Cargando…

Local shape descriptors for neuron segmentation

We present an auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of local shape descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The sh...

Descripción completa

Detalles Bibliográficos
Autores principales: Sheridan, Arlo, Nguyen, Tri M., Deb, Diptodip, Lee, Wei-Chung Allen, Saalfeld, Stephan, Turaga, Srinivas C., Manor, Uri, Funke, Jan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group US 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9911350/
https://www.ncbi.nlm.nih.gov/pubmed/36585455
http://dx.doi.org/10.1038/s41592-022-01711-z
_version_ 1784884974857486336
author Sheridan, Arlo
Nguyen, Tri M.
Deb, Diptodip
Lee, Wei-Chung Allen
Saalfeld, Stephan
Turaga, Srinivas C.
Manor, Uri
Funke, Jan
author_facet Sheridan, Arlo
Nguyen, Tri M.
Deb, Diptodip
Lee, Wei-Chung Allen
Saalfeld, Stephan
Turaga, Srinivas C.
Manor, Uri
Funke, Jan
author_sort Sheridan, Arlo
collection PubMed
description We present an auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of local shape descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a study comparing several existing methods across various specimen, imaging techniques, and resolutions, auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinity-based segmentation methods to be on par with the current state of the art for neuron segmentation (flood-filling networks), while being two orders of magnitudes more efficient—a critical requirement for the processing of future petabyte-sized datasets.
format Online
Article
Text
id pubmed-9911350
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Nature Publishing Group US
record_format MEDLINE/PubMed
spelling pubmed-99113502023-02-11 Local shape descriptors for neuron segmentation Sheridan, Arlo Nguyen, Tri M. Deb, Diptodip Lee, Wei-Chung Allen Saalfeld, Stephan Turaga, Srinivas C. Manor, Uri Funke, Jan Nat Methods Article We present an auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of local shape descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a study comparing several existing methods across various specimen, imaging techniques, and resolutions, auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinity-based segmentation methods to be on par with the current state of the art for neuron segmentation (flood-filling networks), while being two orders of magnitudes more efficient—a critical requirement for the processing of future petabyte-sized datasets. Nature Publishing Group US 2022-12-30 2023 /pmc/articles/PMC9911350/ /pubmed/36585455 http://dx.doi.org/10.1038/s41592-022-01711-z Text en © The Author(s) 2022 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) .
spellingShingle Article
Sheridan, Arlo
Nguyen, Tri M.
Deb, Diptodip
Lee, Wei-Chung Allen
Saalfeld, Stephan
Turaga, Srinivas C.
Manor, Uri
Funke, Jan
Local shape descriptors for neuron segmentation
title Local shape descriptors for neuron segmentation
title_full Local shape descriptors for neuron segmentation
title_fullStr Local shape descriptors for neuron segmentation
title_full_unstemmed Local shape descriptors for neuron segmentation
title_short Local shape descriptors for neuron segmentation
title_sort local shape descriptors for neuron segmentation
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9911350/
https://www.ncbi.nlm.nih.gov/pubmed/36585455
http://dx.doi.org/10.1038/s41592-022-01711-z
work_keys_str_mv AT sheridanarlo localshapedescriptorsforneuronsegmentation
AT nguyentrim localshapedescriptorsforneuronsegmentation
AT debdiptodip localshapedescriptorsforneuronsegmentation
AT leeweichungallen localshapedescriptorsforneuronsegmentation
AT saalfeldstephan localshapedescriptorsforneuronsegmentation
AT turagasrinivasc localshapedescriptorsforneuronsegmentation
AT manoruri localshapedescriptorsforneuronsegmentation
AT funkejan localshapedescriptorsforneuronsegmentation