Classifying and segmenting microscopy images with deep multiple instance learning.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: High-content screening (HCS) technologies have enabled large scale imaging experiments for studying cell biology and for drug screening. These systems produce hundreds of thousands of microscopy images per day and their utility depends on automated image analysis. Recently, deep learning approaches that learn feature representations directly from pixel intensity values have dominated object recognition challenges. These tasks typically have a single centered object per image and existing models are not directly applicable to microscopy datasets. Here we develop an approach that combines deep convolutional neural networks (CNNs) with multiple instance learning (MIL) in order to classify and segment microscopy images using only whole image level annotations.

Authors

  • Oren Z Kraus
    Department of Electrical and Computer Engineering, University of Toronto, Toronto, M5S 2E4, Canada The Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, M5S 3E1, Canada.
  • Jimmy Lei Ba
    Department of Electrical and Computer Engineering, University of Toronto, Toronto, M5S 2E4, Canada.
  • Brendan J Frey
    Department of Electrical and Computer Engineering, University of Toronto, Toronto, Ontario M5S 3G4, Canada. Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, Ontario M5S 3E1, Canada. Program on Genetic Networks and Program on Neural Computation & Adaptive Perception, Canadian Institute for Advanced Research, Toronto, Ontario M5G 1Z8, Canada. Department of Computer Science, University of Toronto, Toronto, Ontario M5S 3G4, Canada. McLaughlin Centre, University of Toronto, Toronto, Ontario M5G 0A4, Canada. Department of Molecular Genetics, University of Toronto, Toronto, Ontario M5S 1A8, Canada. eScience Group, Microsoft Research, Redmond, WA 98052, USA. frey@psi.toronto.edu.