By Topic

Analysis of diffuse reflectance spectra of various skin conditions by principal component method

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Shanthi Prince ; Department of Electronics and Communication Engineering, SRM University, SRM Nagar, Kattankulathur 603203, Tamil Nadu, India ; S. Malarvizhi

Different skin and sub-surface tissues have distinct or unique reflectance pattern which help us differentiate normal and cancerous tissues. Optical means of characterizing tissues have gained importance due to its noninvasive nature. Spectral characteristics of the components provide useful information to identify the components, because different chromophores have different spectroscopic responses to electromagnetic waves of a certain energy band. Even though different tissues have different reflectance spectra, visually they all look alike. The large volumes of multidimensional data obtained are analyzed using a principal component analysis (PCA) method to quickly and objectively extract any useful signature associated with a skin disorder under study. An optical fiber spectrometer is set up for collection of diffuse reflectance data from different skin conditions. The method involves exposure of skin surface to white light produced by an incandescent source. These back scattered photons emerging from various layers of tissue are detected by spectrometer resulting in diffuse reflectance data. For the present study different skin conditions like warts, vitiligo, thrombus (due to injury) and angioma are chosen. The spectral data obtained from the scan are plotted and compared. More or less the shapes of the spectral curves for various skin conditions resemble. In order to characterize and differentiate different diseased tissue principal component analysis method is carried out. The preliminary results show that the proposed principal component analysis method is able to enhance the peculiar characteristics of the diseased diffuse reflectance spectra.

Published in:

2009 International Conference on Biomedical and Pharmaceutical Engineering

Date of Conference:

2-4 Dec. 2009