Translator Disclaimer
6 April 2016 Statistical image segmentation for the detection of skin lesion borders in UV fluorescence excitation
Author Affiliations +
Abstract
The skin contains several fluorescent molecules or fluorophores that serve as markers of structure, function and composition. UV fluorescence excitation photography is a simple and effective way to image specific intrinsic fluorophores, such as the one ascribed to tryptophan which emits at a wavelength of 345 nm upon excitation at 295 nm, and is a marker of cellular proliferation. Earlier, we built a clinical UV photography system to image cellular proliferation. In some samples, the naturally low intensity of the fluorescence can make it difficult to separate the fluorescence of cells in higher proliferation states from background fluorescence and other imaging artifacts -- like electronic noise. In this work, we describe a statistical image segmentation method to separate the fluorescence of interest. Statistical image segmentation is based on image averaging, background subtraction and pixel statistics. This method allows to better quantify the intensity and surface distributions of fluorescence, which in turn simplify the detection of borders. Using this method we delineated the borders of highly-proliferative skin conditions and diseases, in particular, allergic contact dermatitis, psoriatic lesions and basal cell carcinoma. Segmented images clearly define lesion borders. UV fluorescence excitation photography along with statistical image segmentation may serve as a quick and simple diagnostic tool for clinicians.
Conference Presentation
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Antonio Ortega-Martinez, Juan Pablo Padilla-Martinez, and Walfre Franco "Statistical image segmentation for the detection of skin lesion borders in UV fluorescence excitation", Proc. SPIE 9711, Imaging, Manipulation, and Analysis of Biomolecules, Cells, and Tissues IX, 97111B (6 April 2016); https://doi.org/10.1117/12.2208741
PROCEEDINGS
6 PAGES + PRESENTATION

SHARE
Advertisement
Advertisement
Back to Top