Label-free morphological profiling and isolation of immune cell subsets using VisionSort, a novel, AI-based flow cytometry platform.

---

Presentation Time: 11:30 AM - 12:45 PM
Poster Board Number: B893
Abstract ID: 4944

Presenting Author:
Greg Schneider , Manager, US Field Application Science at ThinkCyte

Abstract:

Identification, characterization, and minimally invasive isolation of specific populations of human immune cells are critical for understanding and treating disease. Here we present data on label-free identification of three immune cell subsets by morphological profiling using VisionSort; a label-free, artificial intelligence (AI)-driven cellular analysis and sorting platform. By capturing single-cell digital phenotypes, we characterized mouse T-cells and generated ‘ground truth’ functional profiles for activated and non-activated T cells. A set of machine-learning derived classifiers was generated to identify these phenotypic classes in unlabeled T-cell subsets. The classifier showed an area under the curve (AUC) performance for differentiating between phenotypically defined T cell populations of 0.917. In addition, by using unsupervised machine learning, we were able to resolve activated and non-activated T cell populations label free, using morphological data alone. Using a similar approach, we show label-free differentiation/classification of B cells from plasma cells with an AUC score of 0.941 and M1 and M2 polarized macrophages with an AUC score of 0.878 +/- 0.002 (n=6). Here we report results on the use of a novel, label-free cytometry platform to characterize and isolate human immune cell subsets using morphological profiling and AI with applications for investigators in basic life sciences and drug developers in small molecule, antibody, and cell therapy R&D.