Using R‐Based Image Analysis to Quantify Rusts on Perennial Ryegrass

Abstract

Core Ideas An automated open‐source analysis system was developed to rate crown and stem rust. The system was validated against manual measurements and visual rater ability. Consistency in rater (n = 9) ability was excellent for crown rust and fair to good for stem rust. Agreement in rater scores for individual images was low and showed high levels of variation. The automated system can replace visual rating of crown rust in the field but not stem rust. Crown and stem rust are major diseases of perennial ryegrass (Lolium perenne L.). Plant breeders and pathologists often rate rust severity in the field using the modified Cobb scale, but this method is subjective and labor intensive. A novel, open‐source system using ImageJ and R was developed to quantify pustule number and area using digital images collected from spaced plants in the field. The computer‐processing pipeline included development of training data for prediction of pixel identity using random forest and noise reduction spatial processing. Raters and the computer scored rust severity on plant images of varying complexity including whole‐plant (WP), five‐leaf (FL), and single‐leaf (SL) image series. Computer accuracy was determined using the SL, while the FL series gave insight into the true value of WP severity. Rater ability was assessed using a panel of nine scientists with varying levels of disease rating experience. Results showed rater perceptions of crown rust severity were very consistent across images, but agreement on severity values for a given image were low. Rater consistency for stem rust severity was low and FL scores were not strongly correlated with WP scores (r = 0.36, P = 0.03), indicating low rater accuracy. The computer‐processing pipeline was able to accurately discriminate, count, and quantify crown and stem rust pustules on leaf samples. Correlations between computer and the median rater score for crown rust were excellent (r > 0.90, P < 0.001) for all image series. Similar to raters, there was a lack of correlation between WP and FL series (r = 0.20, not significant) indicating that this technique is limited to leaf or stem samples for stem rust and not applicable to WP. However, the computer‐processing pipeline shows promise in replacing visual rating of WP for crown rust.

Predictive ability of perennial ryegrass spaced‐plant nurseries for turfgrass and seed production swards in Minnesota

“…The results for crown rust showed that computer‐estimated severity was much lower than visual severity, which corresponds to the findings of Heineck et al. (2019). Image analysis has several benefits over visual estimates, including lower employee skill level requirements and the permanent recording of digital phenotypes that can be analyzed at any time throughout the year (Bade & Carmona, 2011; Sherwood, Berg, Hoover, & Zeiders, 1983) with repeatable R scripts and training data that can be shared within and among research groups.…”

“…For instance, as plant density increased from three plants m −2 (SPN) to 5,000 plants m −2 (TGS), mean severity increased by more than 100‐fold from 0.01 to 1.6% rust pustule coverage of healthy tissue. These more conservative severity estimates in general may seem very small; however, the computer was trained to detect crown rust pustules, which excludes the necrotic or chlorotic leaf tissue that often inflate visual estimates (Heineck et al., 2019; Sherwood et al., 1983). Proliferation of disease severity such as crown rust as a result of plant density are axiomatic in epidemiology and are caused by increased inoculum load and moisture within the plant canopy (Burdon & Chilvers, 1982).…”

“…Images were used to quantify density, crown rust, and winter survival in each environment via a method described in detail by Heineck, McNish, Jungers, Gilbert, and Watkins (2019). Image analysis was done with ImageJ (Schneider et al, 2012) and R Version 3.6.0 (R Core Team, 2020).…”

The fungal endophyte Epichloë festucae var. lolii plays a limited role in mediating crown rust severity in perennial ryegrass

“…Visual ratings have long proven effective; however, data taken by several raters on the same experimental unit over time have been shown to be imprecise for several foliar pathogens including Puccinia spp. (Heineck, McNish, Jungers, Gilbert, & Watkins, 2019;Sherwood, Berg, Hoover, & Zeiders, 1983). Therefore, quantitative ratings using image analysis can be used to reinforce visual ratings in the field to provide more accurate insight into endophyte effects.…”

“…Quantification of rust severity was conducted using an automated system described by Heineck et al (2019) for both five-leaf samples and whole plants. Image analysis was done using ImageJ and R (Schneider, Rasband, & Eliceiri, 2012; Version 3.5.0; R Core Team, 2018).…”