Biology subjects

Bouchareb, O.

Publications and source records attributed to Bouchareb, O..

4 recordsLinked to original sources

bioRxiv2026

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

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 softwares 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{+/-}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.

bioinformatics↗

bioRxiv2025

Smart Microscopy: Current Implementations and a Roadmap for Interoperability

Smart microscopy is transforming life sciences by automating experimental imaging workflows and enabling real-time adaptation based on feedback from images and other data streams. This shift increases throughput, improves reproducibility, and expands the functional capabilities of microscopes. However, the current landscape is highly fragmented. Academic researchers often develop custom solutions for specific scientific needs, while industry offerings are typically proprietary and tied to specific hardware. This diversity, while fostering innovation, also creates major challenges in interoperability, reproducibility, and standardization, which slows progress and adaption. This article presents a collaborative effort between academic and industry leaders to survey the current state of smart microscopy, highlight representative implementations, and identify common technical and organizational barriers. We propose a framework for greater interoperability based on shared standards, modular software design, and community-driven development. Our goal is to support collaboration across the field and lay the groundwork for a more connected, reusable, and accessible smart microscopy ecosystem. We conclude with a call to action for researchers, hardware developers, and institutions to join in building an open, interoperable foundation that will unlock the full potential of smart microscopy in life science research.

cell biology↗

bioRxiv2024

The Roboscope: Smart and Fast Microscopy for Generic Event-Driven Acquisition

Automation of fluorescence microscopy is a challenge for capturing rare or transient events in biology and medicine. It relies on smart devices that integrate and interpret the observed data, and react to the targeted biological event. We report on the Roboscope, a novel autonomous microscope combining sequence interruption and deep learning integration, allowing generic event-driven acquisitions. This system distinguishes itself by its adaptability to various experiments, quick capture of dynamic events, and minimal data greediness - training with less than 100 images per class. The Roboscopes capability is demonstrated in non-synchronized cells by capturing the metaphase, a 20-minute event happening once per day or less. Conversely, double thymidine-block synchronisation, despite occurring during DNA replication, may perturb mitotic-spindle mechanics. The Roboscopes versatility and efficiency offer significant advancements to tackle the current challenges of cell biology, spreading out advanced microscopy methods to fundamental research as well as high content screening and precision medicine.

bioengineering↗

bioRxiv2020

Neural network fast-classifies biological images using features selected after their random-forests-importance to power smart microscopy.

Artificial intelligence is nowadays used for cell detection and classification in optical microscopy, during post-acquisition analysis. The microscopes are now fully automated and next expected to be smart, to make acquisition decisions based on the images. It calls for analysing them on the fly. Biology further imposes training on a reduced dataset due to cost and time to prepare the samples and have the datasets annotated by experts. We propose here a real-time image processing, compliant with these specifications by balancing accurate detection and execution performance. We characterised the images using a generic, high-dimensional feature extractor. We then classified the images using machine learning for the sake of understanding the contribution of each feature in decision and execution time. We found that the non-linear-classifier random forests outperformed Fishers linear discriminant. More importantly, the most discriminant and time-consuming features could be excluded without any significant loss in accuracy, offering a substantial gain in execution time. It suggests a feature-group redundancy likely related to the biology of the observed cells. We offer a method to select fast and discriminant features. In our assay, a 79.6 {+/-} 2.4 % accurate classification of a cell took 68.7 {+/-} 3.5 ms (mean {+/-} SD, 5-fold cross-validation nested in 10 bootstrap repeats), corresponding to 14 cells per second, dispatched into 8 phases of the cell cycle using 12 feature-groups and operating a consumer market ARM-based embedded system. Interestingly, a simple neural network offered similar performances paving the way to faster training and classification, using parallel execution on a general-purpose graphic processing unit. Finally, this strategy is also usable for deep neural networks paving the way to optimising these algorithms for smart microscopy.

bioinformatics↗