MSCA-Mamba: A Compact Multi-Scale Mamba Network for Multi-Label ECG Classification.
- 1Department of Computer Engineering, Malatya Turgut Ozal University, 44210 Malatya, Türkiye.
Abstract
Objective: Multi-label electrocardiogram (ECG) classification requires modeling morphological patterns across different temporal scales and their sequential relationships while maintaining limited model complexity. This study proposes Multi-Scale Channel-Attentive Mamba (MSCA-Mamba), a compact architecture integrating multi-scale feature extraction, branch-wise recalibration, and state-space sequence modeling. Methods: MSCA-Mamba combines three parallel dilated Conv1D branches, branch-wise Squeeze-and-Excitation modules, and a unidirectional Mamba block. The model was evaluated on the PTB-XL diagnostic superclass task using the official patient-wise split and five random seeds. Component ablations, parameter-matched Conv1D, GRU, LSTM, and Transformer controls, unidirectional-bidirectional comparisons, and GPU benchmarks were performed. Results: MSCA-Mamba achieved a Macro ROC-AUC of 0.8998 ± 0.0022, Macro PR-AUC of 0.7651 ± 0.0036, and Macro F1-score of 0.7038 ± 0.0045 with 121,149 parameters. Multi-scale feature extraction provided the clearest benefit, particularly for macro-averaged metrics. Parameter-matched alternatives showed broadly comparable performance. Bidirectional Mamba achieved a modestly higher Macro ROC-AUC but increased the parameter count to 214,077 and inference latency. Conclusions: MSCA-Mamba provides a compact framework for multi-label ECG classification on PTB-XL. Its primary strength lies in compact architectural integration rather than universal superiority of individual components.
Related
- Boundary-aware multi-scale residual learning with hybrid radiomic–deep fusion for lung tumor segmentation and classification
- Automatic grading of HER2 immunohistochemical whole-slide images based on a multi-scale hierarchical graph neural network
- Comparative analysis of CNN, Transformer, and Mamba-based models for automated eye disease classification from fundus images
- Multi-scale feature fusion for image-level kidney stone classification on NCCT images: a cross-center generalization evaluation.
- Triple-path bidirectional Mamba enables linear-complexity temporal hyperspectral plant stress classification
BibTeX
@article{cetintas2026mscamamba,
title = {{MSCA-Mamba: A Compact Multi-Scale Mamba Network for Multi-Label ECG Classification.}},
author = {Dilber Cetintas},
journal = {Diagnostics (Basel, Switzerland)},
year = {2026},
month = sep,
doi = {10.3390/diagnostics16193135},
url = {https://europepmc.org/article/MED/42882289},
note = {CC BY},
}
RIS
TY - JOUR
TI - MSCA-Mamba: A Compact Multi-Scale Mamba Network for Multi-Label ECG Classification.
AU - Dilber Cetintas
PY - 2026
DA - 2026/09/26
JO - Diagnostics (Basel, Switzerland)
DO - 10.3390/diagnostics16193135
UR - https://europepmc.org/article/MED/42882289
AB - Objective: Multi-label electrocardiogram (ECG) classification requires modeling morphological patterns across different temporal scales and their sequential relationships while maintaining limited model complexity. This study proposes Multi-Scale Channel-Attentive Mamba (MSCA-Mamba), a compact architecture integrating multi-scale feature extraction, branch-wise recalibration, and state-space sequence modeling. Methods: MSCA-Mamba combines three parallel dilated Conv1D branches, branch-wise Squeeze-and-Excitation modules, and a unidirectional Mamba block. The model was evaluated on the PTB-XL diagnostic superclass task using the official patient-wise split and five random seeds. Component ablations, parameter-matched Conv1D, GRU, LSTM, and Transformer controls, unidirectional-bidirectional comparisons, and GPU benchmarks were performed. Results: MSCA-Mamba achieved a Macro ROC-AUC of 0.8998 ± 0.0022, Macro PR-AUC of 0.7651 ± 0.0036, and Macro F1-score of 0.7038 ± 0.0045 with 121,149 parameters. Multi-scale feature extraction provided the clearest benefit, particularly for macro-averaged metrics. Parameter-matched alternatives showed broadly comparable performance. Bidirectional Mamba achieved a modestly higher Macro ROC-AUC but increased the parameter count to 214,077 and inference latency. Conclusions: MSCA-Mamba provides a compact framework for multi-label ECG classification on PTB-XL. Its primary strength lies in compact architectural integration rather than universal superiority of individual components.
SN - 2075-4418
ER -