Hyperspectral imaging and improved feature variable selection for automated determination of deoxynivalenol in various genetic lines of barley kernels for resistance screening. (1st May 2021)

• Record Type: Journal Article
• Authors: Su, Wen-Hao; Yang, Ce; Dong, Yanhong; Johnson, Ryan; Page, Rae; Szinyei, Tamas; Hirsch, Cory D.; Steffenson, Brian J.
• Is Part Of: Food chemistry. Volume 343(2021)
• Publication Date: 2021-05-01
• Subjects: Hyperspectral imaging -- Cereals -- Deoxynivalenol -- Feature variable selection -- Machine learning; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2020.128507
• Languages: English
• ISSNs: 0308-8146

Abstract

Highlights: DON levels in barley kernels was screened using hyperspectral imaging. Feature wavelengths were selected and optimized using CARS-ISSPA. DON contents were predicted using CARS-ISSPA-LWPLSR algorithm. CARS-ISSPA-PLSDA algorithm classified kernels according to their DON levels. Abstract: Fusarium head blight (FHB), a fungus disease of small grain cereal crops, results in reduced yields and diminished value of harvested grain due to the presence of deoxynivalenol (DON), a mycotoxin produced by the causal pathogen Fusarium graminearum . DON and other tricothecene mycotoxins pose serious health risks to both humans and livestock, especially swine. Due to these health concerns, barley used for malting, food or feed is routinely assayed for DON levels. Various methods are available for assaying DON levels in grain samples including enzyme-linked immunosorbent assay (ELISA) and gas chromatography-mass spectrometry (GC-MS). ELISA and GC-MS are very accurate; however, assaying grain samples by these techniques are laborious, expensive and destructive. In this study, we explored the feasibility of using hyperspectral imaging (382–1030 nm) to develop a rapid and non-destructive protocol for assaying DON in barley kernels. Samples of 888 and 116 from various genetic lines were selected for calibration and prediction. Full-wavelength locally weighted partial least squares regression (LWPLSR) achieved high accuracy with the coefficient of determination in prediction ( R 2 P ) of 0.728 and root mean square error of prediction (RMSEP) of 3.802. Competitive adaptive reweighted sampling (CARS) was used to choose potential feature wavelengths, and these selected variables were further optimized using the iterative selection of successive projections algorithm (ISSPA). The CARS-ISSPA-LWPLSR model developed using 7 feature variables yielded R 2 P of 0.680 and RMSEP of 4.213 in DON content prediction. Based on the 7 wavelengths selected by CARS-ISSPA, partial least square discriminant analysis (PLSDA) discriminated barley kernels having lower DON (less than1.25 mg/kg) levels from those with higher levels (including 1.25–3 mg/kg, 3–5 mg/kg, and 5–10 mg/kg), with Matthews correlation coefficient in cross-validation (M- R CV ) of as high as 0.931. The results demonstrate that hyperspectral imaging have potential for accelerating non-destructive DON assays of barley samples.