Artificial Intelligence Automates Fluorescent Microscopy

Researchers in Switzerland have developed software to automate microscope control for imaging biological events in detail. The solution uses artificial intelligence to detect precursors to division and automatically update the microscope’s control software to take more pictures.

Previously, using a fluorescent microscope to study events like bacterial division—which can take hours—either required manual surveillance or frequent imaging that could damage the sample and result in copious amounts of useless images.

Described in a recent issue of Nature Methods, the École polytechnique fédérale de Lausanne (EFPL) tool automates the imaging of biological events like bacterial cell division and mitochondrial division with the help of artificial neural networks.

“An intelligent microscope is kind of like a self-driving car. It needs to process certain types of information, subtle patterns that it then responds to by changing its behavior,” says principal investigator Suliana Manley of EPFL’s Laboratory of Experimental Biophysics. “By using a neural network, we can detect much more subtle events and use them to drive changes in acquisition speed.”

Manley and her colleagues first solved how to detect mitochondrial division, which is unpredictable because it occurs infrequently and can happen almost anywhere within the mitochondrial network. They trained the neural network to look out for mitochondrial constrictions—a change in shape of mitochondria that leads to division—as well as observations of a protein known to be enriched at sites of division. When both constrictions and protein levels are high, the microscope switches into high-speed imaging to capture many images of division events in detail. When constriction and protein levels are low, the microscope then switches to low-speed imaging to avoid exposing the sample to excessive light.

With this intelligent fluorescent microscope, the scientists showed that they could observe the sample for longer compared to standard fast imaging. While the sample was more stressed compared to standard slow imaging, they were able to obtain more meaningful data. “The potential of intelligent microscopy includes measuring what standard acquisitions would miss,” Manley says. “We capture more events, measure smaller constrictions, and can follow each division in greater detail.”

The scientists are making the control framework available as an open source plug-in for the open microscope software Micro-Manager, with the aim of allowing other scientists to integrate artificial intelligence into their own microscopes.