Automated, image-based disease measurement for phenotyping resistance to soybean frogeye leaf spot

Abstract

Background Frogeye leaf spot is a disease of soybean, and there are limited sources of crop genetic resistance. Accurate quantification of resistance is necessary for the discovery of novel resistance sources, which can be accelerated by using a low-cost and easy-to-use image analysis system to phenotype the disease. The objective herein was to develop an automated image analysis phenotyping pipeline to measure and count frogeye leaf spot lesions on soybean leaves with high precision and resolution while ensuring data integrity. Results The image analysis program developed measures two traits: the percent of diseased leaf area and the number of lesions on a leaf. Percent of diseased leaf area is calculated by dividing the number of diseased pixels by the total number of leaf pixels, which are segmented through a series of color space transformations and pixel value thresholding. Lesion number is determined by counting the number of objects remaining in the image when the lesions are segmented. Automated measurement of the percent of diseased leaf area deviates from the manually measured value by less than 0.05% on average. Automatic lesion counting deviates by an average of 1.6 lesions from the manually counted value. The proposed method is highly correlated with a conventional method using a 1–5 ordinal scale based on a standard area diagram. Input image compression was optimal at a resolution of 1500 × 1000 pixels. At this resolution, the image analysis method proposed can process an image in less than 10 s and is highly concordant with uncompressed images. Conclusion Image analysis provides improved resolution over conventional methods of frogeye leaf spot disease phenotyping. This method can improve the precision and resolution of phenotyping frogeye leaf spot, which can be used in genetic mapping to identify QTLs for crop genetic resistance and in breeding efforts for resistance to the disease.

RGB image-based method for phenotyping rust disease progress in pea leaves using R

“…In others pathosystems, incorporation of additional colour space transformations or implementation of machine learning tool was shown to improve lesion segmentation and accuracy however each additional step increased processing time. For example, McDonald et al proposed an automated method for measuring soybean [ Glycine max (L.) Merr] frogeye leaf spot that involves converting RGB images to HSB (hue, saturation, brightness) and then to LAB (lightness, a* chrominance, b* chrominance) to remove the background and isolate the lesion [ 34 ]. While the method was highly accurate, reaching accuracy of 0.99 it took 16.7 min to analyse 100 leaf samples.…”

“…Little advances have been achieved toward automatization of pea rust phenotyping in comparison with other aerial fungal pathosystems, for which many platforms and methodologies have been developed to increase accuracy and precision of disease estimation including from other fungal pathogens in legumes [ 34 ] to bacterial pathogens in citrus plants [ 35 , 36 ]. Among these so-called high-throughput methods, development of image-based phenotyping techniques has largely increased in the last decade partly thanks to the decrease in imaging technologies cost and the increase in computing power [ 37 ] that contributed to make them more affordable and accurate.…”

Genome-wide identification and expression analysis of the MADS gene family in sweet orange (Citrus sinensis) infested with pathogenic bacteria

“…The lesions are usually 1-5 mm in diameter and can combine to form large spots when severely infected. The leaf spot fungus is highly latent, with leaf spot symptoms appearing within 48 h at high humidity, but the spots are usually not observable until 8–12 days ( McDonald, Buck & Li, 2022 ). Leaf spot disease produces irregular patches on the surface of sweet orange leaves, which perforate, wilt, and fall off.…”

ScAnalyzer: an image processing tool to monitor plant disease symptoms and pathogen spread in Arabidopsis thaliana leaves

“…Assessing disease severity in the context of resistance/susceptibility of individual plants is often done by human evaluations and is therefore a subjective method not readily transferred between persons and it is time consuming. Clearly, there is a need for quantifying disease symptoms in an objective manner, which is underlined by a growing number of scientific reports that describe computational pipelines that use digital images of diseased plants to quantify disease severity [2][3][4][5][6][7].…”