Metraipolis › archive › dc_761cde09fa5b

Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction — arXiv:2609.02969

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02969
License (as archived)
CC0-1.0
Archived
2026-10-17T02:08:31.653Z
SHA-256 of the archived text
73ca08aa346733a0191e12d3d39d711782b83707058f5f9176e8959432a291a3
Stable URL of this page
https://metraipolis.com/documento/dc_761cde09fa5b

How to cite

Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction — arXiv:2609.02969 — arXiv (en), https://arxiv.org/abs/2609.02969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_761cde09fa5b (Metraipolis archive dc_761cde09fa5b, sha256 73ca08aa346733a0191e12d3d39d711782b83707058f5f9176e8959432a291a3)
BibTeX
@misc{dc761cde09fa5b,
  title = {Learning from Scarce Labels: Multi-View Echocardiography for Ejection Fraction Prediction — arXiv:2609.02969},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02969},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_761cde09fa5b; sha256 73ca08aa346733a0191e12d3d39d711782b83707058f5f9176e8959432a291a3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present, to the best of our knowledge, the first publicly available resource for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography. Because no PLAX-EF datasets previously existed, our work focuses on an innovative data generation strategy to overcome this scarcity. By leveraging a time-based correlation between clinical notes and echocardiographic videos, combined with fine-tuning view classifiers and proxy labeling, we created a labeled dataset of over 25,000 PLAX videos. This enables us to train the first reproducible PLAX EF model, achieving a mean absolute error (MAE) of 6.86%. Given that apical four-chamber (A4C) methods, the clinical standard, report MAE values of 6%-7%, our results demonstrate that EF estimation from PLAX views is both feasible and clinically relevant. This surpasses the performance of existing methods and provides a clinically relevant solution for situations where apical views may not be feasible. Going further, we demonstrate that combining PLAX and A4C predictions via simple unweighted late fusion improves both single-view baselines to a 6.37% MAE, underscoring the value of multi-view integration. To promote continued research, we release the dataset labels, trained models, and runnable demos on GitHub, Hugging Face, and Google Colab: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.02969 — 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 2026-10-17T01:47:25.594Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).