SALK INSTITUTE (KUSI) – Scientists at the Salk Institute needed a way to improve low-quality images critical for seeing structures inside cells. Now, they have figured out how to use artificial intelligence to improve microscope images. Barriers to this included microscopes being extremely expensive, and even with those high-tech microscopes, the low light allowed for the absence of important detail. High amounts of light could damage the cells, making them unable to be studied. The solution uses "deep learning," in which computer software learns to recognize something and improve by studying examples.

IMAGE: Time-lapse gradient light interference microscopy, or GLIM, left, and phase imaging with computational specificity imaged over seven days. Researchers at the University of Illinois Urbana Champaign have developed a new technique that combines label-free imaging with artificial intelligence to visualize unlabeled live cells over a prolonged time. This technique has potential applications in studying cell viability and pathology. The study "Phase imaging with computational specificity (PICS) for measuring dry mass changes in sub-cellular compartments" was published in Nature Communications. "Our lab specializes in label-free imaging, which allows us to visualize cells without using toxic chemicals," said Gabriel Popescu, a professor of electrical and computer engineering and the director of the Quantitative Light Imaging Laboratory at the Beckman Institute for Advanced Science and Technology.