Take a fresh look at your lifestyle.

Powerful microscopes made faster and more accurate with machine learning

Researchers have combined AI algorithms with two advanced microscopy techniques to dramatically reduce image processing time from days to seconds, while the resulting images are clear and accurate.

In observing the fast neuronal signals in, for example, a fish brain (see photo below), scientists have started to use a technique called light field microscopy, which makes it possible to image such fast biological processes in 3D.

But the images are often not of quality and it takes hours or days for huge amounts of data to be converted into 3D volumes and movies.

Light field microscopy captures large 3D images that allow researchers to track and measure remarkably fine movements, such as the beating heart of a fish larva, at very high speeds.

However, this technique produces massive amounts of data, which can take days to process, and the final images usually have no resolution.

To counter this, the team at the European Molecular Biology Laboratory (EMBL) has started to use a technique of the same name, light-sheet microscopy, located on a single 2D plane of a given sample at a time, to detect AI- quickly train algorithms to more easily understand the 3D images developed using the more data-intensive technique.

“Ultimately, we were able to take ‘the best of both worlds’ in this approach,” said Nils Wagner, one of the paper’s two lead authors. were able to take images as the light field microscopy allows and get as close as possible to the image resolution of light sheet microscopy.

”“ When you build algorithms that produce an image, you need to check that these algorithms form the correct image, ”says Anna Kreshuk, the EMBL group leader She explained that their new study used light-sheet microscopy to make sure the AI ​​algorithms worked properly.

The researchers believe their approach could potentially be modified to work with different types of microscopes as well, ultimately allowing biologists to look at dozens of different specimens and see much more, much faster.

For example, it could help find genes involved in the development of the heart, or it could measure the activity of thousands of neurons at the same time.