Machine Learning To Keep An Eye On Migrating Cells

Japanese researchers have developed a machine learning tool that allows the study of label-free cells migrating in vitro.

AsianScientist (Apr. 2, 2019) – Cell migration is a critical aspect of organismal development and disease, so scientists in Japan have devised a tool to directly track and characterize moving cells in vitro. They published their results in SoftwareX.

In living creatures, cells are constantly on the move, be it to generate a new organ or to respond to injury or infection. However, biologists have long struggled to quantify the movement and changing morphology of cells over time.

To better understand cell migration, researchers led by Professor Amy Shen at the Okinawa Institute of Science and Technology (OIST) in Japan have applied machine learning to analyze microscopic snapshots of migrating cells. The program is built around a machine learning infrastructure known as a ‘convolutional neural network,’ which enables the software to trace the outlines of individual cells, monitor their movement and transform that information into quantitative data.

“Most software… cannot distinguish individual cells under conditions of high-density culture,” said Dr. Tsai Hsieh-Fu of OIST, the first author of the study. “With our software, we can segment images correctly even if cells are touching. We can actually do single-cell tracking throughout the entire experiment.”

They named the software Usiigaci, a Ryukyuan word that refers to tracing the outlines of objects, as the tool detects the changing outlines of individual cells in a label-free manner, which means that the cells need not be stained with any dyes or fluorescent molecules beforehand. Going forward, the researchers aim to develop neural networks to identify different components within cells, rather than just their outlines.

“We’re hoping this software can become quite useful for the scientific community,” said Shen. “You can use this software for any biological study or drug screening that requires you to track cellular responses to different stimuli.”

The article can be found at: Tsai et al. (2019) Usiigaci: Instance-aware Cell Tracking in Stain-free Phase Contrast Microscopy Enabled by Machine Learning.


Source: Okinawa Institute of Science and Technology Graduate University.
Disclaimer: This article does not necessarily reflect the views of AsianScientist or its staff.

Asian Scientist Magazine is an award-winning science and technology magazine that highlights R&D news stories from Asia to a global audience. The magazine is published by Singapore-headquartered Wildtype Media Group.

Related Stories from Asian Scientist