"But now a team of scientists at Harvard and MIT have found a way to bypass that bottleneck: using machine learning to guide a simpler, less-expensive variety of microscope in real time. The idea is to home in on key details first and minimize time spent on areas of lesser interest - the same way we might zero in on words on a page instead of margins."
"said Professor Aravinthan Samuel, a researcher in the Department of Physics and Center for Brain Science and one of the senior authors of a new paper published in Nature Methods. "Our goal is to democratize connectomics. If you can make the relatively common single-beam scanning electron microscope more intelligent, it can run an order of magnitude faster. With foreseeable improvements, a single-beam microscope with SmartEM capability can reach the performance of a very expensive and rare machine.""
SmartEM applies machine learning to steer simpler, less-expensive single-beam scanning electron microscopes in real time. The method focuses high-resolution imaging on informative regions while skipping less relevant areas, analogous to human visual attention. SmartEM can speed scanning roughly sevenfold and bring single-beam microscopes toward the performance of expensive multi-beam instruments. A five-year collaboration involving Harvard, MIT, Johns Hopkins Applied Physics Laboratory, and Thermo Fisher Scientific developed the method. SmartEM aims to lower cost and increase accessibility of connectomics, enabling broader mapping of neural circuits and accelerating studies of brain function and behavior.
Read at Harvard Gazette
Unable to calculate read time
Collection
[
|
...
]