Metraipolis › archive › dc_ea42a79d750b

Label-Preserving Fourier Domain Adaptation with Generative-AI and Real Style Donors for 3D Mitral Valve Segmentation — arXiv:2611.05106

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05106
License (as archived)
CC0-1.0
Archived
2026-11-04T19:05:05.175Z
SHA-256 of the archived text
083c27208807bd44e6306c2d5d645ff5b24ca97e364731443ab8501cd15c507b
Stable URL of this page
https://metraipolis.com/documento/dc_ea42a79d750b

How to cite

Label-Preserving Fourier Domain Adaptation with Generative-AI and Real Style Donors for 3D Mitral Valve Segmentation — arXiv:2611.05106 — arXiv (en), https://arxiv.org/abs/2611.05106 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ea42a79d750b (Metraipolis archive dc_ea42a79d750b, sha256 083c27208807bd44e6306c2d5d645ff5b24ca97e364731443ab8501cd15c507b)
BibTeX
@misc{dcea42a79d750b,
  title = {Label-Preserving Fourier Domain Adaptation with Generative-AI and Real Style Donors for 3D Mitral Valve Segmentation — arXiv:2611.05106},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05106},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ea42a79d750b; sha256 083c27208807bd44e6306c2d5d645ff5b24ca97e364731443ab8501cd15c507b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05106. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate segmentation of the mitral valve from three-dimensional transesophageal echocardiography (3D TEE) is severely restricted by the scarcity of publicly available expert- annotated volumetric datasets. To address this critical limitation, we investigated Fourier Domain Adaptation (FDA), utilizing general-purpose generative-AI images (from platforms like Chat- GPT, Google Gemini, and Microsoft MAI) as annotation-free style donors for 3D mitral valve segmentation. We employed a DeepMitral residual U-Net model on the public MVSeg2023 dataset, comparing six conditions over three runs: real-only training, traditional augmentation, FDA with each generative source, and a non-AI FDA control using real-image style donors, plus an optimization-matched real-only control and a \b{eta} sensitivity analysis. Case-level paired testing showed that FDA with these generative sources led to significant reductions in boundary- and surface-related errors across all three donor conditions relative to the primary real-only baseline. However, the impact on the core segmentation metric, Generalized Dice Score (GDS), proved generator-dependent. ChatGPT-FDA showed a significant GDS advantage over the optimization-matched control but not over the primary baseline, and Gemini-FDA showed no significant GDS difference. Notably, only MAI-FDA provided a statistically robust and significant increase in GDS compared to the primary baseline. The \b{eta} sensitivity was not robust across training runs. These findings confirm that FDA remains an important augmentation mechanism. While generative-AI images offer a practical means of acquiring style diversity without new annotations, the non-AI control performed comparably to ChatGPT-FDA, so we do not conclude that this approach is superior to training with real-image donors.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.05106 — 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 2026-11-04T18:39:37.607Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).