Rapid, label-free classification of tumor-reactive T cell killing with quantitative phase microscopy and machine learning

Abstract

Quantitative phase microscopy (QPM) enables studies of living biological systems without exogenous labels. To increase the utility of QPM, machine-learning methods have been adapted to extract additional information from the quantitative phase data. Previous QPM approaches focused on fluid flow systems or time-lapse images that provide high throughput data for cells at single time points, or of time-lapse images that require delayed post-experiment analyses, respectively. To date, QPM studies have not imaged specific cells over time with rapid, concurrent analyses during image acquisition. In order to study biological phenomena or cellular interactions over time, efficient time-dependent methods that automatically and rapidly identify events of interest are desirable. Here, we present an approach that combines QPM and machine learning to identify tumor-reactive T cell killing of adherent cancer cells rapidly, which could be used for identifying and isolating novel T cells and/or their T cell receptors for studies in cancer immunotherapy. We demonstrate the utility of this method by machine learning model training and validation studies using one melanoma-cognate T cell receptor model system, followed by high classification accuracy in identifying T cell killing in an additional, independent melanoma-cognate T cell receptor model system. This general approach could be useful for studying additional biological systems under label-free conditions over extended periods of examination.

Functional blood cell analysis by label-free biosensors and single-cell technologies

“…Increase in dry cell mass as detected with the same technique can as well be detected for the same purpose [304]. Similarly, quantitative phase microscopy based image acquisition combined with machine learning successfully detected T-cell mediated cytotoxicity [305].…”

Wavefront Microscopy Using Quadriwave Lateral Shearing Interferometry: From Bioimaging to Nanophotonics

“…To feed a machine learning algorithm, many quantitative features can be extracted from an OPD image: the dry mass and dry mass density, as already mentioned, but also the area, the optical volume, the eccentricity, the perimeter, and the shape factor, among others . In 2021, the group of Teitell used many such parameters extracted from CGM images to feed a machine learning algorithm and train it to classify tumor-reactive T cells in a rapid and label-free manner …”