-time clinical deployment. IESS-FusionNet delivers an accurate, computationally efficient solution with physiologically inspired cross-modal fusion for the automated detection of infantile epileptic spasms, offering promise for future clinical applications in reducing diagnostic delay.Keywords
Funding Information
- National Natural Science Foundation of China (62502320)
- Natural Science Foundation of Guangdong Province (2025A1515010184)
- Science, Technology and Innovation Commission of Shenzhen Municipality (JCYJ20240813141424032)
- Foundation for Young Innovative Talents in Ordinary Universities of Guangdong (2024KQNCX042)
- Science and Technology Planning Project of Shenzhen (JCYJ20230807093819039)
- Science and Technology Planning Project of Shenzhen (JCYJ20230807093815032)
- Shenzhen Children’s Hospital (ynkt2021-zz33)
- Shenzhen Children’s Hospital (LCYJ2022093)
- Shenzhen Children’s Hospital (LCYJ2022075)
This publication has 31 references indexed in Scilit:
- Emotion recognition using cross-modal attention from EEG and facial expressionKnowledge-Based Systems, 2024
- Cosine convolutional neural network and its application for seizure detectionNeural Networks, 2024
- Scalp EEG functional connection and brain network in infants with West syndromeNeural Networks, 2022
- An EEG based real-time epilepsy seizure detection approach using discrete wavelet transform and machine learning methodsBiomedical Signal Processing and Control, 2022
- Construction and analysis of cortical–muscular functional network based on EEG-EMG coherence using wavelet coherenceNeurocomputing, 2021
- Recognition of Infantile Spasms Is Often Delayed: The ASSIST StudyThe Journal of Pediatrics, 2017
- Infantile spasms syndrome, West syndrome and related phenotypes: What we know in 2013Brain and Development, 2014
- sEMG-based continuous estimation of joint angles of human legs by using BP neural networkNeurocomputing, 2012
- Favourable prognostic factors with infantile spasmsEuropean Journal of Paediatric Neurology, 2010
- Sleep spindles and spike–wave discharges in EEG: Their generic features, similarities and distinctions disclosed with Fourier transform and continuous wavelet analysisJournal of Neuroscience Methods, 2009