Machine learning and feature analysis of the cortical microtubule organization of Arabidopsis cotyledon pavement cells

Yoshida, Daichi; Akita, Kae; Higaki, Takumi

doi:10.1007/s00709-022-01813-7

Cited by 7 publications

(7 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning-based image transformation was conducted using the 2-D segmentation function of the AIVIA image analysis software (DRVision, Bellevue, WA, USA) (Kikukawa et al 2021(Kikukawa et al , 2023. Measurements of cytoskeleton metrics were performed using the ImageJ plug-in 'LpxLineFeature' (Higaki 2017;Yoshida et al 2023). Statistical analyses were conducted using the R statistical analysis software (https://www.r-project.org/).…”

Section: Image Processing and Analysismentioning

confidence: 99%

Deep learning-based cytoskeleton segmentation for accurate high-throughput measurement of cytoskeleton density

Horiuchi,

Kamimura,

Hanaki

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Microscopic analyses of cytoskeleton organization are crucial for understanding various cellular activities, including cell proliferation and environmental responses in plants. Traditionally, assessments of cytoskeleton dynamics have been qualitative, relying on microscopy-assisted visual inspection. However, the transition to quantitative digital microscopy has introduced new technical challenges, with segmentation of cytoskeleton structures proving particularly demanding. In this study, we examined the utility of a deep learning-based segmentation method for accurate quantitative evaluation of cytoskeleton organization using confocal micrographs of the cortical microtubules in tobacco BY-2 cells. The results showed that, although conventional methods sufficed for measurement of cytoskeleton angles and parallelness, the deep learning-based method significantly improved the accuracy of density measurements. To assess the versatility of the method, we extended our analysis to physiologically significant models in the context of changes in cytoskeleton density, namely Arabidopsis thaliana guard cells and zygotes. The deep learning-based method successfully improved the accuracy of cytoskeleton density measurements for quantitative evaluations of physiological changes in both stomatal movement in guard cells and intracellular polarization in elongating zygotes, confirming its utility in these applications. The results demonstrate the effectiveness of deep learning-based segmentation in providing precise and high-throughput measurements of cytoskeleton density, and has the potential to automate and expedite analyses of large-scale image datasets.

show abstract

Section: Image Processing and Analysismentioning

confidence: 99%

Deep learning-based cytoskeleton segmentation for accurate high-throughput measurement of cytoskeleton density

Horiuchi,

Kamimura,

Hanaki

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…To determine which of the four types of intracellular structures contribute to the compartmentalization of the zygotes, we conducted a supervised learning analysis. A classification model to segregate the apical and basal subregions of the zygote was developed using the "random forest" method, an ensemble machine learning algorithm that enhances generalization capabilities by integrating multiple weak decision tree learners 18,19 . The classification accuracy was evaluated using the out-of-bag error rate, which is computed by classifying the training data as test data subsequent to the construction of a partial forest by aggregating groups of decision trees not involving the training data.…”

Section: Machine Learning Of Zygote Subcellular Regions Based On Intr...mentioning

confidence: 99%

“…Additionally, the random forest algorithm can estimate the importance of the variables used for classification 18 . Consequently, we investigated the relative importance of these four intracellular structures based on the mean decrease in the Gini coefficient 19 . Vacuolar membranes were identified as the most significant determinant for the classification of apical and basal regions (Fig.…”

Section: Machine Learning Of Zygote Subcellular Regions Based On Intr...mentioning

confidence: 99%

Comprehensive and quantitative analysis of intracellular structure polarization at the apical–basal axis in elongatingArabidopsiszygotes

Hiromoto,

Minamino,

Kikuchi

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

A comprehensive and quantitative evaluation of multiple intracellular structures or proteins is a promising approach to provide a deeper understanding of and new insights into cellular polarity. In this study, we developed an image analysis pipeline to obtain intensity profiles of fluorescent probes along the apical–basal axis in elongatingArabidopsis thalianazygotes based on two-photon live-cell imaging data. This technique showed the intracellular distribution of actin filaments, mitochondria, microtubules, and vacuolar membranes along the apical–basal axis in elongating zygotes from the onset of cell elongation to just before asymmetric cell division. Hierarchical cluster analysis of the quantitative data on intracellular distribution revealed that the zygote may be compartmentalized into two parts, with a boundary located 43.6% from the cell tip, immediately after fertilization. To explore the biological significance of this compartmentalization, we examined the positions of the asymmetric cell divisions from the dataset used in this distribution analysis. We found that the cell division plane was reproducibly inserted 20.5% from the cell tip. This position corresponded well with the midpoint of the compartmentalized apical region, suggesting a potential relationship between the zygote compartmentalization, which begins with cell elongation, and the position of the asymmetric cell division.

show abstract

“…Thus, a quantification of its morphological aspects is mandatory. The contribution by Yoshida et al ( 2023 ) explores a machine-learning strategy to quantify the organisation of cortical microtubules in epidermal pavement cells of the model plant Arabidopsis thaliana . These cells provide mechanic constraints to the expanding leaves and, thus, decide about their size and shape.…”

mentioning

confidence: 99%

“…More than 60 years after its discovery, the cytoskeleton has still retained many of its secrets. The contributions by Yoshida et al ( 2023 ) and Stick and Peter ( 2023 ) show how new technology can complement classic cell biological analysis to unveil new and hitherto unknown facets. These new facets are inspiring curiosity in the first place.…”

mentioning

confidence: 99%

Scrutinising the cytoskeleton

Nick

2023

Protoplasma

View full text Add to dashboard Cite

Machine learning and feature analysis of the cortical microtubule organization of Arabidopsis cotyledon pavement cells

Cited by 7 publications

References 42 publications

Deep learning-based cytoskeleton segmentation for accurate high-throughput measurement of cytoskeleton density

Deep learning-based cytoskeleton segmentation for accurate high-throughput measurement of cytoskeleton density

Comprehensive and quantitative analysis of intracellular structure polarization at the apical–basal axis in elongatingArabidopsiszygotes

Scrutinising the cytoskeleton

Contact Info

Product

Resources

About