This image shows the program “thinking,” as it considers what cellular structures to identify. IMAGE COURTESY OF DR. FINKBEINER, GLADSTONES INSTITUTES AND UCSFMicrographs of fluorescently labeled cells are undoubtedly beautiful, but they require invasive and sometimes disruptive or deadly protocols to get their glow. To avoid such perturbations, researchers have developed a computer program that can distinguish between cell types and identify subcellular structures, among other features—all without the fluorescent probes our human eyes rely on.
“This approach has the potential to revolutionize biomedical research,” Margaret Sutherland, program director at the National Institute of Neurological Disorders and Stroke, which partially funded the work, says in a statement.
The researchers, who published their work in Cell today (April 12), designed their a neural network, a program modeled after the brain, using an approach called deep learning, which uses data to recognize patterns, form rules, and apply those rules to new information. “We trained the neural network by showing it two sets of matching images of the same cells; one unlabeled and one with fluorescent labels,” coauthor Eric Christiansen, a software engineer at Google Accelerated Science, says a press release. “We repeated this process millions of times. Then, when we presented the network ...
