Differentiation of Maize Ear Rot Pathogens, on Growth Media, with Near Infrared Hyperspectral Imaging
In this study, the major maize ear rot pathogens were differentiated from one another, on growth media, with near-infrared (NIR) hyperspectral imaging. Fungal isolates of four pathogens commonly associated with maize grain (Fusarium verticillioides, F. graminearum s.s., F. boothii and Stenocarpella maydis) were plated on potato dextrose agar, in triplicate, and incubated at 25°C for 5 days. Images were collected with a SisuChema short-wave infrared (SWIR) pushbroom hyperspectral imaging system ranging from 1000 to 2500 nm. Pixel and object wise classification algorithms were compared to determine the best approach. These were evaluated with principal component analysis and partial least squares discriminant analysis. The pathogens were distinguished using three-way classification models that were validated with independent images. The object wise approach proved to be more effective in distinguishing ear rot pathogens with a higher average overall classification accuracy (93.75%). The object wise models achieved two 100% classification accuracies from the four pathogen models, while none of the pixel wise classification models were error free. The specificity and sensitivity further highlighted the superiority of the object wise approach. The high accuracy of object wise classification (> 86%) can be attributed to the representation of the mean spectra per object. NIR hyperspectral imaging can thus accurately distinguish between the major maize ear rot pathogens, with object wise classification proving to be the optimal approach.
KeywordsNear-infrared hyperspectral imaging Maize ear rot pathogens Growth media Multivariate image analysis Object wise approach Classification
The authors wish to thank Prof Alvaro Viljoen and Dr. Ilze Vermaak, Tshwane University of Technology, Pretoria for use of the NIR hyperspectral imaging system.
This work is based on the research supported in part by the National Research Foundation of South Africa (grant numbers 94031 and 95343).
Compliance with Ethical Standards
Conflict of Interest
Paul J. Williams declares that he has no conflict of interest. Cenette Bezuidenhout declares that she has no conflict of interest. Lindy J. Rose declares that she has no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Boutigny A, Ward TJ, Van Coller GJ, Flett B, Lamprecht SC, O’Donnell K, Viljoen A (2011) Analysis of the Fusarium graminearum species complex from wheat, barley and maize in South Africa provides evidence of species-specific differences in host preference. Fungal Genet Biol 48:914–920CrossRefGoogle Scholar
- Burger JE (2006) Hyperspectral NIR Image Analysis. PhD Thesis. Swedish University of Agricultural Sciences, UmeåGoogle Scholar
- EPPO. (2017) Stenocarpella macrospora and Stenocarpella maydis [Internet document] URL https://www.eppo.int/QUARANTINE/data_sheets/.../DIPDSP_ds.pdf. Accessed 24/07/2017
- Esbensen KH, Guyot D, Westad F & Houmøller LP (2002) Principal component analysis (PCA)—introduction. In: Multivariate data analysis in practice: an introduction to multivariate data analysis and experimental design. 5th edn. CAMO process ASGoogle Scholar
- Gelderblom WCA, Seier JV, Snijman PW, Van Schalkwyk DJ, Shephard GS, Marasas WFO (2001) Toxicity of culture material of Fusarium verticillioides strain MRC 826 to nonhuman primates. Environ Health Perspect 109:267–276Google Scholar
- Gokul A (2015) Fusarium graminearum species complex (FGSC) composition in South African wheat and maize grown in rotation. Stellenbosch University, Stellenbosch, MSc ThesisGoogle Scholar
- Osborne BG, Fearn T, Hindle PH (1993) Practical NIR spectroscopy with applications in food and beverage analysis, 2nd edn. Longman Scientific & Technical, EssexGoogle Scholar
- Peraica M, Radić B, Lucić A, Pavlović M (1999) Toxic effects of mycotoxins in humans. Bull World Health Organ 77:754–766Google Scholar
- Rabie CJ, Van Rensburg SJ, Kriek NPJ, Lübben A (1977) Toxicity of Diplodia maydis to laboratory animals. Appl Environ Microbiol 34:111–114Google Scholar
- Rinnan A, Van Den Berg F & Engelsen SB (2009) Review of the most common pre-processing techniques for near-infrared spectra. Trends in Analytical Chemistry, 28Google Scholar
- Seo Y, Park B, Hinton A, Yoon JS, Lawrence KC (2016) Identification of Staphylococcus species with hyperspectral microscope imaging and classification algorithms. J Food Meas Charact 10:253–263Google Scholar
- Sokolova M, Japkowicz N, Szpakowicz S (2006) Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In: Advances in Artificial Intelligence: 19th Australian Joint Conference on Artificial Intelligence (edited by a. Sattar & B. Kang). Springer, Berlin Heidelberg, pp 1015–1021Google Scholar
- Williams PJ (2013) Near infrared (NIR) hyperspectral imaging and X-ray computed tomography combined with statistical and multivariate data analysis to study Fusarium infection in maize. PhD Thesis. Stellenbosch University, StellenboschGoogle Scholar