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

Published in Scientific Reports by Springer Science and Business Media LLC.

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)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2021-01-28
Language   en ?
Container Metadata
Open Access Publication
In DOAJ
In Keepers Registry
ISSN-L:  2045-2322
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 34b8abee-9591-4662-8988-9498568ff6d2
API URL: JSON