# DR-net-Mamba: Selective State-Space Modeling for Long-Range ECG Time-Series Denoising

arXiv: https://arxiv.org/abs/2609.35634 · HTML: https://mlsanity.com/paper/2609.35634/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Physiological signal modeling, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 19 of its 67 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- State-space sequence models (S4, Mamba) / [Physiological signal modeling](https://mlsanity.com/ssm/physiological-signal-modeling/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [InceptionTime: Finding AlexNet for Time Series Classification](https://mlsanity.com/paper/1909.04939/) (2019)
- [Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline](https://mlsanity.com/paper/1611.06455/) (2016)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [The Hidden Attention of Mamba Models](https://mlsanity.com/paper/2403.01590/) (2024)
- [Synthesis of Realistic ECG using Generative Adversarial Networks](https://mlsanity.com/paper/1909.09150/) (2019)
- [DeScoD-ECG: Deep Score-Based Diffusion Model for ECG Baseline Wander and Noise Removal](https://mlsanity.com/paper/2208.00542/) (2022)
- [Introducing Hann windows for reducing edge-effects in patch-based image segmentation](https://mlsanity.com/paper/1910.07831/) (2019)
- [Deep Recurrent Neural Networks for ECG Signal Denoising](https://mlsanity.com/paper/1807.11551/) (2018)
- [DeepFilter: an ECG baseline wander removal filter using deep learning techniques](https://mlsanity.com/paper/2101.03423/) (2021)
- [Blind ECG Restoration by Operational Cycle-GANs](https://mlsanity.com/paper/2202.00589/) (2022)
- [MECG-E: Mamba-based ECG Enhancer for Baseline Wander Removal](https://mlsanity.com/paper/2409.18828/) (2024)
- [Mamba Adaptive Anomaly Transformer with association discrepancy for time series](https://mlsanity.com/paper/2502.07858/) (2025)
- [ECG Signal Denoising Using Multi-scale Patch Embedding and Transformers](https://mlsanity.com/paper/2407.11065/) (2024)
- [ECGDeDRDNet: A deep learning-based method for Electrocardiogram noise removal using a double recurrent dense network](https://mlsanity.com/paper/2505.05477/) (2025)

## Abstract (arXiv)

Electrocardiogram (ECG) recordings are corrupted by non-stationary noise sources that degrade diagnostic reliability, particularly in ambulatory and long-duration recordings. Deep learning denoisers exist, but convolutional architectures are limited by their receptive field, transformer-based models scale quadratically with sequence length, and diffusion-based approaches incur prohibitive inference cost. We propose a Mamba-augmented model that inserts selective state-space blocks at the convolutional bottleneck, combining local feature extraction with long-range temporal modeling at linear complexity. We comprehensively evaluate the proposed model with respect to reconstruction fidelity, noise robustness, recording-length scaling, and downstream diagnostic classification across over 40 pathology classes. On synthetic and real datasets, our model achieves the highest SNR and lowest RMSE, with the Mamba advantage increasing with sequence length and in low-SNR regimes. On classification with two independent classifiers, the proposed Mamba-based models achieve the best macro AUROC among all denoisers and improve over their convolutional base models. Calibration is more nuanced and classifier-dependent: denoising improves Binary Cross-Entropy and Brier score on Inception1D but often fails to beat the noisy input on ResNet1D-Wang, and the lead-specific Mamba variant is the only denoiser to improve both calibration metrics over the noisy baseline on both classifiers. Per-class analysis reveals a morphology-dependent benefit: Mamba substantially improves ST/T-change diagnoses, which depend on broad, context-sensitive waveforms.