Plantorganelle Hunter is an effective deep-learning-based method for plant organelle phenotyping in electron microscopy.

Feng, X; Yu, Z; Fang, H; Jiang, H; Yang, G; Chen, L; Zhou, X; Hu, B; Qin, C; Hu, G; Xing, G; Zhao, B; Shi, Y; Guo, J; Liu, F; Han, B; Zechmann, B; He, Y; Liu, F

Plantorganelle Hunter is an effective deep-learning-based method for plant organelle phenotyping in electron microscopy.

Feng, X Yu, Z Fang, H Jiang, H Yang, G Chen, L Zhou, X Hu, B Qin, C Hu, G Xing, G Zhao, B Shi, Y Guo, J Liu, F

Han, B Zechmann, B He, Y Liu, F

Permalink

Publisher:: NATURE PORTFOLIO
Publication Type:: Journal Article
Citation:: Nat Plants, 2023, 9, (10), pp. 1760-1775
Issue Date:: 2023-10

Closed Access

	Filename	Description	Size
	22567340_13991193440005671.pdf	Published version	4.69 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Feng, X
dc.contributor.author	Yu, Z
dc.contributor.author	Fang, H
dc.contributor.author	Jiang, H
dc.contributor.author	Yang, G
dc.contributor.author	Chen, L
dc.contributor.author	Zhou, X
dc.contributor.author	Hu, B
dc.contributor.author	Qin, C
dc.contributor.author	Hu, G
dc.contributor.author	Xing, G
dc.contributor.author	Zhao, B
dc.contributor.author	Shi, Y
dc.contributor.author	Guo, J
dc.contributor.author	Liu, F https://orcid.org/0000-0002-5005-9129
dc.contributor.author	Han, B
dc.contributor.author	Zechmann, B
dc.contributor.author	He, Y
dc.contributor.author	Liu, F https://orcid.org/0000-0002-5005-9129
dc.date.accessioned	2024-05-13T03:23:59Z
dc.date.available	2023-08-25
dc.date.available	2024-05-13T03:23:59Z
dc.date.issued	2023-10
dc.identifier.citation	Nat Plants, 2023, 9, (10), pp. 1760-1775
dc.identifier.issn	2055-0278
dc.identifier.issn	2055-0278
dc.identifier.uri	http://hdl.handle.net/10453/178888
dc.description.abstract	Accurate delineation of plant cell organelles from electron microscope images is essential for understanding subcellular behaviour and function. Here we develop a deep-learning pipeline, called the organelle segmentation network (OrgSegNet), for pixel-wise segmentation to identify chloroplasts, mitochondria, nuclei and vacuoles. OrgSegNet was evaluated on a large manually annotated dataset collected from 19 plant species and achieved state-of-the-art segmentation performance. We defined three digital traits (shape complexity, electron density and cross-sectional area) to track the quantitative features of individual organelles in 2D images and released an open-source web tool called Plantorganelle Hunter for quantitatively profiling subcellular morphology. In addition, the automatic segmentation method was successfully applied to a serial-sectioning scanning microscope technique to create a 3D cell model that offers unique views of the morphology and distribution of these organelles. The functionalities of Plantorganelle Hunter can be easily operated, which will increase efficiency and productivity for the plant science community, and enhance understanding of subcellular biology.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	NATURE PORTFOLIO
dc.relation.ispartof	Nat Plants
dc.relation.isbasedon	10.1038/s41477-023-01527-5
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0607 Plant Biology, 0703 Crop and Pasture Production
dc.subject.classification	3103 Ecology
dc.subject.classification	3108 Plant biology
dc.subject.mesh	Deep Learning
dc.subject.mesh	Microscopy, Electron
dc.subject.mesh	Cell Nucleus
dc.subject.mesh	Mitochondria
dc.subject.mesh	Chloroplasts
dc.subject.mesh	Cell Nucleus
dc.subject.mesh	Mitochondria
dc.subject.mesh	Chloroplasts
dc.subject.mesh	Microscopy, Electron
dc.subject.mesh	Deep Learning
dc.subject.mesh	Deep Learning
dc.subject.mesh	Microscopy, Electron
dc.subject.mesh	Cell Nucleus
dc.subject.mesh	Mitochondria
dc.subject.mesh	Chloroplasts
dc.title	Plantorganelle Hunter is an effective deep-learning-based method for plant organelle phenotyping in electron microscopy.
dc.type	Journal Article
utslib.citation.volume	9
utslib.location.activity	England
utslib.for	0607 Plant Biology
utslib.for	0703 Crop and Pasture Production
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2024-05-13T03:23:56Z
pubs.issue	10
pubs.publication-status	Published
pubs.volume	9
utslib.citation.issue	10

Abstract:

Accurate delineation of plant cell organelles from electron microscope images is essential for understanding subcellular behaviour and function. Here we develop a deep-learning pipeline, called the organelle segmentation network (OrgSegNet), for pixel-wise segmentation to identify chloroplasts, mitochondria, nuclei and vacuoles. OrgSegNet was evaluated on a large manually annotated dataset collected from 19 plant species and achieved state-of-the-art segmentation performance. We defined three digital traits (shape complexity, electron density and cross-sectional area) to track the quantitative features of individual organelles in 2D images and released an open-source web tool called Plantorganelle Hunter for quantitatively profiling subcellular morphology. In addition, the automatic segmentation method was successfully applied to a serial-sectioning scanning microscope technique to create a 3D cell model that offers unique views of the morphology and distribution of these organelles. The functionalities of Plantorganelle Hunter can be easily operated, which will increase efficiency and productivity for the plant science community, and enhance understanding of subcellular biology.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/178888