Salvato in:
Dettagli Bibliografici
Autori principali: Peysakhovich, Alexander, Berman, William, Rufo, Joseph, Wong, Felix, Wilson, Maxwell Z.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.11928
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909959260733440
author Peysakhovich, Alexander
Berman, William
Rufo, Joseph
Wong, Felix
Wilson, Maxwell Z.
author_facet Peysakhovich, Alexander
Berman, William
Rufo, Joseph
Wong, Felix
Wilson, Maxwell Z.
contents Cell painting is a popular technique for creating human-interpretable, high-contrast images of cell morphology. There are two major issues with cell paint: (1) it is labor-intensive and (2) it requires chemical fixation, making the study of cell dynamics impossible. We train a diffusion model (Morphological Observation Neural Enhancement Tool, or MONET) on a large dataset to predict cell paint channels from brightfield images. We show that model quality improves with scale. The model uses a consistency architecture to generate time-lapse videos, despite the impossibility of obtaining cell paint video training data. In addition, we show that this architecture enables a form of in-context learning, allowing the model to partially transfer to out-of-distribution cell lines and imaging protocols. Virtual cell painting is not intended to replace physical cell painting completely, but to act as a complementary tool enabling novel workflows in biological research.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11928
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MONET -- Virtual Cell Painting of Brightfield Images and Time Lapses Using Reference Consistent Diffusion
Peysakhovich, Alexander
Berman, William
Rufo, Joseph
Wong, Felix
Wilson, Maxwell Z.
Computer Vision and Pattern Recognition
Artificial Intelligence
Cell painting is a popular technique for creating human-interpretable, high-contrast images of cell morphology. There are two major issues with cell paint: (1) it is labor-intensive and (2) it requires chemical fixation, making the study of cell dynamics impossible. We train a diffusion model (Morphological Observation Neural Enhancement Tool, or MONET) on a large dataset to predict cell paint channels from brightfield images. We show that model quality improves with scale. The model uses a consistency architecture to generate time-lapse videos, despite the impossibility of obtaining cell paint video training data. In addition, we show that this architecture enables a form of in-context learning, allowing the model to partially transfer to out-of-distribution cell lines and imaging protocols. Virtual cell painting is not intended to replace physical cell painting completely, but to act as a complementary tool enabling novel workflows in biological research.
title MONET -- Virtual Cell Painting of Brightfield Images and Time Lapses Using Reference Consistent Diffusion
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.11928