New Spectral Representation and Dissimilarity Measures Assessment for FTIR-spectra using Unsupervised Classification

Francisco Peñaranda, Fernando López-Mir, Valery Naranjo, Jesús Angulo, Lena Kastl, Juergen Schnekenburger

2015

Abstract

In this work, different combinations of dissimilarity coefficients and clustering algorithms are compared in order to separate FTIR data in different classes. For this purpose, a dataset of eighty five spectra of four types of sample cells acquired with two different protocols are used (fixed and unfixed). Five dissimilarity coefficients were assessed by using three types of unsupervised classifiers (K-means, K-medoids and Agglomerative Hierarchical Clustering). We introduce in particular a new spectral representation by detecting the signals´ peaks and their corresponding dynamics and widths. The motivation of this representation is to introduce invariant properties with respect to small spectra shifts or intensity variations. As main results, the dissimilarity measure called Spectral Information Divergence obtained the best classification performance for both treatment protocols when is used over the proposed spectral representation.

References

  1. Baker, M., Gazi, E., Brown, M., Shanks, J., Gardner, P., and Clarke, N. (2008). FTIR-based spectroscopic analysis in the identification of clinically aggressive prostate cancer. Br J Cancer, 99(11):1859-66.
  2. Bandyopadhyay, S. and Saha, S. (2013). Unsupervised Classification: Similarity Measures, Classical and Metaheuristic Approaches, and Applications. Springer.
  3. Berkhin, P. (2006). A survey of clustering data mining techniques. In Grouping multidimensional data, pages 25- 71. Springer.
  4. Carter, H. B., Albertsen, P., Barry, M., Etzioni, R., Freedland, S., Greene, K., Holmberg, L., Kantoff, P., Konety, B., Murad, M., Penson, D., and Zietman, A. (2013). Early detection of prostate cancer: AUA guideline. The Journal of Urology, 190(2):419 - 26.
  5. Chang, C.-I. (2003). Hyperspectral imaging: techniques for spectral detection and classification, volume 1. Springer.
  6. Jain, A. K. (2010). Data clustering: 50 years beyond kmeans. Pattern Recognition Letters, 31(8):651-666.
  7. Kendall, C., Isabelle, M., Bazant-Hegemark, F., Hutchings, J., Orr, L., Babrah, J., Baker, R., and Stone, N. (2009). Vibrational spectroscopy: a clinical tool for cancer diagnostics. Analyst, 134(6):1029-1045.
  8. Krafft, C., Codrich, D., Pelizzo, G., and Sergo, V. (2008). Raman and ftir microscopic imaging of colon tissue: a comparative study. Journal of biophotonics, 1(2):154- 169.
  9. Lasch, P. (2012). Spectral pre-processing for biomedical vibrational spectroscopy and microspectroscopic imaging. Chemometrics and Intelligent Laboratory Systems, 117:100-114.
  10. Lasch, P., Haensch, W., Naumann, D., and Diem, M. (2004). Imaging of colorectal adenocarcinoma using ft-ir microspectroscopy and cluster analysis. Biochimica et Biophysica Acta (BBA)-Molecular Basis of Disease, 1688(2):176-186.
  11. Nallala, J., Piot, O., Diebold, M.-D., Gobinet, C., Bouché, O., Manfait, M., and Sockalingum, G. D. (2014). Infrared and raman imaging for characterizing complex biological materials: A comparative morphospectroscopic study of colon tissue. Applied spectroscopy, 68(1):57-68.
  12. Petibois, C. and Deleris, G. (2006). Chemical mapping of tumor progression by FT-IR imaging: towards molecular histopathology. Trends in Biotechnology, 24(10):455 - 62.
  13. Rinnan, A., Berg, F. v. d., and Engelsen, S. B. (2009). Review of the most common pre-processing techniques for near-infrared spectra. TrAC Trends in Analytical Chemistry, 28(10):1201-1222.
  14. Soille, P. (2002). Morphological Image Analysis, volume Second edition. Springer.
Download


Paper Citation


in Harvard Style

Peñaranda F., López-Mir F., Naranjo V., Angulo J., Kastl L. and Schnekenburger J. (2015). New Spectral Representation and Dissimilarity Measures Assessment for FTIR-spectra using Unsupervised Classification . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015) ISBN 978-989-758-069-7, pages 172-177. DOI: 10.5220/0005188001720177


in Bibtex Style

@conference{biosignals15,
author={Francisco Peñaranda and Fernando López-Mir and Valery Naranjo and Jesús Angulo and Lena Kastl and Juergen Schnekenburger},
title={New Spectral Representation and Dissimilarity Measures Assessment for FTIR-spectra using Unsupervised Classification},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)},
year={2015},
pages={172-177},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005188001720177},
isbn={978-989-758-069-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2015)
TI - New Spectral Representation and Dissimilarity Measures Assessment for FTIR-spectra using Unsupervised Classification
SN - 978-989-758-069-7
AU - Peñaranda F.
AU - López-Mir F.
AU - Naranjo V.
AU - Angulo J.
AU - Kastl L.
AU - Schnekenburger J.
PY - 2015
SP - 172
EP - 177
DO - 10.5220/0005188001720177