PUBLICATION
Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection
- Authors
- Yakimovich, A., Huttunen, M., Samolej, J., Clough, B., Yoshida, N., Mostowy, S., Frickel, E.M., Mercer, J.
- ID
- ZDB-PUB-201002-5
- Date
- 2020
- Source
- mSphere 5(5): (Journal)
- Registered Authors
- Mostowy, Serge
- Keywords
- Toxoplasma gondii, capsule networks, deep learning, superresolution microscopy, transfer learning, vaccinia virus, zebrafish
- MeSH Terms
-
- Animals
- Artificial Intelligence
- Deep Learning*
- Host-Pathogen Interactions*
- Image Processing, Computer-Assisted/methods*
- Microscopy/methods
- Neural Networks, Computer*
- Toxoplasma/pathogenicity
- Vaccinia virus/pathogenicity
- Zebrafish
- PubMed
- 32907956 Full text @ mSphere
Citation
Yakimovich, A., Huttunen, M., Samolej, J., Clough, B., Yoshida, N., Mostowy, S., Frickel, E.M., Mercer, J. (2020) Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection. mSphere. 5(5):.
Abstract
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 data sets for rapid network evolution. Here, we present a novel strategy, termed "mimicry embedding," for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets.IMPORTANCE In biology, the use of deep neural networks (DNNs) for analysis of pathogen infection is hampered by a lack of large verified data sets needed for rapid network evolution. Artificial neural networks detect handwritten digits with high precision thanks to large data sets, such as MNIST, that allow nearly unlimited training. Here, we developed a novel strategy we call mimicry embedding, which allows artificial intelligence (AI)-based analysis of variable pathogen-host data sets. We show that deep learning can be used to detect and classify single pathogens based on small differences.
Genes / Markers
Expression
Phenotype
Mutations / Transgenics
Human Disease / Model
Sequence Targeting Reagents
Fish
Orthology
Engineered Foreign Genes
Mapping