S2M2ECG: Spatio-temporal bi-directional State Space Model Enabled Multi-branch Mamba for ECG
Preprint
Abstract
As one of the most effective methods for cardiovascular disease (CVD) diagnosis, multi-lead Electrocardiogram (ECG) signals present a characteristic multi-sensor information fusion challenge that has been continuously researched in deep learning domains. Despite the numerous algorithms proposed with different DL architectures, maintaining a balance among performance, computational complexity, and multi-source ECG feature fusion remains challenging. Recently, state space models (SSMs), particularly Mamba, have demonstrated remarkable effectiveness across various fields. Their inherent design for high-efficiency computation and linear complexity makes them particularly suitable for low-dimensional data like ECGs. This work proposes S2M2ECG, an SSM architecture featuring three-level fusion mechanisms: (1) Spatio-temporal bi-directional SSMs with segment tokenization for low-level signal fusion, (2) Intra-lead temporal information fusion with bi-directional scanning to enhance recognition accuracy in both forward and backward directions, (3) Cross-lead feature interaction modules for spatial information fusion. To fully leverage the ECG-specific multi-lead mechanisms inherent in ECG signals, a multi-branch design and lead fusion modules are incorporated, enabling individual analysis of each lead while ensuring seamless integration with others. Experimental results reveal that S2M2ECG achieves superior performance in the rhythmic, morphological, and clinical scenarios. Moreover, its lightweight architecture ensures it has nearly the fewest parameters among existing models, making it highly suitable for efficient inference and convenient deployment. Collectively, S2M2ECG offers a promising alternative that strikes an excellent balance among performance, computational complexity, and ECG-specific characteristics, paving the way for high-performance, lightweight computations in CVD diagnosis.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- ST-MambaSync: Complement the power of Mamba and Transformer fusion for less computational cost in spatial–temporal traffic forecastingInformation Fusion, 2024
- MGCN: Mamba-integrated spatiotemporal graph convolutional network for long-term traffic forecastingKnowledge-Based Systems, 2024
- Pan-Mamba: Effective pan-sharpening with state space modelInformation Fusion, 2024
- Polyp-Mamba: A Hybrid Multi-Frequency Perception Gated Selection Network for polyp segmentationInformation Fusion, 2024
- Semi-Mamba-UNet: Pixel-level contrastive and cross-supervised visual Mamba-based UNet for semi-supervised medical image segmentationKnowledge-Based Systems, 2024
- Honest-GE: 2-step heuristic optimization and node-level embedding empower spatial-temporal graph model for ECGInformation Sciences, 2024
- Deep neural networks generalization and fine-tuning for 12-lead ECG classificationBiomedical Signal Processing and Control, 2024
- MSGformer: A multi-scale grid transformer network for 12-lead ECG arrhythmia detectionBiomedical Signal Processing and Control, 2023
- Multi-class Arrhythmia detection from 12-lead varied-length ECG using Attention-based Time-Incremental Convolutional Neural NetworkInformation Fusion, 2020
- ECG beat classification using PCA, LDA, ICA and Discrete Wavelet TransformBiomedical Signal Processing and Control, 2013