DeepXScope: Segmenting Microscopy Images with a Deep Neural Network

Saponaro, Philip; Treible, Wayne; Kolagunda, Abhishek; Chaya, Timothy; Caplan, Jeffrey; Kambhamettu, Chandra; Wisser, Randall J.

doi:10.1109/cvprw.2017.117

Cited by 13 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pipeline represents a valuable technical advance because previously published automatic stomatal detection and counting algorithms: (1) used data that were collected by slow and laborious methods (e.g., Aono et al, 2019 ; Bhugra et al, 2019 ; Sakoda et al, 2019 ); (2) were limited to detecting stomata and not pavement cells (e.g., Dittberner et al, 2018 ; Fetter et al, 2019 ; Li et al, 2019 ; Sakoda et al, 2019 ); (3) did not achieve the same accuracy (e.g., Duarte et al, 2017 ; Saponaro et al, 2017 ; Bourdais et al, 2019 ); or (4) were demonstrated to work only within the constrained variation of a limited sample set, which did not include demonstrated applicability for quantitative genetics (e.g., Aono et al, 2019 ; Fetter et al, 2019 ; Li et al, 2019 ). Although previous studies achieved these goals individually, combining these features resulted in a tool that could be applied to addressing knowledge gaps about the genetic architecture and trait relationships of epidermal cells in maize.…”

Section: Discussionmentioning

confidence: 99%

“…There have been many attempts to address the phenotyping bottleneck for stomatal patterning through computer-aided image analysis. Classical image processing methods ( Omasa and Onoe, 1984 ; Liu et al, 2016 ; Duarte et al, 2017 ) and machine learning models have been applied ( Vialet-Chabrand and Brendel, 2014 ; Higaki et al, 2015 ; Jayakody et al, 2017 ; Saponaro et al, 2017 ; Dittberner et al, 2018 ; Toda et al, 2018 ; Aono et al, 2019 ; Bhugra et al, 2019 ; Fetter et al, 2019 ; Li et al, 2019 ; Sakoda et al, 2019 ). Although a number of these methods have been demonstrated to work within constrained image sets, none of them have been widely adopted, even within a single species.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optical topometry and machine learning to rapidly phenotype stomatal patterning traits for maize QTL mapping

et al. 2021

View full text Add to dashboard Cite

Stomata are adjustable pores on leaf surfaces that regulate the trade-off of CO2 uptake with water vapor loss, thus having critical roles in controlling photosynthetic carbon gain and plant water use. The lack of easy, rapid methods for phenotyping epidermal cell traits have limited discoveries about the genetic basis of stomatal patterning. A high-throughput epidermal cell phenotyping pipeline is presented here and used for quantitative trait loci (QTL) mapping in field-grown maize (Zea mays). The locations and sizes of stomatal complexes and pavement cells on images acquired by an optical topometer from mature leaves were automatically determined. Computer estimated stomatal complex density (SCD; R2 = 0.97) and stomatal complex area (SCA; R2 = 0.71) were strongly correlated with human measurements. Leaf gas exchange traits were genetically correlated with the dimensions and proportion of stomatal complexes (rg = 0.39 to 0.71) but did not correlate with SCD. Heritability of epidermal traits was moderate to high (h2 = 0.42-0.82) across two field seasons. 36 QTLs were consistently identified for a given trait in both years. 24 hotspots of overlapping QTLs for multiple traits were identified, with univariate versus multivariate single marker analysis providing evidence consistent with pleiotropy in multiple cases. Putative orthologs of genes known to regulate stomatal patterning in Arabidopsis (Arabidopsis thaliana) were located within some, but not all, of these regions. This study demonstrates how discovery of the genetic basis for stomatal patterning can be accelerated in maize, a C4 model species where these processes are poorly understood.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Optical topometry and machine learning to rapidly phenotype stomatal patterning traits for maize QTL mapping

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Although these methods demonstrate efficacy on their respective tasks, they rely on handcrafted and/or multistage processes. The use of Convolutional Neural Networks (CNNs) to detect stomatal attributes has recently increased in popularity (Jayakody et al ., 2017; Saponaro et al ., 2017; Toda et al ., 2018; Bhugra et al ., 2018, 2019; Falk et al ., 2019; Fetter et al ., 2019; Li et al ., 2019; Meeus et al ., 2020; Gibbs et al ., 2021). Convolutional Neural Networks enable a series of pertinent operations to be learnt from examples – acting as a data‐driven approximation of a sequence of computer vision operations.…”

Section: Introductionmentioning

confidence: 99%

StomaAI: an efficient and user‐friendly tool for measurement of stomatal pores and density using deep computer vision

et al. 2023

View full text Add to dashboard Cite

Summary Using microscopy to investigate stomatal behaviour is common in plant physiology research. Manual inspection and measurement of stomatal pore features is low throughput, relies upon expert knowledge to record stomatal features accurately, requires significant researcher time and investment, and can represent a significant bottleneck to research pipelines. To alleviate this, we introduce StomaAI (SAI): a reliable, user‐friendly and adaptable tool for stomatal pore and density measurements via the application of deep computer vision, which has been initially calibrated and deployed for the model plant Arabidopsis (dicot) and the crop plant barley (monocot grass). SAI is capable of producing measurements consistent with human experts and successfully reproduced conclusions of published datasets. SAI boosts the number of images that can be evaluated in a fraction of the time, so can obtain a more accurate representation of stomatal traits than is routine through manual measurement. An online demonstration of SAI is hosted at https://sai.aiml.team, and the full local application is publicly available for free on GitHub through https://github.com/xdynames/sai‐app.

show abstract

“…Although these methods demon- strate efficacy on their respective tasks, they rely on handcrafted and/or multi-stage processes. The use of Convolutional Neural Networks (CNNs) to detect stomatal attributes has recently increased in popularity [22][23][24][25][26][27][28][29] . CNNs enable a series of pertinent operations to be learnt from examples -acting as a data driven approximation of a sequence of computer vision operations.…”

Section: Introductionmentioning

confidence: 99%

SAI: Fast and automated quantification of stomatal parameters on microscope images

Sai

Bockman

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

Using microscopy to investigate stomatal behaviour is a common technique in plant physiology research. Manual inspection and measurement of stomatal features is a low throughput process in terms of time and human effort, which relies on expert knowledge to identify and measure stomata accurately. This process represents a significant bottleneck in research pipelines, adding significant researcher time to any project that requires it. To alleviate this, we introduce StomaAI (SAI): a reliable and user-friendly tool that measures stomata of the model plant Arabidopsis (dicot) and the crop plant barley (monocot grass) via the application of deep computer vision. We evaluated the reliability of predicted measurements: SAI is capable of producing measurements consistent with human experts and successfully reproduced conclusions of published datasets. Hence, SAI boosts the number of images that biologists can evaluate in a fraction of the time so is capable of obtaining more accurate and representative results.

show abstract

DeepXScope: Segmenting Microscopy Images with a Deep Neural Network

Cited by 13 publications

References 4 publications

Optical topometry and machine learning to rapidly phenotype stomatal patterning traits for maize QTL mapping

Optical topometry and machine learning to rapidly phenotype stomatal patterning traits for maize QTL mapping

StomaAI: an efficient and user‐friendly tool for measurement of stomatal pores and density using deep computer vision

SAI: Fast and automated quantification of stomatal parameters on microscope images

Contact Info

Product

Resources

About