Abstract

Medical foundation models learn latent representations of clinically meaningful phenotypes, yet their ability to support controllable image generation remains largely unexplored. We evaluate four retinalfoundationmodelswithintherepresentationtokenizerframework 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 theiroriginatingfoundationmodels,consistentlyoutperformingconventionallatentdiffusiononmultipledownstreampredictiontasks.However, thesegainslargelydisappearwhenevaluatedusingclassifierstrainedon realimages,revealingapreviouslyuncharacterisedsynthetic-to-realrepresentation gap. These findings demonstrate that foundation-model latentspacesprovideapowerfulsubstrateforcontrollableretinalsynthesis whilehighlightingtheneedtobetteralignsyntheticrepresentationswith real-image distributions.

Links to Paper and Supplementary Materials

Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SASHIMI_018.pdf

SharedIt Link: Not yet available

SpringerLink (DOI): Not yet available

Supplementary Material: Not Submitted

Link to Open Review

Open Review Page: https://openreview.net/forum?id=0Wt6mwwRlH

BibTex

@InProceedings{WakZuz_Evaluation_MICCAISAT2026,
        author = { Wakefield-Skórniewska, Zuzanna A. AND Papież, Bartłomiej W.},
        title = { { Evaluation of Clinically Steerable Retinal Image Generation from Foundation Model Latent Spaces } },
        booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
        year = {2026},
        publisher = {Springer Nature Switzerland},
        volume = {LNCS 17258},
        month = {pending},
        page = {pending}
}


back to top