Metraipolis › archive › dc_cf729509eca6
Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces — arXiv:2608.13455
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13455
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:55:55.978Z
- SHA-256 of the archived text
927b571d431849304d187ffd9ba136601b0446ac038c9db16478ea9b90d00013- Stable URL of this page
https://metraipolis.com/documento/dc_cf729509eca6
How to cite
Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces — arXiv:2608.13455 — arXiv (en), https://arxiv.org/abs/2608.13455 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf729509eca6 (Metraipolis archive dc_cf729509eca6, sha256 927b571d431849304d187ffd9ba136601b0446ac038c9db16478ea9b90d00013)
BibTeX
@misc{dccf729509eca6,
title = {Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces — arXiv:2608.13455},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13455},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf729509eca6; sha256 927b571d431849304d187ffd9ba136601b0446ac038c9db16478ea9b90d00013},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13455. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Medical foundation models learn latent representations of clinically meaningful phenotypes, yet their ability to support controllable image generation remains largely unexplored. We evaluate four retinal foundation models within the representation tokenizer framework and examine whether demographic and clinical information encoded in latent representations from foundation models is preserved during synthetic image generation. We show that generated representations and images faithfully inherit phenotype information when evaluated within their originating foundation models, consistently outperforming conventional latent diffusion on multiple downstream prediction tasks. However, these gains largely disappear when evaluated using classifiers trained on real images, revealing a previously uncharacterised synthetic-to-real representation gap. These findings demonstrate that foundation-model latent spaces provide a powerful substrate for controllable retinal synthesis while highlighting the need to better align synthetic representations with real-image distributions. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.13455 — 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 2026-10-19T04:46:30.247Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).