AutoRoot: open-source software employing a novel image analysis approach to support fully-automated plant phenotyping

BackgroundComputer-based phenotyping of plants has risen in importance in recent years. Whilst much software has been written to aid phenotyping using image analysis, to date the vast majority has been only semi-automatic. However, such interaction is not desirable in high throughput approaches. Here, we present a system designed to analyse plant images in a completely automated manner, allowing genuine high throughput measurement of root traits. To do this we introduce a new set of proxy traits.ResultsWe test the system on a new, automated image capture system, the Microphenotron, which is able to image many 1000s of roots/h. A simple experiment is presented, treating the plants with differing chemical conditions to produce different phenotypes. The automated imaging setup and the new software tool was used to measure proxy traits in each well. A correlation matrix was calculated across automated and manual measures, as a validation. Some particular proxy measures are very highly correlated with the manual measures (e.g. proxy length to manual length, r2 > 0.9). This suggests that while the automated measures are not directly equivalent to classic manual measures, they can be used to indicate phenotypic differences (hence the term, proxy). In addition, the raw discriminative power of the new proxy traits was examined. Principal component analysis was calculated across all proxy measures over two phenotypically-different groups of plants. Many of the proxy traits can be used to separate the data in the two conditions.ConclusionThe new proxy traits proposed tend to correlate well with equivalent manual measures, where these exist. Additionally, the new measures display strong discriminative power. It is suggested that for particular phenotypic differences, different traits will be relevant, and not all will have meaningful manual equivalent measures. However, approaches such as PCA can be used to interrogate the resulting data to identify differences between datasets. Select images can then be carefully manually inspected if the nature of the precise differences is required. We suggest such flexible measurement approaches are necessary for fully automated, high throughput systems such as the Microphenotron.

[1]  Michael P. Pound,et al.  What lies beneath: underlying assumptions in bioimage analysis. , 2012, Trends in plant science.

[2]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[3]  S. Cutler,et al.  Glutamate signalling via a MEKK1 kinase-dependent pathway induces changes in Arabidopsis root architecture , 2013, The Plant journal : for cell and molecular biology.

[4]  A. Walter,et al.  Plant phenotyping: from bean weighing to image analysis , 2015, Plant Methods.

[5]  Malia A. Gehan,et al.  Lights, camera, action: high-throughput plant phenotyping is ready for a close-up. , 2015, Current opinion in plant biology.

[6]  O. E. Krips,et al.  High-throughput phenotyping of plant resistance to aphids by automated video tracking , 2015, Plant Methods.

[7]  Ashutosh Kumar Singh,et al.  Machine Learning for High-Throughput Stress Phenotyping in Plants. , 2016, Trends in plant science.

[8]  Pankaj Kumar,et al.  RootGraph: a graphic optimization tool for automated image analysis of plant roots , 2015, Journal of experimental botany.

[9]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[10]  Loïc Pagès,et al.  A Novel Image-Analysis Toolbox Enabling Quantitative Analysis of Root System Architecture1[W][OA] , 2011, Plant Physiology.

[11]  H. Scharr,et al.  HyperART: non-invasive quantification of leaf traits using hyperspectral absorption-reflectance-transmittance imaging , 2015, Plant Methods.

[12]  Patrick Armengaud,et al.  EZ-Rhizo software , 2009, Plant signaling & behavior.

[13]  Hanno Scharr,et al.  Machine Learning for Plant Phenotyping Needs Image Processing. , 2016, Trends in plant science.

[14]  Michael P. Pound,et al.  Phenotyping pipeline reveals major seedling root growth QTL in hexaploid wheat , 2015, Journal of experimental botany.

[15]  Tony P. Pridmore,et al.  Deep machine learning provides state-of-the-art performance in image-based plant phenotyping , 2016, bioRxiv.

[16]  D. Inzé,et al.  Cell to whole-plant phenotyping: the best is yet to come. , 2013, Trends in plant science.

[17]  Michael P. Pound,et al.  RootNav: Navigating Images of Complex Root Architectures1[C][W] , 2013, Plant Physiology.

[18]  Paul R Zurek,et al.  GiA Roots: software for the high throughput analysis of plant root system architecture , 2012, BMC Plant Biology.

[19]  J. Lynch,et al.  Shovelomics: high throughput phenotyping of maize (Zea mays L.) root architecture in the field , 2011, Plant and Soil.

[20]  Tony Pridmore,et al.  High-Throughput Quantification of Root Growth Using a Novel Image-Analysis Tool1[C][W] , 2009, Plant Physiology.

[21]  Pedro J. Navarro,et al.  Machine Learning and Computer Vision System for Phenotype Data Acquisition and Analysis in Plants , 2016, Sensors.

[22]  B. S. Manjunath,et al.  The iPlant Collaborative: Cyberinfrastructure for Plant Biology , 2011, Front. Plant Sci..

[23]  R. E. Sharp,et al.  Growth of Arabidopsis thaliana seedlings under water deficit studied by control of water potential in nutrient-agar media. , 2000, Journal of experimental botany.

[24]  Hanno Scharr,et al.  Leaf segmentation in plant phenotyping: a collation study , 2016, Machine Vision and Applications.

[25]  Michael P. Pound,et al.  The Microphenotron: a robotic miniaturized plant phenotyping platform with diverse applications in chemical biology , 2017, Plant Methods.