Metraipolis › archive › dc_899e42f64d6f

Decoder Design Matters for ECG Delineation — arXiv:2609.16489

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16489
License (as archived)
CC0-1.0
Archived
2026-10-15T18:34:56.658Z
SHA-256 of the archived text
e6aa22e24990fa70bffec66eed5fe00a4954bacfe00acbf2fa32dc839885d5f4
Stable URL of this page
https://metraipolis.com/documento/dc_899e42f64d6f

How to cite

Decoder Design Matters for ECG Delineation — arXiv:2609.16489 — arXiv (en), https://arxiv.org/abs/2609.16489 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_899e42f64d6f (Metraipolis archive dc_899e42f64d6f, sha256 e6aa22e24990fa70bffec66eed5fe00a4954bacfe00acbf2fa32dc839885d5f4)
BibTeX
@misc{dc899e42f64d6f,
  title = {Decoder Design Matters for ECG Delineation — arXiv:2609.16489},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16489},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_899e42f64d6f; sha256 e6aa22e24990fa70bffec66eed5fe00a4954bacfe00acbf2fa32dc839885d5f4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16489. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this http URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.16489 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T18:03:09.648Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).