Evaluation of a Deep Learning Based Approach to Computational Label Free Cell Viability Quantification

Abstract

One of the most common techniques found in a cell biology or tissue engineering lab is the cytotoxicity assay. This can be performed using a variety of different dyes and stains and various protocols to result in a clear indication of dead and live cells within a culture to quantify the viability of a culture and monitor for sudden drops or increases in viability by a drug, material, viral vector, etc introduced into the culture. This assay helps cell biologists determine the health of their culture and what toxicity added substances may add to the culture and whether they are appropriate and safe to use with human cells. However, many of the dyes and stains used for this process are eventually toxic to cells, rendering the cells useless after testing and preventing real time monitoring of the same culture over a period of hours or days. Computation biology is moving cell biology towards novel and innovative techniques such as in silico labeling and dye free labeling using deep learning algorithms. In this work, we investigate whether it is feasible to train a Resnet CNN model to detect morphological changes in human cells that indicate cell death in order to classify cells as live or dead without utilizing a stain or dye. This work also aims to train one CNN model to count all cells regardless of viability status to get a total cell count, and then one CNN model that specifically identifies and counts all of the dead cells for an accurate dead and live cell total by utilizing both pieces of data to determine a general viability percentage for the culture. Additionally, this work explores the use of various image enhancements to understand if this process helps or impedes the deep learning models in their detection of total cells and dead cells.