Menu

Deep Learning Allows for Cell Analysis Without Labeling

A new microscopy program requires no fluorescent markers to identify cell type, nuclei, and other characteristics.

Apr 12, 2018
Kerry Grens

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 with an unlabeled image it had never seen, it could accurately predict where the fluorescent labels belong.”

With high-quality images, the program correctly identified nuclei within cells just about perfectly. It could also distinguish dead from living cells, spot neurons within groups of cells that included astrocytes and immature dividing cells, and even tell a dendrite from an axon.

“Techniques like this tend to have a democratizing effect,” opening up opportunities for smaller groups, Molly Maleckar, the director of mathematical modeling at the Allen Institute for Cell Science who was not involved in the study, tells Wired

The authors of the study say future work will look to optimize the network and boost its performance on certain tasks where it was less robust, such as picking out neuronal subtypes and finding axons in high-density cultures.

November 2018

Intelligent Science

Wrapping our heads around human smarts

Marketplace

Sponsored Product Updates

LGC announces new, integrated, global portfolio brand, Biosearch Technologies, representing genomic tools for mission critical customer applications

LGC announces new, integrated, global portfolio brand, Biosearch Technologies, representing genomic tools for mission critical customer applications

LGC’s Genomics division announced it is transforming its branding under LGC, Biosearch Technologies, a unified portfolio brand integrating optimised genomic analysis technologies and tools to accelerate scientific outcomes.

DefiniGEN licenses CRISPR-Cas9 gene editing technology from Broad Institute to develop cell models for optimized metabolic disease drug development

DefiniGEN licenses CRISPR-Cas9 gene editing technology from Broad Institute to develop cell models for optimized metabolic disease drug development

DefiniGEN Ltd are pleased to announce the commercial licensing of CRISPR-Cas9 gene-editing technology from Broad Institute of MIT and Harvard in the USA, to develop human cell disease models to support preclinical metabolic disease therapeutic programmes.

Thermo Fisher Scientific: Freezers for Biological Samples

Thermo Fisher Scientific: Freezers for Biological Samples

Fluctuations in temperature can reduce the efficacy, decompose, or shorten the shelf life of biologics. Therefore, it is important to store biologics at the right temperature using standardized protocols.