COSMOS: a platform for real-time morphology-based, label-free cell sorting using deep learning

Cells are the singular building blocks of life, and a comprehensive understanding of morphology, among other properties, is crucial to the assessment of underlying heterogeneity. We developed Computational Sorting and Mapping of Single Cells (COSMOS), a platform based on Artificial Intelligence (AI) and microfluidics to characterize and sort single cells based on real-time deep learning interpretation of high-resolution brightfield images. Supervised deep learning models were applied to characterize and sort cell lines and dissociated primary tissue based on high-dimensional embedding vectors of morphology without the need for biomarker labels and stains/dyes. We demonstrate COSMOS capabilities with multiple human cell lines and tissue samples. These early results suggest that our neural networks embedding space can capture and recapitulate deep visual characteristics and can be used to efficiently purify unlabeled viable cells with desired morphological traits. Our approach resolves a technical gap in the ability to perform real-time deep learning assessment and sorting of cells based on high-resolution brightfield images.

Artificial Intelligence-Driven Morphology-Based Enrichment of Malignant Cells from Body Fluid

Cell morphology is a fundamental feature used to evaluate patient specimens in pathologic analysis. However, traditional cytopathology analysis of patient effusion samples is limited by low tumor cell abundance coupled with the high background of nonmalignant cells, restricting the ability of downstream molecular and functional analyses to identify actionable therapeutic targets. We applied the Deepcell platform that combines microfluidic sorting, brightfield imaging, and real-time deep learning interpretations based on multidimensional morphology to enrich carcinoma cells from malignant effusions without cell staining or labels. Carcinoma cell enrichment was validated with whole genome sequencing and targeted mutation analysis, which showed a higher sensitivity for detection of tumor fractions and critical somatic variant mutations that were initially at low levels or undetectable in presort patient samples. Our study demonstrates the feasibility and added value of supplementing traditional morphology-based cytology with deep learning, multidimensional morphology analysis, and microfluidic sorting.