Skip to main content

Elastic and collagen fibers discriminant analysis using H&E stained hyperspectral images


Hematoxylin and eosin (H&E) stain is one of the most common specimen staining methods in pathology diagnosis due to the capability to show the morphological structure of tissue. However, the appearance of the specific component, i.e., elastic fibers might not be recognized easily because have similar color and pattern with ones of collagen fibers. To distinguish these two components, Verhoeff’s Van Gieson (EVG) staining method is commonly used. Nevertheless, procedures of EVG stain are more complex and expensive than H&E stain. In this study, we investigate the possibility to distinguish elastic and collagen fibers from H&E stained images by applying spectral image analysis based on hyperspectral images. With experiments, we measure the transmittance spectral of 61-band H&E stained hyperspectral image, which are converted into absorbance spectral of hematoxylin, eosin, and red blood cell. As many as 3000 sampling pixels both from RGB and hyperspectral images of HE stained specimens were trained using Linear Discriminant Analysis (LDA) to get a discriminant function to classify elastic and collagen components in H&E RGB and H&E hyperspectral images. We conducted verification based on leave-one-out cross-validation of six data sets for evaluation. The verification result both visually and quantitatively compared to EVG stained image shows that the usage of hyperspectral images performs better than RGB images.

This is a preview of subscription content, access via your institution.

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


  1. Uitto, J., et al.: Elastin in diseases. J. Invest. Dermatol. 79, 160s–168s (1982)

    Article  Google Scholar 

  2. Lakiotaki, E., et al.: Vascular and Ductal Elastatic Change in Pancreatic Cancer, Acta Pathologica, Microbiologica et Immunologica Scandinavica. Wiley, New York (2015)

    Google Scholar 

  3. Piesik, B., Zimmerman, G.: Determination of ocean reflectance by multispectral remote sensing. Acta Astronaut. 11, 349–351 (1984)

    ADS  Article  Google Scholar 

  4. Farkas, D., Du, C., Fisher, G., Lau, C., Niu, W., Wachman, E.S., et al.: Noninvasive image acquisition and advance processing in optical bioimaging. Comput. Med. Imaging Graph. 22, 89–102 (1998)

    Article  Google Scholar 

  5. Wilson, B.C., Jacques, S.L.: Optical reflectance and transmittance of tissues: principles and applications. IEEE J. Quantum Electron. 26, 2186–2198 (1990)

    ADS  Article  Google Scholar 

  6. Lu, G., et al.: Detection of head and neck cancer in surgical specimens using quantitative hyperspectral imaging. Clin. Cancer Res. 23(18), 5426–5436 (2017)

    Article  Google Scholar 

  7. Bautista, P.A.: Digital staining for multispectral images of pathological tissue specimens based on combined classification of spectral transmittance. Comput. Med. Imaging Graph. 29, 649–657 (2005)

    Article  Google Scholar 

  8. Omucheni, D.L., et al.: Application of principal component analysis to multispectral-multimodal optical image analysis for malaria diagnostics. Malar. J. 13, 485 (2014)

    Article  Google Scholar 

  9. Septiana, L., et al.: Staining Adjustment of Dye Amount to Clarify the Appearance of Fiber, Nuclei, and Cytoplasm in HE-stained Pathological Kidney Tissue Image, International Multidiciplinary Conference and Productivity and Sustainability. Ukrida Press, Jakarta (2017)

    Google Scholar 

  10. Abe, T., Murakami, Y., Yamaguchi, M., et al.: Color correction of pathological images based on dye amount quantification. Opt. Rev. 12, 293 (2005)

    Article  Google Scholar 

  11. Yang, T.-Y., Chen. C.C.: Data visualization by PCA, LDA, and ICA. In: The Annual Conference on Engineering and Technology ACEAT-493, 4–6 November (2015)

  12. McLachlan, G.J.: Discriminant Analysis and Statistical Pattern Recognition. Wiley Interscience, New York (2004). (ISBN: 0-471-69115-1)

    MATH  Google Scholar 

  13. Abe, T., et al.: Quantification of collagen and elastic fibers using whole slide images of liver biopsy specimens. Pathol. Int. 63(6), 305–310 (2013)

    Article  Google Scholar 

  14. StatSoft, Inc.: Electronic Statistics Textbook. StatSoft, Tulsa (2013). Accessed on 30 Nov 2018

  15. MathWorks (2018). Statistic and machine learning toolbox: user’s guide (R2018b). Retrieved 30 Nov 2018

  16. Fisher, R.A.: The use of multiple measurements in taxonomic problems. Ann. Eugen. 7, 179–188 (1936)

    Article  Google Scholar 

  17. Altman, D.G., Bland, J.M.: Diagnostic tests. 1: sensitivity and specificity. BMJ 308(6943), 1552 (1994). (PMC 2540489. PMID 8019315)

    Article  Google Scholar 

  18. Jawien, W.: Searching for a n optimal AUC estimation method: a never-ending task. J. Pharmacokinet. Parmacodynamics 41(6), 655–673 (2014)

    Article  Google Scholar 

Download references


This work is supported by Indonesia Endowment Fund for Education (LPDP) and Japan Society for The Promotion of Science (JSPS)—Indonesian Institute of Science (LIPI) Joint Research Program.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Lina Septiana.

Additional information

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Septiana, L., Suzuki, H., Ishikawa, M. et al. Elastic and collagen fibers discriminant analysis using H&E stained hyperspectral images. Opt Rev 26, 369–379 (2019).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


  • Pathology
  • Hyperspectral image
  • Discriminant analysis
  • Classification