Intelligent image-based deformation-assisted cell sorting with molecular specificity

Abstract

The identification and separation of specific cells from heterogeneous populations is an essential prerequisite for further analysis or use. Conventional passive and active separation approaches rely on fluorescent or magnetic tags introduced to the cells of interest through molecular markers. Such labeling is time-and cost-intensive, can alter cellular properties, and might be incompatible with subsequent use, for example, in transplantation. Alternative label-free approaches utilizing morphological or mechanical features are attractive, but lack molecular specificity. Here we combine image-based real-time fluorescence and deformability cytometry (RT-FDC) with downstream cell sorting using standing surface acoustic waves (SSAW). We demonstrate basic sorting capabilities of the device by separating cell mimics and blood cell types based on fluorescence as well as deformability and other image parameters. The identification of blood sub-populations is enhanced by flow alignment and deformation of cells in the microfluidic channel constriction. In addition, the classification of blood cells using established fluorescence-based markers provides hundreds of thousands of labeled cell images used to train a deep neural network. The trained algorithm, with latency optimized to below 1 ms, is then used to identify and sort unlabeled blood cells at rates of 100 cells/sec. This approach transfers molecular specificity into labelfree sorting and opens up new possibilities for basic biological research and clinical therapeutic applications.

Single-Cell Mechanophenotyping in Microfluidics to Evaluate Behavior of U87 Glioma Cells

“…The images of the cells were obtained every 12 h between 48 to 120 h. ImageJ was used to manually measure the diameter and perimeter of the cells. The single-cell deformation indexes (D) of each cell were calculated using Equation (1) [ 39 , 40 ], where is 3.14. Figure 5 illustrates the deformation index of single cells in the microfluidic cell culture platform.…”

Sensitivity‐Enhancing Strategies in Optical Biosensing

“…There have been successful applications of machine learning for the precise analysis of biological data such as genetic information [113][114][115] and cellular images. [116][117][118][119][120] With its capability of processing a large amount of data, machine learning enables the detection of complex and/or marginally varying sensing signals in an accurate and rapid way. [121][122][123] Along with their contributions to developing autonomous systems and optimizing sensor designs, machinelearning-based approaches can fully benefit multiplexed and real-time sensing (e.g., wearable health monitoring systems) where complex and fluctuating signal matrices must be crossinterpreted to draw diagnostic outcomes.…”

Microfluidic label-free bioprocessing of human reticulocytes from erythroid culture

“…As an alternative to utilizing cell surface markers, biophysical markers are relatively new and are gaining momentum as unique biomarker for cell identification. Masaeli et al, Nawaz et al and Nitta et al have developed label-free biophysical cytometers using image analysis and microfluidic structures to measure cell deformation and size albeit with limited sorting throughput of 100 cells per s. 23,55,56 DFF devices are scalable and have been shown to process samples at mL per minute, while DLD have been shown to sort cell at high cell concentrations. In this study, we further developed the DFF and DLD technology for the label-free biophysical marker sorting of reticulocytes from erythroid culture and compared the outcome with the current gold standard of FACS sorting.…”