UC San Diego

The ability to classify and map numerous cell types as well as healthy and diseased cells can bring significant insight to biology and medicine. While single-cell sequencing becomes cornerstone for cell classification and mapping, isolation of interested cells for genomic analyses rely on fluorescence activated cell sorting (FACS), which can only isolate cells based on integrated intensities. The availability of flow cytometers with the capability to classify and isolate cells guided by high-content cell images is enabling and transformative. It provides a new paradigm to allow researchers and clinicians to isolate cells using multiple user-defined characteristics encoded by both fluorescent signals and morphological and spatial features. In this thesis, we demonstrated the “Image-Guided Cell Classification and Sorting” technology. This technology possesses high throughput isolation capability of FACS and high information content of microscopy.

To achieve “Image-Guided Cell Classification and Sorting”, we combined the techniques of machine learning, photonics, real-time signal processing and microfluidics.