Dense cellular segmentation for EM using 2D–3D neural network ensembles
release_4hxhcwt2lrefxeddi2libml7mq
by
Matthew D. Guay, Zeyad A. S. Emam, Adam B. Anderson, Maria A. Aronova, Irina D. Pokrovskaya, Brian Storrie, Richard D. Leapman
2021 Volume 11, Issue 1, p2561
Abstract
<jats:title>Abstract</jats:title>Biologists who use electron microscopy (EM) images to build nanoscale 3D models of whole cells and their organelles have historically been limited to small numbers of cells and cellular features due to constraints in imaging and analysis. This has been a major factor limiting insight into the complex variability of cellular environments. Modern EM can produce gigavoxel image volumes containing large numbers of cells, but accurate manual segmentation of image features is slow and limits the creation of cell models. Segmentation algorithms based on convolutional neural networks can process large volumes quickly, but achieving EM task accuracy goals often challenges current techniques. Here, we define <jats:italic>dense cellular segmentation</jats:italic> as a multiclass semantic segmentation task for modeling cells and large numbers of their organelles, and give an example in human blood platelets. We present an algorithm using novel hybrid 2D–3D segmentation networks to produce dense cellular segmentations with accuracy levels that outperform baseline methods and approach those of human annotators. To our knowledge, this work represents the first published approach to automating the creation of cell models with this level of structural detail.
In application/xml+jats
format
Archived Files and Locations
application/pdf 9.0 MB
file_s2yazafdhfar7fgihsbswilbxi
|
www.nature.com (publisher) web.archive.org (webarchive) |
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar