Computer Vision for High-Throughput Quantitative Phenotyping: A Case Study of Grapevine Downy Mildew Sporulation and Leaf Trichomes

Abstract

Quantitative phenotyping of downy mildew sporulation is frequently used in plant breeding and genetic studies, as well as in studies focused on pathogen biology such as chemical efficacy trials. In these scenarios, phenotyping a large number of genotypes or treatments can be advantageous but is often limited by time and cost. We present a novel computational pipeline dedicated to estimating the percent area of downy mildew sporulation from images of inoculated grapevine leaf discs in a manner that is time and cost efficient. The pipeline was tested on images from leaf disc assay experiments involving two F grapevine families, one that had glabrous leaves (Vitis rupestris B38 × 'Horizon' [RH]) and another that had leaf trichomes (Horizon × V. cinerea B9 [HC]). Correlations between computer vision and manual visual ratings reached 0.89 in the RH family and 0.43 in the HC family. Additionally, we were able to use the computer vision system prior to sporulation to measure the percent leaf trichome area. We estimate that an experienced rater scoring sporulation would spend at least 90% less time using the computer vision system compared with the manual visual method. This will allow more treatments to be phenotyped in order to better understand the genetic architecture of downy mildew resistance and of leaf trichome density. We anticipate that this computer vision system will find applications in other pathosystems or traits where responses can be imaged with sufficient contrast from the background.

A High-Throughput Phenotyping System Using Machine Vision to Quantify Severity of Grapevine Powdery Mildew

“…The goal of the system is to have automated scoring that is highly correlated with human observers assessing the severity of infection. The outcome was much better than correlations previously obtained (r = 0.43 and 0.80) in a leaf disk-based computer vision system using a smartphone and pixel counting to quantify downy mildew caused by Plasmopara viticola [2] and similar (r = 0.94) to a flatbed scanner and pixel counting used to quantify Septoria tritici blotch caused by Zymoseptoria tritici [3]. The agreement between experts and the APS reflects the amount of training set classifications provided by each; experts supplying more training data had higher agreement with the APS.…”

Single and multiple phenotype QTL analyses of downy mildew resistance in interspecific grapevines

“…Infection on grapevine leaves can be detected by observing sporulation or host necrosis, which on resistant vines is often associated with a hypersensitive response (HR) (Bellin et al 2009 ; Buonassisi et al 2017 ). Sporulation can be quantified either manually using human vision or by computer vision algorithms (Divilov et al 2017 ). Research in identifying downy mildew resistance quantitative trait loci (QTL) in grapevine has focused on disease phenotypes, e.g., sporulation and HR, but physical barriers produced by a plant can also play a role in the prevention of disease.…”

Identification of Lipid Markers of Plasmopara viticola Infection in Grapevine Using a Non-targeted Metabolomic Approach

“…The accurate quantification of pathogen development is important for a better understanding of plant-pathogen interactions. In the case of P. viticola , methods based on cell counting or image analysis are routinely used to quantify sporulation, especially as a phenotyping tool to characterize resistance sources in the Vitis genus (Peressotti et al, 2011 ; Divilov et al, 2017 ). Our differential metabolomic approach has led to the characterization of lipids, which are abundant in the sporangia of P. viticola and not detected in healthy grapevine leaf tissues.…”

“…Assessment of resistance to grapevine downy mildew has been traditionally performed by visually scoring disease symptoms or by measuring sporulation using a cell counter (Bellin et al, 2009 ). More recently, high-throughput imaging-based methods to quantify sporulation have been developed (Peressotti et al, 2011 ; Divilov et al, 2017 ). Although such high-throughput methods are very useful to screen breeding populations, they do not allow monitoring of disease progression.…”