Practicability investigation of using near-infrared hyperspectral imaging to detect rice kernels infected with rice false smut in different conditions

Abstract Rice false smut (RFS) is a devastating seed-brone rice disease in many rice-growing countries, endangering the health of rice germplasm resources and reducing the yield and quality of rice. This study aimed to propose an effective method for RFS detection in actual production based on near-infrared hyperspectral imaging (NIR-HSI) paired with pathological analysis. The true infection status of rice kernels collected in different conditions was labeled by PCR. The separability between healthy and infected rice kernels was explored using principal component analysis (PCA). Multivariate quantitative analysis models were constructed based on full wavelengths of laboratory-inoculated kernels. Characteristic wavelengths extracted to improve detection performance contained fingerprint information related to RFS infection. The best classification accuracies for healthy and infected mixed kernels with different infection degrees achieved 99.33 % on calibration set and 99.20 % on prediction set, respectively, using RF-ELM model. The practicality of detection model was further verified through obtaining detection accuracies of 91.07 % and 89.38 % for two varieties of field-infected rice kernels and visualizing the category attribute of single rice kernel in hyperspectral images. The overall results indicated the excellent potential of NIR-HSI for on-line large-scale seeds detection in modern seed industry.

[1]  Tanaka Eiji,et al.  Villosiclava virens gen. nov., comb. nov., teleomorph of Ustilaginoidea virens, the causal agent of rice false smut [Erratum: 2009 Jan-Mar, v. 107, p. 540.] , 2008 .

[2]  Jing Fan,et al.  Rice False Smut: An Increasing Threat to Grain Yield and Quality , 2019, Protecting Rice Grains in the Post-Genomic Era.

[3]  M Daszykowski,et al.  Near-infrared reflectance spectroscopy and multivariate calibration techniques applied to modelling the crude protein, fibre and fat content in rapeseed meal. , 2008, The Analyst.

[4]  J Kolar,et al.  Use of genetic algorithms with multivariate regression for determination of gelatine in historic papers based on FT-IR and NIR spectral data. , 2010, Talanta.

[5]  Yong He,et al.  Discrimination of CRISPR/Cas9-induced mutants of rice seeds using near-infrared hyperspectral imaging , 2017, Scientific Reports.

[6]  Chu Zhang,et al.  Rice Seed Cultivar Identification Using Near-Infrared Hyperspectral Imaging and Multivariate Data Analysis , 2013, Sensors.

[7]  M. Kim,et al.  Rapid assessment of corn seed viability using short wave infrared line-scan hyperspectral imaging and chemometrics , 2018 .

[8]  Y. Chen,et al.  Quantitative detection of the rice false smut pathogen Ustilaginoidea virens by real-time PCR. , 2013, Genetics and molecular research : GMR.

[9]  Silvia Serranti,et al.  The development of a hyperspectral imaging method for the detection of Fusarium-damaged, yellow berry and vitreous Italian durum wheat kernels , 2013 .

[10]  Chu Zhang,et al.  Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine , 2016 .

[11]  V. Segtnan,et al.  Near-Infrared Hyperspectral Imaging of Fusarium-Damaged Oats (Avena sativa L.) , 2015 .

[12]  J. Meng,et al.  The Contents of Ustiloxins A and B along with Their Distribution in Rice False Smut Balls , 2016, Toxins.

[13]  Panmanas Sirisomboon,et al.  Application of near infrared spectroscopy to detect aflatoxigenic fungal contamination in rice , 2013 .

[14]  J. Meng,et al.  New Ustilaginoidins from Rice False Smut Balls Caused by Villosiclava virens and Their Phytotoxic and Cytotoxic Activities. , 2017, Journal of agricultural and food chemistry.

[15]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[16]  B Nessa,et al.  Spatial Pattern of Natural Spread of Rice False Smut ( Ustilaginoidea virens ) Disease in Fields , 2015 .

[17]  Y. Makino,et al.  Monitoring fungal growth on brown rice grains using rapid and non-destructive hyperspectral imaging. , 2015, International journal of food microbiology.

[18]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[19]  D Cozzolino,et al.  Identification of transgenic foods using NIR spectroscopy: a review. , 2010, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[20]  Jian Wang,et al.  Ustiloxin G, a New Cyclopeptide Mycotoxin from Rice False Smut Balls , 2017, Toxins.

[21]  E. Sieniawska,et al.  Antimycobacterial Activity of Cinnamaldehyde in a Mycobacterium tuberculosis(H37Ra) Model , 2018, Molecules.

[22]  Yuying Li,et al.  Development of a monoclonal antibody with equal reactivity to ustiloxins A and B for quantification of main cyclopeptide mycotoxins in rice samples , 2018, Food Control.

[23]  Giyoung Kim,et al.  Classification of Fusarium-Infected Korean Hulled Barley Using Near-Infrared Reflectance Spectroscopy and Partial Least Squares Discriminant Analysis , 2017, Sensors.

[24]  Noel D.G. White,et al.  Fungal Damage Detection in Wheat Using Short-Wave Near-Infrared Hyperspectral and Digital Colour Imaging , 2012 .

[25]  Kurt C. Lawrence,et al.  Near-infrared hyperspectral imaging for detecting Aflatoxin B1 of maize kernels , 2015 .

[26]  Chu Zhang,et al.  Application of Near-Infrared Hyperspectral Imaging with Variable Selection Methods to Determine and Visualize Caffeine Content of Coffee Beans , 2016, Food and Bioprocess Technology.

[27]  P. Zapotoczny,et al.  Classification of Fusarium-infected and healthy wheat kernels based on features from hyperspectral images and flatbed scanner images: a comparative analysis , 2018, European Food Research and Technology.

[28]  J. Meng,et al.  Preparative Separation of Main Ustilaginoidins from Rice False Smut Balls by High-Speed Counter-Current Chromatography , 2016, Toxins.

[29]  Santosh Lohumi,et al.  Comparative nondestructive measurement of corn seed viability using Fourier transform near-infrared (FT-NIR) and Raman spectroscopy , 2016 .

[30]  Moon S. Kim,et al.  Detection of cucumber green mottle mosaic virus-infected watermelon seeds using a near-infrared (NIR) hyperspectral imaging system: Application to seeds of the “Sambok Honey” cultivar , 2016 .

[31]  W. Shier,et al.  Ustilaginoidea virens Infection of Rice in Arkansas: Toxicity of False Smut Galls, Their Extracts and the Ustiloxin Fraction , 2014 .

[32]  Chu Zhang,et al.  Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network , 2018, Molecules.

[33]  Paul J. Williams,et al.  Investigation of fungal development in maize kernels using NIR hyperspectral imaging and multivariate data analysis , 2012 .

[34]  M. Kim,et al.  Selection of Optimal Hyperspectral Wavebands for Detection of Discolored, Diseased Rice Seeds , 2019, Applied Sciences.

[35]  M. C. U. Araújo,et al.  The successive projections algorithm for variable selection in spectroscopic multicomponent analysis , 2001 .

[36]  Qing-Song Xu,et al.  Random frog: an efficient reversible jump Markov Chain Monte Carlo-like approach for variable selection with applications to gene selection and disease classification. , 2012, Analytica chimica acta.

[37]  Chu Zhang,et al.  Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network , 2018 .

[38]  Eiji Tanaka,et al.  Villosiclava virens gen nov, comb, nov, teleomorph of Ustilaginoidea virens, the causal agent of rice false smut , 2008 .

[39]  Da-Wen Sun,et al.  Recent Advances in Wavelength Selection Techniques for Hyperspectral Image Processing in the Food Industry , 2014, Food and Bioprocess Technology.

[40]  Hongdong Li,et al.  Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. , 2009, Analytica chimica acta.

[41]  D. Lai,et al.  A monoclonal antibody-based enzyme-linked immunosorbent assay for detection of ustiloxin A in rice false smut balls and rice samples. , 2015, Food chemistry.

[42]  P. Okubara,et al.  Real-time PCR quantification of Fusarium avenaceum in soil and seeds. , 2019, Journal of microbiological methods.

[43]  R. Sonoda,et al.  PCR-based specific detection of Ustilaginoidea virens and Ephelis japonica , 2003 .

[44]  M. Kim,et al.  Non-destructive evaluation of bacteria-infected watermelon seeds using visible/near-infrared hyperspectral imaging. , 2016, Journal of the science of food and agriculture.