AI counts and tests cell health using normal microscope images
Label-free cell counting and viability prediction with brightfield imaging and deep learning
Computer Vision and Pattern Recognition
Summary
Measuring whether cells are alive or dead usually requires special dyes that can affect the cells or require complicated processes. The authors show that regular microscope images without dyes contain enough clues to tell live cells from dead ones. They created a software called ViabiLens that spots and classifies cells using artificial intelligence to predict cell health without damaging them. This method works well compared to standard dye methods and can be used for cells grown in labs, helping to simplify cell health checks.
What this means in practice
- •For biopharmaceutical manufacturers: Assess cell health in bioreactors without using dyes, enabling nondestructive and ongoing monitoring during production.
- •For drug development teams: Perform real-time cell viability checks in drug screening using only standard microscope images, eliminating delays from staining.
Authors
Amir Reza Vazifeh, Christian Zeigler, Sornanathan Meyyappan, Richard Jeske, Jason W. Fleischer
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/.