Rxivist logo

Mimicry embedding for advanced neural network training of 3D biomedical micrographs

By Artur Yakimovich, Moona Huttunen, Jerzy Samolej, Barbara Clough, Nagisa Yoshida, Serge Mostowy, Eva Frickel, Jason Mercer

Posted 28 Oct 2019
bioRxiv DOI: 10.1101/820076

The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified datasets for rapid network evolution. Here we present a novel “mimicry embedding” strategy for rapid application of neural network architecture-based analysis of biomedical imaging datasets. Embedding of a novel biological dataset, such that it mimics a verified dataset, enables efficient deep learning and seamless architecture switching. We apply this strategy across various microbiological phenotypes; from super-resolved viruses to in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of three-dimensional microscopy datasets. The results suggest that transfer learning from pre-trained network data may be a powerful general strategy for analysis of heterogeneous biomedical imaging datasets.

Download data

  • Downloaded 413 times
  • Download rankings, all-time:
    • Site-wide: 38,865 out of 88,847
    • In bioinformatics: 4,766 out of 8,398
  • Year to date:
    • Site-wide: 20,150 out of 88,847
  • Since beginning of last month:
    • Site-wide: 31,299 out of 88,847

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide


Sign up for the Rxivist weekly newsletter! (Click here for more details.)