A neural network for phenotyping <i>Fusarium</i>‐damaged kernels (FDKs) in wheat and its impact on genomic selection accuracy

Wu, Jun; Ackerman, Arlyn; Gaire, Rupesh; Chowdhary, Girish; Rutkoski, Jessica

doi:10.1002/ppj2.20065

Cited by 3 publications

(2 citation statements)

References 87 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As DI and FDK are often differentially regulated, and DON contamination correlates significantly more closely with FDK, its evaluation is important. The results were confirmed by Wu et al [ 136 ]. They evaluated a highly sophisticated neural network methodology to evaluate FDK to improve the accuracy of genomic selection.…”

Section: Breeding Aspectssupporting

confidence: 82%

“…Despite many excellent papers like Zhang et al [ 135 ] that analyze only visual symptoms, presenting important interactions of pyramided QTLs, toxin data do not support the conclusion. A recent paper found the FDK has the closest correlation trait to DON [ 136 ] and found with a sophisticated neural network technology correlation among FDK and DON between 0.41 and 0.58. Our simple visual data showed much closer relations [ 87 , 89 , 90 , 94 , 95 , 133 ].…”

Section: Phenotyping How To Evaluate Resistancementioning

confidence: 99%

See 1 more Smart Citation

What Is Fusarium Head Blight (FHB) Resistance and What Are Its Food Safety Risks in Wheat? Problems and Solutions—A Review

Mesterhazy

2024

Toxins

View full text Add to dashboard Cite

The term “Fusarium Head Blight” (FHB) resistance supposedly covers common resistances to different Fusarium spp. without any generally accepted evidence. For food safety, all should be considered with their toxins, except for deoxynivalenol (DON). Disease index (DI), scabby kernels (FDK), and DON steadily result from FHB, and even the genetic regulation of Fusarium spp. may differ; therefore, multitoxin contamination is common. The resistance types of FHB form a rather complex syndrome that has been the subject of debate for decades. It seems that resistance types are not independent variables but rather a series of components that follow disease and epidemic development; their genetic regulation may differ. Spraying inoculation (Type 1 resistance) includes the phase where spores land on palea and lemma and spread to the ovarium and also includes the spread-inhibiting resistance factor; therefore, it provides the overall resistance that is needed. A significant part of Type 1-resistant QTLs could, therefore, be Type 2, requiring the retesting of the QTLs; this is, at least, the case for the most effective ones. The updated resistance components are as follows: Component 1 is overall resistance, as discussed above; Component 2 includes spreading from the ovarium through the head, which is a part of Component 1; Component 3 includes factors from grain development to ripening (FDK); Component 4 includes factors influencing DON contamination, decrease, overproduction, and relative toxin resistance; and for Component 5, the tolerance has a low significance without new results. Independent QTLs with different functions can be identified for one or more traits. Resistance to different Fusarium spp. seems to be connected; it is species non-specific, but further research is necessary. Their toxin relations are unknown. DI, FDK, and DON should be checked as they serve as the basic data for the risk analysis of cultivars. A better understanding of the multitoxin risk is needed regarding resistance to the main Fusarium spp.; therefore, an updated testing methodology is suggested. This will provide more precise data for research, genetics, and variety registration. In winter and spring wheat, the existing resistance level is very high, close to Sumai 3, and provides much greater food safety combined with sophisticated fungicide preventive control and other practices in commercial production.

show abstract

Section: Breeding Aspectssupporting

confidence: 82%

Section: Phenotyping How To Evaluate Resistancementioning

confidence: 99%

What Is Fusarium Head Blight (FHB) Resistance and What Are Its Food Safety Risks in Wheat? Problems and Solutions—A Review

Mesterhazy

2024

Toxins

View full text Add to dashboard Cite

show abstract

Estimating Fusarium head blight severity in winter wheat using deep learning and a spectral index

McConachie,

Belot,

Serajazari

et al. 2024

The Plant Phenome Journal

View full text Add to dashboard Cite

Fusarium head blight (FHB) of wheat (Triticum aestivum L.), caused by the fungal pathogen Fusarium graminearum (Fg), reduces grain yield and quality due to the production of the mycotoxin deoxynivalenol. Manual rating for incidence (percent of infected wheat heads/spikes) and severity (percent of spikelets infected) to estimate FHB resistance is time‐consuming and subject to human error. This study uses a deep learning model, combined with a spectral index, to provide rapid phenotyping of FHB severity. An object detection model was used to localize wheat heads within boundary boxes. Corresponding boxes were used to prompt Meta's Segment Anything Model to segment wheat heads. Using 2576 images of wheat heads point inoculated with Fg in a controlled environment, a spectral index was developed using the red and green bands to differentiate healthy from infected tissue and estimate disease severity. Stratified random sampling was applied to pixels within the segmentation mask, and the model classified pixels as healthy or infected with an accuracy of 87.8%. Linear regression determined the relationship between the index and visual severity scores. The severity estimated by the index was able to predict visual scores (R2 = 0.83, p = < 2e‐16). This workflow was also applied to plot size images of infected wheat heads from an outside dataset with varying cultivars and lighting to assess model transferability. It correctly classified pixels as healthy or infected with a prediction accuracy of 85.8%. These methods may provide rapid estimation of FHB severity to improve selection efficiency for resistance or estimate disease pressure for effective management.

show abstract

Integrating genomics, phenomics, and deep learning improves the predictive ability for Fusarium head blight–related traits in winter wheat

Thapa,

Gill,

Halder

et al. 2024

The Plant Genome

View full text Add to dashboard Cite

Fusarium head blight (FHB) remains one of the most destructive diseases of wheat (Triticum aestivum L.), causing considerable losses in yield and end‐use quality. Phenotyping of FHB resistance traits, Fusarium‐damaged kernels (FDK), and deoxynivalenol (DON), is either prone to human biases or resource expensive, hindering the progress in breeding for FHB‐resistant cultivars. Though genomic selection (GS) can be an effective way to select these traits, inaccurate phenotyping remains a hurdle in exploiting this approach. Here, we used an artificial intelligence (AI)‐based precise FDK estimation that exhibits high heritability and correlation with DON. Further, GS using AI‐based FDK (FDK_QVIS/FDK_QNIR) showed a two‐fold increase in predictive ability (PA) compared to GS for traditionally estimated FDK (FDK_V). Next, the AI‐based FDK was evaluated along with other traits in multi‐trait (MT) GS models to predict DON. The inclusion of FDK_QNIR and FDK_QVIS with days to heading as covariates improved the PA for DON by 58% over the baseline single‐trait GS model. We next used hyperspectral imaging of FHB‐infected wheat kernels as a novel avenue to improve the MT GS for DON. The PA for DON using selected wavebands derived from hyperspectral imaging in MT GS models surpassed the single‐trait GS model by around 40%. Finally, we evaluated phenomic prediction for DON by integrating hyperspectral imaging with deep learning to directly predict DON in FHB‐infected wheat kernels and observed an accuracy (R2 = 0.45) comparable to best‐performing MT GS models. This study demonstrates the potential application of AI and vision‐based platforms to improve PA for FHB‐related traits using genomic and phenomic selection.

show abstract

A neural network for phenotyping Fusarium‐damaged kernels (FDKs) in wheat and its impact on genomic selection accuracy

Cited by 3 publications

References 87 publications

What Is Fusarium Head Blight (FHB) Resistance and What Are Its Food Safety Risks in Wheat? Problems and Solutions—A Review

What Is Fusarium Head Blight (FHB) Resistance and What Are Its Food Safety Risks in Wheat? Problems and Solutions—A Review

Estimating Fusarium head blight severity in winter wheat using deep learning and a spectral index

Integrating genomics, phenomics, and deep learning improves the predictive ability for Fusarium head blight–related traits in winter wheat

Contact Info

Product

Resources

About