Machine learning and microscopy make sense of cells
Image: New method predicts 3D fluorescence microscopy images from transmitted light microscopy images. [Allen Institute]
Researchers at the Allen Institute, US, have used machine learning to train computers to see parts of the cell the human eye cannot easily distinguish.
Using 3D images of fluorescently labeled cells, the research team taught computers to find structures inside living cells without fluorescent labels, using only black and white images generated by brightfield microscopy.
"This technology lets us view a larger set of those structures than was possible before," says Dr Greg Johnson from the Allen Institute for Cell Science. "This means that we can explore the organization of the cell in ways that nobody has been able to do, especially in live cells."
As Dr Rick Horwitz, Executive Director of the Allen Institute for Cell Science, highlights, the prediction tool could also help scientists understand what goes wrong in cells during disease.
"This technique has huge potential ramifications... you can watch processes live as they are taking place; it's almost like magic," he says. "This method allows us, in the most non-invasive way that we have so far, to obtain information about human cells that we were previously unable to get."
According to the researchers, the combination of the freely available prediction toolset and brightfield microscopy could lower research costs if used in place of fluorescence microscopy, which requires expensive equipment and trained operators.
Fluorescent tags are also subject to fading, and the light itself can damage living cells, limiting the technique's utility to study live cells and their dynamics.
The machine learning approach would allow scientists to track precise changes in cells over long periods of time, potentially shedding light on events such as early development or disease progression.
To the human eye, cells viewed in a brightfield microscope are sacs rendered in shades of gray.
A trained scientist can find the edges of a cell and the nucleus, the cell's DNA-storage compartment, but not much else.
The research team used an existing machine learning technique, known as a convolutional neural network, to train computers to recognize finer details in these images, such as the mitochondria, cells' powerhouses.
They tested 12 different cellular structures and the model generated predicted images that matched the fluorescently labeled images for most of those structures, the researchers said.
It also turned out what the algorithm was able to capture surprised even the modeling scientists.
"Going in, we had this idea that if our own eyes aren't able to see a certain structure, then the machine wouldn't be able to learn it," says Dr Molly Maleckar, Director of Modeling at the Allen Institute for Cell Science. "Machines can see things we can't. They can learn things we can't. And they can do it much faster."
The technique can also predict precise structural information from images taken with an electron microscope.
The computational approach here is the same, but the applications are different, adds Dr Forrest Collman, Assistant Investigator at the Allen Institute for Brain Science.
Collman is part of a team working to map connections between neurons in the mouse brain. They are using the method to line up images of the neurons taken with different types of microscopes, normally a challenging problem for a computer and a laborious task for a human.
Label-free microscopy: Allen Institute researchers have used machine learning to train computers to see parts of the cell the human eye cannot easily distinguish.
Dr Roger Brent, a Member of the Basic Sciences Division at Fred Hutchinson Cancer Research Center, is also using the new approach as part of a research effort he is leading to develop microscopes for biologists studying yeast and mammalian cells.
"Replacing fluorescence microscopes with less light intensive microscopes would enable researchers to accelerate their work, make better measurements of cell and tissue function, and save some money in the process," he says. "By making these networks available, the Allen Institute is helping to democratize biological and medical research."
Research is published in Nature Methods.