AsianScientist (Jun. 25, 2018) – Researchers in Japan have devised a method that combines an imaging technique with artificial intelligence to identify and sort cells with unprecedented speed. Their work is published in Science.
Cell sorting is a technique used in laboratories to separate complex mixtures of cells into their component cell types. Because certain cell types are very similar in size and shape, existing cell sorting methods may struggle with distinguishing one group of cells from another.
In the present study, scientists at the University of Tokyo have invented a new cell identification and sorting system called ghost cytometry. In ghost cytometry, cells flow one at a time though a narrow channel underneath a single-pixel detector camera that senses the fluorescent light waves emitted by each cell. This interpretation of light waves without needing to transform them into a full image is what makes ghost cytometry an image-free visual system.
An electrical circuit equipped with machine learning algorithms is attached to the single-pixel detector camera and learns the unique light wave pattern of each cell type to identify cells within ten microseconds. The circuit then sends an electrical signal to push cells into the correct sorting pathway for their type as they flow past.
The machine learning system does not need images to analyze the cells, but if researchers require images for additional analysis, the single-pixel detector camera captures enough information to digitally reconstruct traditional two-dimensional pictures of cells that pass through the cytometry system.
The researchers demonstrated that their technique can identify cells at a rate of more than 10,000 cells per second and sort cells into appropriate groups at a rate of multiple thousands of cells per second. Human experts using microscopy routinely identify and sort fewer than ten cells per second, sometimes with less accuracy.
Some of the researchers on the project have spun off a company—ThinkCyte—to commercialize ghost cytometry. This year, ThinkCyte plans to start oncology and regenerative medicine clinical research projects using ghost cytometry in collaboration with research institutes.
“Ghost cytometry will help researchers who need to classify cells in the lab, and benefit clinicians and patients who need fast and accurate isolation and diagnosis of cell samples,” said Associate Professor Sadao Ota from the University of Tokyo, who was involved in the research.
The article can be found at: Ota et al. (2018) Ghost Cytometry.
Source: University of Tokyo; Photo: Sacco Fujishima.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.