Comparison of preprocessing techniques to reduce nontissue-related variations in hyperspectral reflectance imaging.

Journal: Journal of biomedical optics
Published Date:

Abstract

SIGNIFICANCE: Hyperspectral reflectance imaging can be used in medicine to identify tissue types, such as tumor tissue. Tissue classification algorithms are developed based on, e.g., machine learning or principle component analysis. For the development of these algorithms, data are generally preprocessed to remove variability in data not related to the tissue itself since this will improve the performance of the classification algorithm. In hyperspectral imaging, the measured spectra are also influenced by reflections from the surface (glare) and height variations within and between tissue samples.

Authors

  • Mark Witteveen
    the Netherlands Cancer Institute, Surgical Oncology, Amsterdam, The Netherlands, Netherlands.
  • Hendricus J C M Sterenborg
    the Netherlands Cancer Institute, Surgical Oncology, Amsterdam, The Netherlands, Netherlands.
  • Ton G van Leeuwen
    Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.
  • Maurice C G Aalders
    Amsterdam UMC, University of Amsterdam, Cancer Center Amsterdam, Amsterdam Cardiovascular Sciences, Department of Biomedical Engineering and Physics, Amsterdam, The Netherlands, Netherlands.
  • Theo J M Ruers
  • Anouk L Post
    the Netherlands Cancer Institute, Surgical Oncology, Amsterdam, The Netherlands, Netherlands.