Mimicry embedding for advanced neuralnetwork training of 3D biomedical micrographs
Yakimovich, A.; Huttunen, M.; Samolej, J.; Clough, B.; Yoshida, N.; Mostowy, S.; Frickel, E.; Mercer, J.
Show 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 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.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- The SARS-CoV-2 nucleocapsid protein associates with the replication organelles before viral assembly at the Golgi/ERGIC and lysosome-mediated egress 95%
- Tunneling nanotubes provide a novel route for SARS-CoV-2 spreading between permissive cells and to non-permissive neuronal cells. 94%
- Temporal control of the integrated stress response by a stochastic molecular switch 94%
Similar papers in this journal
- A statistical framework for quantifying the nuclear export rate of influenza viral mRNAs. 95%
- In vivo imaging of retrovirus infection reveals a role for Siglec-1/CD169 in multiple routes of transmission 94%
- SARS-CoV-2 mechanistic correlates of protection: insight from modelling response to vaccines 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.