Abstract
Computational pathology has made significant progress in recent years, fueling advances in both fundamental disease understanding and clinically ready tools. This evolution is driven by the availability of large amounts of digitized slides and specialized deep learning methodsandmodels.Multipleself-supervisedfoundationfeatureextractors have been developed, enabling many downstream predictive applications. In contrast, generative foundation models designed specifically for histopathology remain scarce. Such models could address tasks that arebeyondthecapabilitiesoffeatureextractors,suchasvirtualstaining. Inthispaper,weintroduceCytoSyn,astate-of-the-artfoundationlatent diffusionmodelthatenablestheguidedgenerationofhighlyrealisticand diverse histopathology H&E-stained images, as shown in an extensive benchmark. We explored training set scaling, slide-level overfitting and methodologicalimprovements,culminatingintheimprovedCytoSyn-v2, and compared our work to PixCell, a state-of-the-art model, in an indepthmanner.Thiscomparisonhighlightedthestrongsensitivityofboth diffusion models and performance metrics to preprocessing-specific details.OurmodelwastrainedonadatasetcreatedusingTCGAdiagnostic whole-slide images of 32 different cancer types but is able to maintain state-of-the-art performance on a non-oncology dataset. To support the research community, we publicly release CytoSyn’s weights, its training and validation datasets, and a sample of synthetic images in this repository: https://huggingface.co/Owkin-Bioptimus/CytoSyn.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/SASHIMI_022.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=qhFL0Z2NNF
BibTex
@InProceedings{DubTho_CytoSyn_MICCAISAT2026,
author = { Duboudin, Thomas AND Fontaine, Xavier AND Andrier, Étienne AND Guillou, Lionel AND Filiot, Alexandre AND Baiocco-Rodrigues, Thalyssa AND Olivier, Antoine AND Romagnoni, Alberto AND Klein, John AND Schiratti, Jean-Baptiste},
title = { { CytoSyn: a Foundation Diffusion Model for Histopathology Image Synthesis } },
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}
}