Evaluation of Methods for Measuring Fusarium-Damaged Kernels of Wheat

Ackerman, Arlyn; Holmes, R. M.; Gaskins, Ezekiel; Jordan, Kathleen; Hicks, Dawn S.; Fitzgerald, Joshua; Griffey, Carl A.; Mason, Richard E.; Harrison, Stephen A.; Murphy, J. Paul; Cowger, Christina; Boyles, Richard

doi:10.3390/agronomy12020532

Cited by 7 publications

(18 citation statements)

References 45 publications

(69 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reflectance data were exported from the software in the form of Excel sheets using the export option. Following the method of estimating the percentage of Fusarium-damaged kernels (FDKs) developed by Ackerman [ 38 ], we collected the kernel damage percentage. This method quantifies visual symptoms with the help of human observation.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels

Dhakal

Sivaramakrishnan

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Fusarium head blight (FHB) is a disease of small grains caused by the fungus Fusarium graminearum. In this study, we explored the use of hyperspectral imaging (HSI) to evaluate the damage caused by FHB in wheat kernels. We evaluated the use of HSI for disease classification and correlated the damage with the mycotoxin deoxynivalenol (DON) content. Computational analyses were carried out to determine which machine learning methods had the best accuracy to classify different levels of damage in wheat kernel samples. The classes of samples were based on the DON content obtained from Gas Chromatography–Mass Spectrometry (GC-MS). We found that G-Boost, an ensemble method, showed the best performance with 97% accuracy in classifying wheat kernels into different severity levels. Mask R-CNN, an instance segmentation method, was used to segment the wheat kernels from HSI data. The regions of interest (ROIs) obtained from Mask R-CNN achieved a high mAP of 0.97. The results from Mask R-CNN, when combined with the classification method, were able to correlate HSI data with the DON concentration in small grains with an R2 of 0.75. Our results show the potential of HSI to quantify DON in wheat kernels in commercial settings such as elevators or mills.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels

Dhakal

Sivaramakrishnan

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Type II is assessed by rating the visual symptoms on the spikes, which appear as bleached, yellowish or discolored, and stunted (Zakieh et al, 2021;Steed et al, 2022). FDK is quantified traditionally by estimating the amount of visibly damaged kernels, which appear smaller, shriveled, and in a range of colors from pale pink to brown (Delwiche et al, 2010), according to a predetermined scale for visual assessments or by employing manual tools (Ackerman et al, 2022). Comparisons between both types of resistance (resistance types II and III) have revealed that it would be more efficient and consistent to estimate FHB than the degree of colonization on the spike (Agostinelli, 2009;Balut et al, 2013;Khaeim et al, 2019;Ackerman et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

Developing affordable high-throughput plant phenotyping methods for breeding of cereals and tuber crops

Leiva-Sandoval¹

2023

Acta Universitatis Agriculturae Sueciae

View full text Add to dashboard Cite

High-throughput plant phenotyping (HTPP) is a fast, accurate, and non-destructive process for evaluating plants' health and environmental adaptability. HTPP accelerates the identification of agronomic traits of interest, eliminates subjectivism (which is innate to humans), and facilitates the development of adapted genotypes. Current HTPP methods often rely on imaging sensors and computer vision both in the field and under controlled (indoor) conditions. However, their use is limited by the costs and complexity of the necessary instrumentation, data analysis tools, and software. This issue could be overcome by developing more cost-efficient and user-friendly methods that let breeders, farmers, and stakeholders access the benefits of HTPP. To assist such efforts, this thesis presents an ensemble of dedicated affordable phenotyping methods using RGB imaging for a range of key applications under controlled conditions. The affordable Phenocave imaging system for use in controlled conditions was developed to facilitate studies on the effects of abiotic stresses by gathering data on important plant characteristics related to growth, yield, and adaptation to growing conditions and cultivation systems. Phenocave supports imaging sensors including visible (RGB), spectroscopic (multispectral and hyperspectral), and thermal imaging. Additionally, a pipeline for RGB image analysis was implemented as a plugin for the free and easy-to-use software ImageJ. This plugin has since proven to be an accurate alternative to conventional measurements that produces highly reproducible results. A subsequent study was conducted to evaluate the effects of heat and drought stress on plant growth and grain nutrient composition in wheat, an important staple cereal in Sweden. The effects of stress on plant growth were evaluated using image analysis, while stress-induced changes in the abundance of key plant compounds were evaluated by analyzing the nutrient composition of grains via chromatography. This led to the discovery of genotypes whose harvest quality remains stable under heat and drought stress. The next objective was to evaluate biotic stress; for this case, the effect of the fungal disease Fusarium head blight (FHB) that affects grain development in wheat was investigated. For this purpose, seed phenotyping parameters were used to determine the components and settings of a statistical model, which predicts the occurrence of FHB. The results reveal that grain morphology evaluations, such as length and width, were found to be significantly affected by the disease. Another study was carried out to estimate the disease severity of the common scab (CS) in potatoes, a widely popular food source. CS occurs on the tubers and reduces their visual appeal, significantly affecting their market value. Tubers were analyzed by a deep learning-based method to estimate disease lesion areas caused by CS. Results showed a high correlation between the predictions and expert visual scorings of the disease and proved to be a potential tool for the selection of genotypes that fulfill the market standards and resistance to CS. Both case studies highlight the role of imaging in plant health monitoring and its integration into the larger picture of plant health management. The methods presented in this work are a starting point for bridging the gap between costs and accessibility to imaging technology. These are affordable and user-friendly resources for generating pivotal knowledge on plant development and genotype selection. In the future, image acquisition of all the methods can be integrated into the Phenocave system, potentially allowing for a more automated and efficient plant health monitoring process, leading to the identification of tolerant genotypes to biotic and abiotic stresses.

show abstract

“…Type II is assessed by rating the visual symptoms on the spikes, which appear as bleached, yellowish or discolored, and stunted ( Zakieh et al., 2021 ; Steed et al., 2022 ). FDK is quantified traditionally by estimating the amount of visibly damaged kernels, which appear smaller, shriveled, and in a range of colors from pale pink to brown ( Delwiche et al., 2010 ), according to a predetermined scale for visual assessments or by employing manual tools ( Ackerman et al., 2022 ). Comparisons between both types of resistance (resistance types II and III) have revealed that it would be more efficient and consistent to estimate FHB than the degree of colonization on the spike ( Agostinelli, 2009 ; Balut et al., 2013 ; Khaeim et al., 2019 ; Ackerman et al., 2022 ).…”

Section: Introductionmentioning

confidence: 99%

“…FDK is quantified traditionally by estimating the amount of visibly damaged kernels, which appear smaller, shriveled, and in a range of colors from pale pink to brown ( Delwiche et al., 2010 ), according to a predetermined scale for visual assessments or by employing manual tools ( Ackerman et al., 2022 ). Comparisons between both types of resistance (resistance types II and III) have revealed that it would be more efficient and consistent to estimate FHB than the degree of colonization on the spike ( Agostinelli, 2009 ; Balut et al., 2013 ; Khaeim et al., 2019 ; Ackerman et al., 2022 ). However, screening by either manual or visual assessments is a labor- and time-consuming process for rating genotypes, is biased due to the subjectivity of visual assessments, and has low reproducibility among experiments ( Barbedo et al., 2015 ; Khaeim et al., 2019 ).…”

Section: Introductionmentioning

confidence: 99%

Phenotyping Fusarium head blight through seed morphology characteristics using RGB imaging

Leiva

Zakieh²,

Alamrani³

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Fusarium head blight (FHB) is an economically important disease affecting wheat and thus poses a major threat to wheat production. Several studies have evaluated the effectiveness of image analysis methods to predict FHB using disease-infected grains; however, few have looked at the final application, considering the relationship between cost and benefit, resolution, and accuracy. The conventional screening of FHB resistance of large-scale samples is still dependent on low-throughput visual inspections. This study aims to compare the performance of two cost–benefit seed image analysis methods, the free software “SmartGrain” and the fully automated commercially available instrument “Cgrain Value™” by assessing 16 seed morphological traits of winter wheat to predict FHB. The analysis was carried out on a seed set of FHB which was visually assessed as to the severity. The dataset is composed of 432 winter wheat genotypes that were greenhouse-inoculated. The predictions from each method, in addition to the predictions combined from the results of both methods, were compared with the disease visual scores. The results showed that Cgrain Value™ had a higher prediction accuracy of R2 = 0.52 compared with SmartGrain for which R2 = 0.30 for all morphological traits. However, the results combined from both methods showed the greatest prediction performance of R2 = 0.58. Additionally, a subpart of the morphological traits, namely, width, length, thickness, and color features, showed a higher correlation with the visual scores compared with the other traits. Overall, both methods were related to the visual scores. This study shows that these affordable imaging methods could be effective to predict FHB in seeds and enable us to distinguish minor differences in seed morphology, which could lead to a precise performance selection of disease-free seeds/grains.

show abstract

Evaluation of Methods for Measuring Fusarium-Damaged Kernels of Wheat

Cited by 7 publications

References 45 publications

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels

Machine Learning Analysis of Hyperspectral Images of Damaged Wheat Kernels

Developing affordable high-throughput plant phenotyping methods for breeding of cereals and tuber crops

Phenotyping Fusarium head blight through seed morphology characteristics using RGB imaging

Contact Info

Product

Resources

About