Rotation equivariant and invariant neural networks for microscopy image analysis.

Journal: Bioinformatics (Oxford, England)
PMID:

Abstract

MOTIVATION: Neural networks have been widely used to analyze high-throughput microscopy images. However, the performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Highly relevant to the goal of automated cell phenotyping from microscopy image data is rotation invariance. Here we consider the application of two schemes for encoding rotation equivariance and invariance in a convolutional neural network, namely, the group-equivariant CNN (G-CNN), and a new architecture with simple, efficient conic convolution, for classifying microscopy images. We additionally integrate the 2D-discrete-Fourier transform (2D-DFT) as an effective means for encoding global rotational invariance. We call our new method the Conic Convolution and DFT Network (CFNet).

Authors

  • Benjamin Chidester
    Computational Biology Department, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA.
  • Tianming Zhou
    Toyota Technological Institute at Chicago, USA.
  • Minh N Do
    University of Illinois, Department of Electrical and Computer Engineering, Computational Imaging Group, Coordinated Science Laboratory, Urbana-Champaign, Illinois, United States.
  • Jian Ma