High‐content video flow cytometry with digital cell filtering for label‐free cell classification by machine learning

Abstract

Recent development of imaging flow cytometry (IFC) has enabled the measurements of single cells with high throughput, where fluorescent labels provide specificity for cellular diagnosis. The fluorescent labels may disturb the cell functions, and the requirements for high‐throughput measurements limit the cell image quality. Here, we develop the high‐content video flow cytometry (VFC) that measures unlabeled single cells with a rate of approximately 1000 cells per minute. For the obtained big data, the frame of interest (FOI) is automatically prepared by a digital cell filtering technique with machine learning. Cervical carcinoma cell lines (Caski, HeLa and C33‐A cells) are differentiated with an accuracy of 91.5%, 90.5%, and 90.5% by deep learning in a three‐way classification, respectively. The high‐content VFC not only provides high‐quality images of single cells with high throughput and rewinding, but also performs automatic digital cell filtering and label‐free cell classification that may have clinical applications.

Is AI essential? Examining the need for deep learning in image-activated sorting of Saccharomyces cerevisiae

“…Furthermore, the analyses presented here were conducted using our previously reported IACS system 28 that operates using fluorescence microscopy. Flow cytometric systems incorporating other methods for cell imaging have been reported including bright-field, 56–59 2D light-scattering 59–61 and Raman, 15,25 as well as 3D imaging techniques such as tomographic phase microscopy 62 and light-sheet fluorescence microscopy. 63–65 Similar investigations using images generated by a wider range of imaging flow cytometric systems would allow us to again draw more universal deductions about the value of utilizing AI for image classification in IACS overall, as well as provide insights for developing AI-enabled microfluidic cell sorting systems based on imaging modalities that have yet to be extended to cell sorting.…”

Label-free analysis of single microparticles and nanoscale exosomes with two-dimensional light scattering technology

“…Our previous study demonstrated that 2D light scattering pattern collected in the defocusing state contains information about the internal structure of cells 7 . We successfully identified a variety of cancer cells using 2D light scattering patterns [8][9][10][11][12] . The in focus 2D light scattering of particles can be used to track particle motion, such as Brownian motion of nanoparticles.…”

Processing and analysis of motion-blur images in light scattering flow cytometry

“…Twodimensional (2D) light scattering technology that simultaneously measures scattering polar angle θ and azimuthal angle φ obtains more information about label-free cells compared with one-dimensional (1D) light scattering 9,10 . 2D light scattering technology combined with hydrodynamic focusing technique could provide a powerful tool for highthroughput and label-free single particle or cell detection, which has been demonstrated by our group 11,12 .…”