Semi supervised GAN for smart microscopy, fast and data efficient cell cycle classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Manick, Rajeev, Habouz, Youssef El, Guillout, Maëlle, Martin, Celia, Bonnet, Julia, Ruel, Louis, Pastezeur, Sylvain, Chanteux, Olivier, Bouchareb, Otmane, Tramier, Marc, Pécréaux, Jacques
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917550048149504
author Manick, Rajeev
Habouz, Youssef El
Guillout, Maëlle
Martin, Celia
Bonnet, Julia
Ruel, Louis
Pastezeur, Sylvain
Chanteux, Olivier
Bouchareb, Otmane
Tramier, Marc
Pécréaux, Jacques
author_facet Manick, Rajeev
Habouz, Youssef El
Guillout, Maëlle
Martin, Celia
Bonnet, Julia
Ruel, Louis
Pastezeur, Sylvain
Chanteux, Olivier
Bouchareb, Otmane
Tramier, Marc
Pécréaux, Jacques
contents Modern optical microscopes are fully motorised; however, transforming them into truly smart systems requires real-time adjustment of acquisition settings in response to detected objects and dynamic biological events. At the core are classification algorithms that commonly depend on customised software and are generally designed for narrowly-defined biological applications. In addition, they often require substantial annotated datasets for effective training. We introduce a semi-supervised generative adversarial network (SGAN) for robust cell-cycle stage classification under low-resource conditions, adaptable to diverse cellular structures. The framework combines unlabelled microscopy images with synthetically generated samples to mitigate limited annotation, while preserving stable performance even when the unlabelled subset is class-imbalanced. Tested on the Mitocheck dataset, which features five mitosis classes, the model achieved $93 \pm 2\%$ accuracy using only 80 labelled per class and 600 unlabelled images. The proposed algorithm is generic and can be readily adapted to new labeling schemes, classification targets, cell lines, or microscopy modalities through transfer learning. SGAN is well suited for integration into automated microscopes, enabling efficient and adaptable image analysis across diverse biological and microscopy applications.
format Preprint
id arxiv_https___arxiv_org_abs_2604_20615
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Semi supervised GAN for smart microscopy, fast and data efficient cell cycle classification
Manick, Rajeev
Habouz, Youssef El
Guillout, Maëlle
Martin, Celia
Bonnet, Julia
Ruel, Louis
Pastezeur, Sylvain
Chanteux, Olivier
Bouchareb, Otmane
Tramier, Marc
Pécréaux, Jacques
Quantitative Methods
I.2.10; I.4.8
Modern optical microscopes are fully motorised; however, transforming them into truly smart systems requires real-time adjustment of acquisition settings in response to detected objects and dynamic biological events. At the core are classification algorithms that commonly depend on customised software and are generally designed for narrowly-defined biological applications. In addition, they often require substantial annotated datasets for effective training. We introduce a semi-supervised generative adversarial network (SGAN) for robust cell-cycle stage classification under low-resource conditions, adaptable to diverse cellular structures. The framework combines unlabelled microscopy images with synthetically generated samples to mitigate limited annotation, while preserving stable performance even when the unlabelled subset is class-imbalanced. Tested on the Mitocheck dataset, which features five mitosis classes, the model achieved $93 \pm 2\%$ accuracy using only 80 labelled per class and 600 unlabelled images. The proposed algorithm is generic and can be readily adapted to new labeling schemes, classification targets, cell lines, or microscopy modalities through transfer learning. SGAN is well suited for integration into automated microscopes, enabling efficient and adaptable image analysis across diverse biological and microscopy applications.
title Semi supervised GAN for smart microscopy, fast and data efficient cell cycle classification
topic Quantitative Methods
I.2.10; I.4.8
url https://arxiv.org/abs/2604.20615