Utilization of multi-spectral images in photodynamic diagnosis

Authors:
Andrzej Zacher
Affiliations:
The Silesian University of Technology, Institute of Informatics, Gliwice, Poland
Venue:
ICCVG'10 Proceedings of the 2010 international conference on Computer vision and graphics: Part II
Year:
2010

Citing 1
Cited 1

Physically Based Rendering: From Theory to Implementation

Physically Based Rendering: From Theory to Implementation

The application of orthogonal subspace projection in multi-spectral images processing for cancer recognition in human skin tissue

ICCCI'12 Proceedings of the 4th international conference on Computational Collective Intelligence: technologies and applications - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces multi-spectral images for healthy and cancerous parts of human skin. It compares light spectrum calculated from those images with spectrum obtained from simulation. First the mathematical model of tissue and Monte Carlo algorithm of light propagation in turbid media is presented. This theory was then extended to imitate the fluorescence phenomenon, necessary for cancer recognition. Then the processing method of non-normalized multi-spectral images was described. Finally both results were compared to confirm that the assumed model is correct. Having all those information it will be possible to simulate such environment, which applied into reality, would make the cancer diagnosis much faster.