465-Ichita-VirtualStainPlant
Author reviewedImage datasets for training and evaluating virtual staining of plant cell structures and cell viability classification
Project ID
465-Ichita-VirtualStainPlant
Project SID
465
Title
Image datasets for training and evaluating virtual staining of plant cell structures and cell viability classification
Description
The applicability of a deep learning model for the virtual staining of plant cell structures using bright-field microscopy was investigated. The training dataset consisted of microscopy images of tobacco BY-2 cells with the plasma membrane stained with the fluorescent dye PlasMem Bright Green and the cell nucleus labeled with Histone-red fluorescent protein. The trained models successfully detected the expansion of cell nuclei upon aphidicolin treatment and a decrease in the cell aspect ratio upon propyzamide treatment, demonstrating its utility in cell morphometry. The model also accurately documented the shape of Arabidopsis pavement cells in both wild type and the bpp125 triple mutant, which has an altered pavement cell phenotype. Metrics such as cell area, circularity, and solidity obtained from virtual staining analyses were highly correlated with those obtained by manual measurements of cell features from microscopy images. Furthermore, the versatility of virtual staining was highlighted by its application to track chloroplast movement in Egeria densa. The method was also effective for classifying live and dead BY-2 cells using texture-based machine learning, suggesting that virtual staining can be applied beyond typical segmentation tasks. Although this method still has some limitations, its non-invasive nature and efficiency make it highly suitable for label-free, dynamic, and high-throughput analyses in quantitative plant cell biology.
Submission Date
2025-08-19
Opened Date
-
Release Date
2026-09-30
Update Date
-
Kind
Image datasets
License
Project URL
-
Project DOI
Metadata Version
-
Template Version
3.0.3
Funding Information
This work was supported by a grant from the Japan Science and Technology Agency (CREST; JPMJCR2121) to Takumi Higaki.
Total
14 files / 14.9 GB
Image datasets
zipped 7 files / 5.7 GB, raw image 7 files / 9.3 GB, total 14 files / 14.9 GB
Quantitative datasets
zipped 0 files / 0 bytes, raw bdml 0 files / 0 bytes, total 0 files / 0 bytes
Biosample
Organism
Nicotiana tabacum
(
NCBITaxon:4097
)
Egeria densa
(
NCBITaxon:55453
)
Strain
-
Cell
-
Cell line
TBY-2 cell
(
BTO:0001972
)
MeSH
Ontology
Anatomical Entity
leaf
(
PO:0025034
)
UBERON
-
Biological Process
-
Cellular Component
plasma membrane
(
GO:0005886
)
nucleus
(
GO:0005634
)
chloroplast
(
GO:0009507
)
vacuole
(
GO:0005773
)
Molecular Function
-
Medical Subject Headings
Imaging Method
Method involved in biological imaging
spinning disk confocal microscopy
(
FBbi:00000253
)
Transmitted bright-field microscopy
Paper(s)
People
Contact
Takumi Higaki
Kumamoto University
Graduate School of Science and Technology
-
Imaging dataset contributor
Manami Ichita (Kumamoto University)
Haruna Yamamichi (Kumamoto University)
Takumi Higaki (Kumamoto University)
Quantitative dataset contributor
-
Image datasets
7
Quantitative datasets
0
Dataset List
Thumbnail
Dataset
Organism
Kind / Links
Bright-field and confocal images of transgenic tobacco BY-2 cells with Histone-RFP and PlasMem Bright Green staining
Bright-field and chloroplast autofluorescence images of Egeria densa
Bright-field images of live tobacco BY-2 cells
Bright-field images of dead tobacco BY-2 cells
Virtually stained images of live tobacco BY-2 cells
Virtually stained images of dead tobacco BY-2 cells
Bright-field and confocal images of wild-type tobacco BY-2 cells stained with BCECF for vacuolar lumen visualization