“Fusarium head blight causes a lot of economic losses in wheat, and the associated toxin, deoxynivalenol, can cause issues for human and animal health. The disease has been a big deterrent for people growing wheat in the Eastern U.S. because they could grow a perfectly nice crop, and then take it to the elevator only to have it get docked or rejected. That’s been painful for people. So it’s a big priority to try to increase resistance and reduce DON risk as much as possible,” said Jessica Rutkoski, assistant professor in the University of Illinois’ College of Agricultural, Consumer and Environmental Sciences’ department of crop sciences. Rutkoski is a co-author on the new paper in the Plant Phenome Journal.

Increasing resistance to any crop disease traditionally means growing a lot of genotypes of the crop, infecting them with the disease, and looking for symptoms. The process, known in plant breeding as phenotyping, is successful when it identifies resistant genotypes that don’t develop symptoms, or less severe symptoms. When that happens, researchers try to identify the genes related to disease resistance and then put those genes in high-performing hybrids of the crop.

It’s a long repetitive process, but Rutkoski hoped one step – phenotyping for disease symptoms – could be accelerated. She looked for help from artificial intelligence experts Junzhe Wu, doctoral student in the Department of Agricultural and Biological Engineering, and Girish Chowdhary, associate professor in the Department of Agricultural and Biological Engineering and the Department of Computer Science.

“We wanted to test whether we could quantify kernel damage using simple cell phone images of grains. Normally, we look at a petri dish of kernels and then give it a subjective rating. It’s very mind-numbing work. You have to have people specifically trained and it’s slow, difficult and subjective. A system that could automatically score kernels for damage seemed doable because the symptoms are pretty clear,” Rutkoski said.

Wu and Chowdhary agreed it was possible. They started with algorithms similar to those used by tech giants for object detection and classification. But discerning minute differences in diseased and healthy wheat kernels from cell phone images required Wu and Chowdhary to advance the technology further.

Chowdhary said, “One of the unique things about this advance is that we trained our network to detect minutely damaged kernels with good enough accuracy using just a few images. We made this possible through meticulous pre-processing of data, transfer learning and bootstrapping of labeling activities. This is another nice win for machine learning and AI for agriculture and society.”

He said, “This project builds on the AIFARMS National AI Institute and the Center for Digital Agriculture here at Illinois to leverage the strength of AI for agriculture.”

Successfully detecting fusarium damage – small, shriveled, gray or chalky kernels – meant the technology could also foretell the grain’s toxin load; the more external signs of damage, the greater the deoxynivalenol content.

When the team tested the machine learning technology alone, it was able to predict deoxynivalenol levels better than in-field ratings of disease symptoms, which breeders often rely on instead of kernel phenotyping to save time and resources. But when compared to humans rating disease damage on kernels in the lab, the technology was only 60 percent as accurate.

The researchers are still encouraged, though, as their initial tests didn’t use a large number of samples to train the model. They’re currently adding samples and expect to achieve greater accuracy with additional tweaking.

Wu said, “While further training is needed to improve the capabilities of our model, initial testing shows promising results and demonstrates the possibility of providing an automated and objective phenotyping method for fusarium damaged kernels that could be widely deployed to support resistance breeding efforts.”

Rutkoski said the ultimate goal is to create an online portal where breeders like her could upload cell phone photos of wheat kernels for automatic scoring of fusarium damage.

Rutkoski said, “A tool like this could save weeks of time in a lab, and that time is critical when you’re trying to analyze the data and prepare the next trial. And ultimately, the more efficiency we can bring to the process, the faster we can improve resistance to the point where scab can be eliminated as a problem.”

The article, “A neural network for phenotyping fusarium-damaged kernels (FDK) in wheat and its impact on genomic selection accuracy,” is published in the Plant Phenome Journal. Authors include Junzhe Wu, Arlyn Ackerman, Rupesh Gaire, Girish Chowdhary and Jessica Rutkoski. The research was supported by the U.S. Wheat and Barley Scab Initiative and the U.S. Department of Agriculture’s National Institute of Food and Agriculture. Visit aces.illinois.edu/news/could-ai-powered-object-recognition-technology-help-solve-wheat-disease for more information.