Skip to main content
SpringerLink
Log in

Evaluation of the benefits of combined reflection and transmission hyperspectral imaging data through disease detection and quantification in plant–pathogen interactions

  • Original Article
  • Published:
Journal of Plant Diseases and Protection Aims and scope Submit manuscript

Abstract

Previous studies investigating the performance of transmission and reflection datasets for disease detection showed inconsistent results. Within the studies, the performance of transmission imaging varied significantly for the detection of biotroph and necrotrophy plant pathogens, while reflection imaging showed excellent results in both studies. The current study explores the hypothesis that the disparity between these results might be correlated with the different interactions of the respective pathogens with the host plants and the way light interacts with the plant tissue. Pyrenophora teres f. teres and Puccinia hordei—the causative agents of net blotch and brown rust in barley—have been investigated with focus on early-stage detection and quantification (disease severity) of symptoms. Datasets of hyperspectral imaging time-series measurements were analysed through application of multiple data analysis methods (support vector machines; principal component analysis with following distance classifier; spectral decomposition) in order to compare the performance of both datasets for the detection of disease symptoms. It could be shown that transmittance-based brown rust detection (e.g. 12% disease severity) is outperformed by reflectance-based detection (e.g. 36% disease severity) regardless of the algorithm. However, both the detection and quantification of brown rust through transmittance were more accurate than those of powdery mildew in earlier studies. Transmittance and reflectance performed similar for the detection of net blotch disease during the experiments (~ 1% disease severity for reflection and transmission). Each data analysis method outperformed manual rating in terms of disease detection (e.g. 15% disease severity according to manual rating and 36% through support vector machines for rust reflection data). Except for the application of a distance classifier on net blotch transmittance data, it could be shown that pixels, which were classified as symptomatic through the data analysis methods while estimated to represent healthy tissue during manual rating, correlate with areas at the edges of manually detected symptoms. The results of this study support the hypothesis that transmission imaging results are highly correlated with the type of plant–pathogen interaction of the respective pathogens, offering new insights into the nature of transmission-based hyperspectral imaging and its application range.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Data availability

The datasets, which were generated and analysed during the study, are not publicly available due to their large sizes. However, they can be provided by the corresponding author upon request.

Code availability

Fluxtrainer and Envi software are commercially available. Matlab scripts can be provided by the corresponding author upon request.

References

  • Alisaac E, Behmann J, Kuska MT, Dehne H-W, Mahlein A-K (2018) Hyperspectral quantification of wheat resistance to Fusarium head blight: comparison of two Fusarium species. Eur J Plant Pathol 152:869–884

    Article  Google Scholar 

  • AlSuwaidi A, Grieve B, Yin H (2018) Feature-ensemble-based novelty detection for analyzing plant hyperspectral datasets. IEEE J Select Top Appl Earth Observ Remote Sens 11:1041–1055

    Article  Google Scholar 

  • Barreto A, Paulus S, Varrelmann M, Mahlein A-K (2020) Hyperspectral imaging of symptoms induced by Rhizoctonia solani in sugar beet: comparison of input data and different machine learning algorithms. J Plant Dis Prot 127:441–451

    Article  Google Scholar 

  • Behmann J, Bohnenkamp D, Paulus S, Mahlein A-K (2018) Spatial referencing of hyperspectral images for tracing of plant disease symptoms. J Imaging 4:143

    Article  Google Scholar 

  • Bergsträsser S, Fanourakis D, Schmittgen S, Cendrero-Mateo MP, Jansen M, Scharr H, Rascher U (2015) HyperART: non-invasive quantification of leaf traits using hyperspectral absorption-reflectance-transmittance imaging. Plant Methods 11:1–17

    Article  Google Scholar 

  • Bhat R, Miklis M, Schmelzer E, Schulze-Lefert P, Panstruga R (2005) Recruitment and interaction dynamics of plant penetration resistance components in a plasma membrane microdomain. Proc Natl Acad Sci USA 102:3135–3140. https://doi.org/10.1073/pnas.0500012102

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Brakke TW (1994) Specular and diffuse components of radiation scattered by leaves. Agric Meteorol 71:283–295

    Article  Google Scholar 

  • Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297

    Google Scholar 

  • Dean R, Van Kan JAL, Pretorius ZA, Hammond-Kosack KE, Pietro AD, Spanu PD, Rudd JJ, Dickman M, Kahmann R, Ellis J, Foster GD (2012) The top 10 fungal pathogens in molecular plant pathology. Mol Plant Pathol 13:414–430. https://doi.org/10.1111/j.1364-3703.2011.00783.x

    Article  PubMed  PubMed Central  Google Scholar 

  • Dhillon IS, Modha DS (2001) Concept decompositions for large sparse text data using clustering. Mach Learn 42:143–175

    Article  Google Scholar 

  • Feng X, Zhan Y, Wang Q, Yang X, Yu C, Wang H, Tang Z, Jiang D, Peng C, He Y (2020) Hyperspectral imaging combined with machine learning as a tool to obtain high-throughput plant salt-stress phenotyping. Plant J 101:1448–1461

    Article  CAS  Google Scholar 

  • Golhani K, Balasundram SK, Vadamalai G, Pradhan B (2018) A review of neural networks in plant disease detection using hyperspectral data. Inf Process Agric 5:354–371

    Google Scholar 

  • Hack H et al (1992) Einheitliche codierung der phänologischen entwicklungsstadien mono-und dikotyler pflanzen–erweiterte BBCH-Skala. Allgemein. Nachrichtenbl Deut Pflanzenschutzd 44(12):265–270

    Google Scholar 

  • Heckmann D, Schluter U, Weber APM (2017) Machine learning techniques for predicting crop photosynthetic capacity from leaf reflectance spectra. Mol Plant 10:878–890

    Article  CAS  Google Scholar 

  • Hinze K, Thompson RD, Ritter E, Salamini F, Schulze-Lefert P (1991) Restriction fragment length polymorphism-mediated targeting of the ml-o resistance locus in barley (Hordeum vulgare). Proc Nat AcadSci 88(9):3691–3695. https://doi.org/10.1073/pnas.88.9.3691

    Article  CAS  Google Scholar 

  • Hovi A, Forsström P, Mõttus M, Rautiainen M (2018) Evaluation of accuracy and practical applicability of methods for measuring leaf reflectance and transmittance spectra. Remote Sens 10(1):25. https://doi.org/10.3390/rs10010025

    Article  Google Scholar 

  • Keshava N, Mustard JF (2002) Spectral unmixing. IEEE Signal Process Mag 19:44–57

    Article  Google Scholar 

  • Kuska M, Wahabzada M, Leucker M, Dehne H-W, Kersting K, Oerke EC, Steiner U, Mahlein A-K (2015) Hyperspectral phenotyping on the microscopic scale: towards automated characterization of plant-pathogen interactions. Plant Methods 11:28

    Article  Google Scholar 

  • Leucker M, Wahabzada M, Kersting K, Peter M, Beyer W, Steiner U, Mahlein A-K, Oerke E-C (2016) Hyperspectral imaging reveals the effects of sugar beet QTLs on Cercospora leaf spot resistance. Funct Plant Biol 44:1–9

    Article  Google Scholar 

  • Liu Z, Ellwood SR, Oliver RP, Friesen TL (2011) Pyrenophora teres: profile of an increasingly damaging barley pathogen. Mol Plant Pathol 12:1–19

    Article  Google Scholar 

  • Mahalanobis A, Vijaya Kumar BVK, Sims SRF (1996) Distance-classifier correlation filters for multiclass target recognition. Appl Opt 35:3127–3133

    Article  CAS  Google Scholar 

  • Mahlein A-K, Steiner U, Hillnhütter C, Dehne H-W, Oerke E-C (2012) Hyperspectral imaging for small-scale analysis of symptoms caused by different sugar beet diseases. Plant Methods 8:3

    Article  Google Scholar 

  • Mahlein A-K, Kuska M, Thomas S, Wahabzada M, Behmann J, Rascher U, Kersting K (2019) Quantitative and qualitative phenotyping of disease resistance of crops by hyperspectral sensors: seamless interlocking of phytopathology, sensors, and machine learning is needed! Curr Opin Plant Biol 50:156–162

    Article  CAS  Google Scholar 

  • Nansen C (2018) Penetration and scattering—Two optical phenomena to consider when applying proximal remote sensing technologies to object classifications. PLOS ONE 13(10):e0204579. https://doi.org/10.1371/journal.pone.0204579

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Oerke EC (2020) Remote sensing of diseases. Annu Rev Phytopathol 58:225–252

    Article  CAS  Google Scholar 

  • Rangel LI, Spanner RE, Ebert MK, Pethybridge SJ, Stukenbrock EH, de Jonge R, Secor GA, Bolton MD (2020) Cercospora beticola: the intoxicating lifestyle of the leaf spot pathogen of sugar beet. Mol Plant Pathol 21:1020–1041. https://doi.org/10.1111/mpp.12962

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Roitsch T, Cabrera-Bosquet L, Fournier A, Ghamkhar K, Jiménez-Berni J, Pinto F, Ober ES (2019) Review: new sensors and data-driven approaches—a path to next generation phenomics. Plant Sci 282:2–10

    Article  CAS  Google Scholar 

  • Savitzky A, Golay M (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36:1627–1639

    Article  CAS  Google Scholar 

  • Singh AK, Ganapathysubramanian B, Sarkar S, Singh A (2018) Deep learning for plant stress phenotyping: trends and future perspectives. Trends Plant Sci 23:883–898

    Article  CAS  Google Scholar 

  • Steinkamp M, Martin S, Hoefert L, Ruppel E (1979) Ultrastructure of lesions produced by Cercospora beticola in leaves of Beta vulgaris. Physiol Plant Pathol 15:13–26

    Article  Google Scholar 

  • Sun J, Kunnemeyer R, McGlone A, Tomer N (2018) Optical properties of healthy and rotten onion flesh from 700 to 1000 nm. Postharvest Biol Technol 140:1–10

    Article  Google Scholar 

  • Thomas S, Wahabzada M, Kuska M, Rascher U, Mahlein A-K (2017) Observation of plant–pathogen interaction by simultaneous hyperspectral imaging reflection and transmission measurements. Funct Plant Biol 44:23–34

    Article  CAS  Google Scholar 

  • Ugarte Fajardo J, Bayona Andrade O, Criollo Bonilla R, Cevallos-Cevallos J, Mariduena-Zavala M, Ochoa Donoso D, Vicente Villardón JL (2020) Early detection of black Sigatoka in banana leaves using hyperspectral images. Appl Plant Sci 8:e11383

    Article  Google Scholar 

  • Voegele RT (2006) Uromyces fabae: development, metabolism, and interactions with its host Vicia faba. FEMS Microbiol Lett 259:165–173

    Article  CAS  Google Scholar 

  • Vogelmann TC (1989) Penetration of light into plants. Photochem Photobiol 50:895–902

    Article  Google Scholar 

  • Wahabzada M, Mahlein A-K, Bauckhage C, Steiner U, Oerke E-C, Kersting K (2015) Metro maps of plant disease dynamics—automated mining of differences using hyperspectral images. PLoS ONE 10(1):e0116902. https://doi.org/10.1371/journal.pone.0116902

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  • Wold S, Esbensen K, Geladi P (1987) Principal component analysis. Chemom Intell Lab Syst 2:37–52

    Article  CAS  Google Scholar 

  • Zhang H, Salo D, Kim DM, Komarov S, Tai Y-C, Berezin MY (2016) Penetration depth of photons in biological tissues from hyperspectral imaging in shortwave infrared in transmission and reflection geometries. J Biomed Opt 21:126006

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank the members of the INRES‑Plant Protection and Plant Diseases and IBG2: Plant Sciences for their support during the experiments and fruitful discussions. Furthermore, the authors would like to thank the reviewers for helpful comments and constructive critique of the article. Experiments in this study were conducted at the INRES of the University of Bonn, as well as the IGB2: Plant sciences of the Research Centre Jülich as part of the CROP.SENSe.net program.

Funding

Funding was provided by the German Federal Ministry of Education and Research (BMBF) within the scope of the competitive grants program “Networks of excellence in agricultural and nutrition research—CROP.SENSe.net” (Funding code: 0315529), junior research group “Hyperspectral phenotyping of resistance reactions of barley,” within the German‑Plant‑Phenotyping Network (project identification number: 031A053), and by the Daimler and Benz foundation. Uwe Rascher and Anne-Katrin Mahlein are partially funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy—EXC 2070-390732324.

Author information

Authors and Affiliations

  1. Department of Phytopathology (360a), Institute of Phytomedicine (360), University of Hohenheim, 70599, Stuttgart, Germany

    Stefan Thomas

  2. INRES Plant Disease, University of Bonn, 53115, Bonn, Germany

    Jan Behmann

  3. IBG2: Plant Sciences, Research Centre Jülich, 52428, Jülich, Germany

    Uwe Rascher

  4. Institute of Sugar Beet Research (IfZ), 37079, Göttingen, Germany

    Anne-Katrin Mahlein

Authors
  1. Stefan Thomas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jan Behmann
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Uwe Rascher
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Anne-Katrin Mahlein
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

ST, UR and AKM designed the study and refined the hyperspectral measurement system. ST performed the hyperspectral measurements. ST and JB performed the statistical analysis. ST drafted the manuscript with support from JB, UR and AKM. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Anne-Katrin Mahlein.

Ethics declarations

Conflicts of interest

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file 1 (TIFF 19842 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Thomas, S., Behmann, J., Rascher, U. et al. Evaluation of the benefits of combined reflection and transmission hyperspectral imaging data through disease detection and quantification in plant–pathogen interactions. J Plant Dis Prot 129, 505–520 (2022). https://doi.org/10.1007/s41348-022-00570-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41348-022-00570-2

Keywords

Search

Navigation