EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Biology-informed virtual staining enables label-free detection of cell state transitions at the single-cell level

Sergi Masó Orriols, Jesús Pineda, Zofia Korczak, Benjamin Midtvedt, Jesús A Dominguez, Montse Masoliver, Joan Bertran, Giovanni Volpe, Carlo Manzo, Caroline Beck Adiels

Machine Learning: Science and Technology · 09.11.2026

DOI: 10.1088/2632-2153/aebff2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 09.11.2026. Verfasst von Sergi Masó Orriols und 9 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universitat de Vic-Universitat Central de Catalunya, Horizon Europe, Knut and Alice Wallenberg Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Assessing cell viability and death pathways is central to biomedical research, yet conventional fluorescence-based live/dead assays are invasive, labour-intensive, and limited in capturing dynamic transitions. Deep learning-based virtual staining has emerged as a noninvasive alternative, but its accuracy remains restricted by the inconsistencies and artifacts inherently present in chemically stained training datasets. Here, we introduce a biology-informed augmented staining framework that integrates human-in-the-loop curation with generative adversarial networks to translate phase-contrast microscopy images into reliable virtual fluorescence representations. By
imposing biologically motivated constraints — such as replacing unreliable labels with controlled synthetic noise — we mitigate biases in conventional datasets and improve the representation of live, unhealthy (early apoptotic), and dead cells.
Using human endothelial cells subjected to oxidative stress in microfluidic devices, we demonstrate that our approach recapitulates population-level fluorescence viability dynamics while also enabling analysis at single-cell resolution. Transition points between viability states are automatically detected by comparing smoothed intensity traces and quantifying change points with associated transition bands. In an independent experiment comprising 20 cells and 2000 frames, assessed by three annotators blinded to the predictions, biology-informed training increased the macro-averaged F1 score from 0.57 to 0.78 and Cohen’s kappa from 0.34 to 0.65 compared with
training on raw fluorescence labels. This analysis also reveals substantial heterogeneity in apoptotic onset and progression, consistent with morphological cues. 
Our results establish biology-informed virtual staining as a strategy to extend the scope of image translation methods, enabling label-free, longitudinal, and accurate single-cell monitoring of viability states. This approach addresses the key bottleneck of training data reliability and provides a framework for integrating domain knowledge into machine learning methods for biological imaging.

Förderung

  • Universitat de Vic-Universitat Central de Catalunya
  • Horizon Europe
  • Knut and Alice Wallenberg Foundation
  • European Union
  • Swedish Foundation for Strategic Research SSF Works
  • Swedish Research Council

Zitieren

APA

Orriols, S. M., Pineda, J., Korczak, Z., Midtvedt, B., Dominguez, J. A., Masoliver, M., Bertran, J., Volpe, G., Manzo, C., & Adiels, C. B. (2026). Biology-informed virtual staining enables label-free detection of cell state transitions at the single-cell level. Machine Learning: Science and Technology. https://doi.org/10.1088/2632-2153/aebff2

Vancouver

Orriols SM, Pineda J, Korczak Z, Midtvedt B, Dominguez JA, Masoliver M, et al. Biology-informed virtual staining enables label-free detection of cell state transitions at the single-cell level. Machine Learning: Science and Technology. 2026. doi:10.1088/2632-2153/aebff2

BibTeX
@article{Orriols2026,
  author = {Orriols, Sergi Masó and Pineda, Jesús and Korczak, Zofia and Midtvedt, Benjamin and Dominguez, Jesús A and Masoliver, Montse and Bertran, Joan and Volpe, Giovanni and Manzo, Carlo and Adiels, Caroline Beck},
  title = {Biology-informed virtual staining enables label-free detection of cell state transitions at the single-cell level},
  journal = {Machine Learning: Science and Technology},
  year = {2026},
  doi = {10.1088/2632-2153/aebff2}
}
Kostenlos starten →