Cargando…

Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics

Automating the three-dimensional (3D) segmentation of stomatal guard cells and other confocal microscopy data is extremely challenging due to hardware limitations, hard-to-localize regions, and limited optical resolution. We present a memory-efficient, attention-based, one-stage segmentation neural...

Descripción completa

Detalles Bibliográficos
Autores principales: Davaasuren, Dolzodmaa, Chen, Yintong, Jaafar, Leila, Marshall, Rayna, Dunham, Angelica L., Anderson, Charles T., Wang, James Z.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9782259/
https://www.ncbi.nlm.nih.gov/pubmed/36569557
http://dx.doi.org/10.1016/j.patter.2022.100627
_version_ 1784857299794264064
author Davaasuren, Dolzodmaa
Chen, Yintong
Jaafar, Leila
Marshall, Rayna
Dunham, Angelica L.
Anderson, Charles T.
Wang, James Z.
author_facet Davaasuren, Dolzodmaa
Chen, Yintong
Jaafar, Leila
Marshall, Rayna
Dunham, Angelica L.
Anderson, Charles T.
Wang, James Z.
author_sort Davaasuren, Dolzodmaa
collection PubMed
description Automating the three-dimensional (3D) segmentation of stomatal guard cells and other confocal microscopy data is extremely challenging due to hardware limitations, hard-to-localize regions, and limited optical resolution. We present a memory-efficient, attention-based, one-stage segmentation neural network for 3D images of stomatal guard cells. Our model is trained end to end and achieved expert-level accuracy while leveraging only eight human-labeled volume images. As a proof of concept, we applied our model to 3D confocal data from a cell ablation experiment that tests the “polar stiffening” model of stomatal biomechanics. The resulting data allow us to refine this polar stiffening model. This work presents a comprehensive, automated, computer-based volumetric analysis of fluorescent guard cell images. We anticipate that our model will allow biologists to rapidly test cell mechanics and dynamics and help them identify plants that more efficiently use water, a major limiting factor in global agricultural production and an area of critical concern during climate change.
format Online
Article
Text
id pubmed-9782259
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-97822592022-12-24 Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics Davaasuren, Dolzodmaa Chen, Yintong Jaafar, Leila Marshall, Rayna Dunham, Angelica L. Anderson, Charles T. Wang, James Z. Patterns (N Y) Article Automating the three-dimensional (3D) segmentation of stomatal guard cells and other confocal microscopy data is extremely challenging due to hardware limitations, hard-to-localize regions, and limited optical resolution. We present a memory-efficient, attention-based, one-stage segmentation neural network for 3D images of stomatal guard cells. Our model is trained end to end and achieved expert-level accuracy while leveraging only eight human-labeled volume images. As a proof of concept, we applied our model to 3D confocal data from a cell ablation experiment that tests the “polar stiffening” model of stomatal biomechanics. The resulting data allow us to refine this polar stiffening model. This work presents a comprehensive, automated, computer-based volumetric analysis of fluorescent guard cell images. We anticipate that our model will allow biologists to rapidly test cell mechanics and dynamics and help them identify plants that more efficiently use water, a major limiting factor in global agricultural production and an area of critical concern during climate change. Elsevier 2022-11-09 /pmc/articles/PMC9782259/ /pubmed/36569557 http://dx.doi.org/10.1016/j.patter.2022.100627 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Article
Davaasuren, Dolzodmaa
Chen, Yintong
Jaafar, Leila
Marshall, Rayna
Dunham, Angelica L.
Anderson, Charles T.
Wang, James Z.
Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics
title Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics
title_full Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics
title_fullStr Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics
title_full_unstemmed Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics
title_short Automated 3D segmentation of guard cells enables volumetric analysis of stomatal biomechanics
title_sort automated 3d segmentation of guard cells enables volumetric analysis of stomatal biomechanics
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9782259/
https://www.ncbi.nlm.nih.gov/pubmed/36569557
http://dx.doi.org/10.1016/j.patter.2022.100627
work_keys_str_mv AT davaasurendolzodmaa automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics
AT chenyintong automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics
AT jaafarleila automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics
AT marshallrayna automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics
AT dunhamangelical automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics
AT andersoncharlest automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics
AT wangjamesz automated3dsegmentationofguardcellsenablesvolumetricanalysisofstomatalbiomechanics