Deep learning to predict microscope images.

Journal: Nature methods
Published Date:

Abstract

A species of neural network first described in 2015 can be trained to translate between images of the same field of view acquired by different modalities. Trained networks can use information inherent in grayscale images of cells to predict fluorescent signals.

Authors

  • Roger Brent
    Division of Basic Sciences, Fred Hutchinson Cancer Research Center, Seattle, WA, USA. rbrent@fhcrc.org.
  • Laura Boucheron
    Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA.