Label-free cell counting and viability prediction with brightfield imaging and deep learning

2026-10-07

AI Summary

This study addresses the limitations of conventional staining methods, including cellular perturbation, photobleaching, and the inability to perform real-time monitoring. We propose ViabiLens, a framework that leverages bright-field microscopy combined with convolutional neural networks and object detection algorithms for label-free cell viability assessment. The core innovation lies in revealing deep feature similarities between unstained and stained images, enabling transfer learning to generalize models to unstained scenarios for cell localization and live/dead classification. This work pioneers a universal predictive model alongside an open-source benchmark dataset. Experimental evaluations on CHO cells demonstrate that predictions for unstained samples achieve a mean absolute error of only 2.68%, validating the framework’s capacity for high-precision, real-time viability monitoring.

Abstract

Cell viability assessment is a core requirement in cell culture systems, with critical applications in biopharmaceutical manufacturing and drug development. Conventionally, it is measured by adding membrane-impermeable dyes to a sample (a process called staining), which allows compromised cell membranes to be distinguished from intact ones. However, staining has several limitations: (a) chemical agents can perturb normal cellular processes of the cells being measured, (b) it is often ambiguous to assign viability to individual cells whose membrane integrity is only partially compromised. (c) photobleaching can undermine measurement accuracy over time when using fluorescent stains, and (d) staining cannot be performed in situ or in real time. Here, we show that (1) stained cells captured under brightfield imaging contain sufficient information to distinguish live and dead cells, and (2) cells captured under unstained brightfield imaging exhibit similar image features to their stained counterparts, enabling models trained on stained cells to generalize to unstained ones. We then report the development and validation of ViabiLens, an AI-assisted software for label-free cell viability analysis. The ViabiLens combines a cell detection model for localizing individual cells with a convolutional neural network (CNN) classifier for live/dead prediction, paired with an interactive UMAP-based viewer for visualizing and exploring individual cells across the sample. Evaluated on Chinese Hamster Ovary (CHO) cells spanning a wide range of viability conditions, ViabiLens achieves a mean absolute error of 2.68\% on unstained samples against fluorescence-based reference measurements. We also release a benchmark dataset for label-free cell viability analysis to facilitate future research, available at https://amirrezavazifeh.github.io/ViabiLens-Project-Page/.

Problem

• cell viability
• label-free
• cell counting
• brightfield imaging
• staining limitations

Innovation

• Label-free cell viability
• Brightfield imaging
• Deep learning
• Convolutional neural network
• UMAP visualization