Figures
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
Citation: (2018) PLoS Computational Biology Issue Image | Vol. 14(12) December 2018. PLoS Comput Biol 14(12): ev14.i12. https://doi.org/10.1371/image.pcbi.v14.i12
Published: December 31, 2018
Copyright: © 2018 Hay and Parthasarathy. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
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