# Decoder Design Matters for ECG Delineation

arXiv: https://arxiv.org/abs/2609.16489 · HTML: https://mlsanity.com/paper/2609.16489/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks](https://mlsanity.com/paper/1707.01836/) (2017)
- [ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis](https://mlsanity.com/paper/2408.08849/) (2024)
- [DENS-ECG: A Deep Learning Approach for ECG Signal Delineation](https://mlsanity.com/paper/2005.08689/) (2020)
- [ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation](https://mlsanity.com/paper/2603.14326/) (2026)
- [SemiSegECG: A Multi-Dataset Benchmark for Semi-Supervised Semantic Segmentation in ECG Delineation](https://mlsanity.com/paper/2507.18323/) (2025)

## Abstract (arXiv)

Electrocardiogram (ECG) delineation identifies the boundaries of P waves, QRS complexes, and T waves, providing structural annotations that can guide AI models in learning to interpret ECGs. However, training accurate delineation models requires manual annotations that are scarce and time-consuming to obtain. Recent work addresses this limitation through semi-supervised learning (SSL), but the design of the architecture, particularly the decoder, has received less attention. To this end, we propose R-U-Net, an ECG delineation model that pairs a ResNet-18 encoder with a U-Net decoder. On SemiSegECG, R-U-Net outperforms the strongest evaluated ResNet-18 + fully convolutional network (FCN) head baseline in each of the 16 in-domain settings by 3.3-13.0 mIoU and achieves 82.6 mIoU in the cross-domain setting, an improvement of 8.1 mIoU. Controlled ablations show that decoder design contributes more to performance gains than the evaluated SSL methods, motivating further exploration of architectures for ECG delineation. All code is open-source at github.com/ELM-Research/ECG-Delineation.