Abstract
Fusarium head blight (FHB) is one of the most significant diseases affecting wheat and other small-grain cereals worldwide. Developing FHB-resistant cultivars is critical but requires field and greenhouse disease assessment, which are typically laborious and time consuming. In this work, we developed automated applications based on three-dimensional (3D) convolutional neural networks (CNNs) that detect FHB symptoms expressed in wheat, estimate the total number of spikelets versus the total number of infected spikelets on a wheat head, and subsequently calculate FHB severity index. Such tools are an important step toward the creation of automated and efficient phenotyping methods. The data used to generate the results are 3D point clouds consisting of four colour channels—red, green, blue (RGB), and near-infrared (NIR)—collected using a multispectral 3D scanner. Our 3D CNN models for FHB detection achieved 100% accuracy. The influence of the multispectral information on performance was evaluated; the results showed the dominance of the RGB channels over both the NIR (720 nm peak wavelength) and the NIR plus RGB channels combined. Our best 3D CNN models for estimation of total and infected number of spikelets achieved mean absolute errors (MAEs) of 1.13 and 1.56, respectively. Our best 3D CNN models for FHB severity estimation achieved 8.6 MAE. A linear regression analysis between the visual FHB severity assessment and the FHB severity predicted by our 3D CNN showed a significant correlation.
Abstract from the paper’s OpenAlex record; open copy licensed cc-by. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 6
Claim · model-written summary
The 3D CNN models detected FHB with 100% accuracy.
- Taxon
- wheat
Triticum aestivumt0 - Interactor
- FHBe0pathogen
- Outcome
- accuracye0
- Value
- 100%e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Our 3D CNN models for FHB detection achieved 100% accuracy”
t0“wheat”
Claim · model-written summary
RGB channels dominated NIR and combined NIR plus RGB channels in model performance.
- Taxon
- wheatTriticum aestivumt0
- Outcome
- dominance of the RGB channelse0
- Direction
- dominancee0
- Comparator
- NIR (720 nm peak wavelength) and the NIR plus RGB channels combinede0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“the results showed the dominance of the RGB channels over both the NIR (720 nm peak wavelength) and the NIR plus RGB channels combined”
t0“wheat”
Claim · model-written summary
The best model estimated total spikelet number with MAE 1.13.
- Taxon
- wheatTriticum aestivumt0
- Outcome
- estimation of totale0
- Value
- 1.13e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Our best 3D CNN models for estimation of total and infected number of spikelets achieved mean absolute errors (MAEs) of 1.13 and 1.56, respectively”
t0“wheat”
Claim · model-written summary
The best model estimated infected spikelet number with MAE 1.56.
- Taxon
- wheatTriticum aestivumt0
- Outcome
- infected number of spikeletse0
- Value
- 1.56e0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Our best 3D CNN models for estimation of total and infected number of spikelets achieved mean absolute errors (MAEs) of 1.13 and 1.56, respectively”
t0“wheat”
Claim · model-written summary
The best model estimated FHB severity with MAE 8.6.
- Taxon
- wheatTriticum aestivumt0
- Outcome
- FHB severity estimatione0
- Value
- 8.6 MAEe0
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Our best 3D CNN models for FHB severity estimation achieved 8.6 MAE”
t0“wheat”
Claim · model-written summary
Visual and CNN predicted FHB severity were significantly correlated.
- Taxon
- wheatTriticum aestivumt0
- Outcome
- significant correlatione0
- Comparator
- visual FHB severity assessmente0
Not reportedDirection
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“A linear regression analysis between the visual FHB severity assessment and the FHB severity predicted by our 3D CNN showed a significant correlation”
t0“wheat”