bioRxiv · 10.1101/2020.01.05.895003
Dense cellular segmentation using 2D-3D neural network ensembles for electron microscopy
Abstract
Cell biologists can now build 3D models from segmentations of electron microscopy (EM) images, but accurate manual segmentation of densely-packed organelles across gigavoxel image volumes is infeasible. Here, we introduce 2D-3D neural network ensembles that produce dense cellular segmentations at scale, with accuracy levels that outperform baseline methods and approach those of human annotators.
Source connections
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Guay, M., Emam, Z., Anderson, A., Aronova, M., Leapman, R. D.. 2020-01-06. Dense cellular segmentation using 2D-3D neural network ensembles for electron microscopy. https://doi.org/10.1101/2020.01.05.895003
Cite the original work for its findings. Save a collection to share your selection of sources.