Abstract
This chapter presents hyperspectral imaging of fluorescence for nonin-vasive detection of tumorous tissue on mouse skin. Hyperspectral imaging sensors collect two-dimensional (2D) image data of an object in a number of narrow, adjacent spectral bands. This high-resolution measurement of spectral information reveals a continuous emission spectrum for each image pixel useful for skin tumor detection. The hyperspectral image data used in this study are fluorescence intensities of a mouse sample consisting of 21 spectral bands in the visible spectrum of wavelengths ranging from 440 to 640 nm. Fluorescence signals are measured using a laser excitation source with the center wavelength of 337 nm. An acousto-optic tunable filter is used to capture individual spectral band images at a 10-nm resolution. All spectral band images are spatially registered with the reference band image at 490 nm to obtain exact pixel correspondences by compensating the offsets caused during the image capture procedure. The support vector machines with polynomial kernel functions provide decision boundaries with a maximum separation margin to classify malignant tumor and normal tissue from the observed fluorescence spectral signatures for skin tumor detection.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Chapter's References
Geller, D. Miller, G. Annas, M. Demierre, B. Gilchrest, and H. Koh, Melanoma incidence and mortality among U.S. whites, 1969–1999,Journal of the American Medical Association, 288(14):1719–1720, 2002.
Cancer Facts and Figures 2005. American Cancer Society, Atlanta, 2005.
D. Landgrebe, Hyperspectral image data analysis as a high dimensional signal processing problem,IEEE Signal Processing Magazine19(1):17–28, 2002.
K. Rajpoot, N. Rajpoot, and M. Turner,Hyperspectral Colon Tissue Cell Classification. SPIE Medical Imaging, San Diego, 2004.
D. Ferris, R. Lawhead, E. Dickman, N. Hotzapple, J. Miller, S. Grogan, S. Bambot, A. Agrawal, and M. Faupel, Multimodal hyperspectral imaging for the noninvasive diagnosis of cervical neoplasia,Journal of Lower Genital Tract Disease5(2):65–72, 2001.
S.G. Kong, Y.R. Chen, I. Kim, and M.S. Kim, Analysis of hyperspectral fluorescence images for poultry skin tumor inspection,Applied Optics43(4):824–833, 2004.
I. Kim, M.S. Kim, Y.R. Chen, and S.G. Kong, Detection of skin tumors on chicken carcasses using hyperspectral fluorescence imaging,Transactions of the American Society of Agricultural Engineers47(5):1785–1792, 2004.
V. Vapnik,Statistical Learning Theory. Wiley, New York, 1998.
N. Cristianini and J. Shawe-Taylor,An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, New York, 2000.
T. Vo-Dinh, D.L. Stokes, M. Wabuyele, M.E. Martin, J.M. Song, R. Jagannathan, E. Michaud, R.J. Lee, and X. Pan, Hyperspectral imaging system for in vivo optical diagnostics,IEEE Engineering in Medicine and Biology23:40–59, 2004.
S.G. Kong, Z. Du, M. Martin, and T. Vo-Dinh, Hyperspectral fluorescence image analysis for use in medical analysis,Proceedings of the SPIE Conference on Biomedical Optics, San Jose, January 2005.
F. Moreau, S.M. Moreau, D.M. Hueber, and T. Vo-Dinh, Fiber-optic remote multisensor system based on an acousto-optic tunable filter (AOTF),Applied Spectroscopy50:1295, 1996.
I.-C. Chang, Electronically tuned imaging spectrometer using acousto-optic tunable filter,Proceedings of the SPIE International Society for Optical Engineering1703:24, 1992.
S.G. Kong, M. Martin, and T. Vo-Dinh, Hyperspectral fluorescence imaging for mouse skin tumor detectionETRI Journal28(6):770–776, 2006.
B. Albers, J. DiBenedetto, S. Lutz, and C. Purdy, More efficient environmental monitoring with laser-induced fluorescence imaging,Biophotonics International Magazine2(6):42–54, 1995.
R.H. Yuhas, A.F.H. Goetz, and J.W. Boardman, Discrimination among semiarid landscape endmembers using the spectral angle mapper (SAM) algorithm,Third Annual JPL Airborne Geoscience Workshop, JPL Publication 92–14 1:147–149, 1992.
R.N. Clark, G.A. Swayze, A. Gallagher, N. Gorelick, and F.A. Kruse, Mapping with imaging spectrometer data using the complete band shape least-squares algorithm simultaneously fit to multiple spectral features from multiple materials,Proceedings of the Third Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) Workshop, JPL Publication 91–28, pp. 2–3, 1991.
F. Roli and G. Fumera, Support vector machines for remote-sensing image classification,Proceedings of SPIE4170: 160–166, 2001.
F. Melangi, and L. Bruzzone, Classification of hyperspectral remote sensing images with support vector machines,IEEE Transactions on Geoscience and Remote Sensing42(8):1778– 1790, 2004.
S. Abe,Support Vector Machines for Pattern Classification. Springer-Verlag, New York, 2005.
Z. Du, M.K. Jeong, and S.G. Kong, Band selection of hyperspectral images for automatic detection of poultry skin tumors,IEEE Transactions on Automation Science and Engineering4(3):332–339, 2007.
C. Chang, Q. Du, T. Sun, and M. Althouse, A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification,IEEE Transactions on Geo-science and Remote Sensing37(6):2631–2641, 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kong, S.G., Park, LJ. (2009). Hyperspectral Image Analysis for Skin Tumor Detection. In: Hammoud, R.I. (eds) Augmented Vision Perception in Infrared. Advances in Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-84800-277-7_7
Download citation
DOI: https://doi.org/10.1007/978-1-84800-277-7_7
Publisher Name: Springer, London
Print ISBN: 978-1-84800-276-0
Online ISBN: 978-1-84800-277-7
eBook Packages: Computer ScienceComputer Science (R0)