Skip to main content
Advertisement
  • Loading metrics

PLoS Computational Biology Issue Image | Vol. 14(12) December 2018

Bacterium or noise?

Two-dimensional projections of three-dimensional light sheet fluorescence microscropy images of gut bacteria in larval zebrafish. The right half consists of images hand-labeled as bacteria, the left half as noise or non-bacterial objects. These and thousands of other datasets were used to train a convolutional neural network, which achieves human-level classfication accuracy.

Image Credit: Edouard A Hay and Raghuveer Parthasarathy, The University of Oregon

thumbnail
Bacterium or noise?

Two-dimensional projections of three-dimensional light sheet fluorescence microscropy images of gut bacteria in larval zebrafish. The right half consists of images hand-labeled as bacteria, the left half as noise or non-bacterial objects. These and thousands of other datasets were used to train a convolutional neural network, which achieves human-level classfication accuracy.

Image Credit: Edouard A Hay and Raghuveer Parthasarathy, The University of Oregon

https://doi.org/10.1371/image.pcbi.v14.i12.g001