A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

The application of machine learning approaches to imaging flow cytometry (IFC) data has the potential to transform the diagnosis of hematological diseases. However, the need for manually labeled single-cell images for machine learning model training has severely limited its clinical application. To address this, we present iCellCnn, a weakly supervised deep learning approach for label-free IFC-based blood diagnostics.

High-throughput multiparametric imaging flow cytometry: toward diffraction-limited sub-cellular detection and monitoring of sub-cellular processes.

We present a sheathless, microfluidic imaging flow cytometer that incorporates stroboscopic illumination for blur-free fluorescence detection at ultra-high analytical throughput. The imaging platform is capable of multiparametric fluorescence quantification and sub-cellular localization of these structures down to 500 nm with microscopy image quality. We demonstrate the efficacy of the approach through the analysis and localization of P-bodies and stress granules in yeast and human cells using fluorescence and bright-field detection at analytical throughputs in excess of 60,000 and 400,000 cells/s, respectively.

Deformation of leukaemia cell lines in hyperbolic microchannels: investigating the role of shear and extensional components.

The mechanical properties of cells are of enormous interest in a diverse range of physio and pathological situations of clinical relevance. Unsurprisingly, a variety of microfluidic platforms have been developed in recent years to study the deformability of cells, most commonly employing pure shear or extensional flows, with and without direct contact of the cells with channel walls. Herein, we investigate the effects of shear and extensional flow components on fluid-induced cell deformation by means of three microchannel geometries.

An optofluidic system with integrated microlens arrays for parallel imaging flow cytometry.

In recent years, high-speed imaging has become increasingly effective for the rapid analysis of single cells in flowing environments. Single cell imaging methods typically incorporate a minimum magnification of 10× when extracting sizing and morphological information. Although information content may be significantly enhanced by increasing magnification, this is accompanied by a corresponding reduction in field of view, and thus a decrease in the number of cells assayed per unit time.

High-throughput microfluidic imaging flow cytometry.

Recently, microfluidic-based flow cytometry platforms have been shown to be powerful tools for the manipulation and analysis of single cells and micron-sized particles in flow. That said, current microfluidic flow cytometers are limited in both their analytical throughput and spatial resolution, due to their reliance on single point interrogation schemes. Conversely, high-speed imaging techniques can be applied to a wide variety of problems in which analyte molecules are manipulated at high linear velocities.