Open AccessOptical configuration of pigmented lesion detection by frequency analysis of skin speckle patterns
Author(s) -
Yael Bishitz,
Nisan Ozana,
Ariel Schwarz,
Yevgeny Beiderman,
Javier Garcı́a,
Zeev Zalevsky
Publication year - 2016
Publication title -
biomedical optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.362
H-Index - 86
ISSN - 2156-7085
DOI - 10.1364/boe.7.001003
Subject(s) - speckle pattern , false positive paradox , computer science , artificial intelligence , speckle noise , signature (topology) , optics , computer vision , pattern recognition (psychology) , physics , mathematics , geometry
In this paper we present a novel approach of realizing a safe, simple, and inexpensive sensor applicable to pigmented lesions detection. The approach is based on temporal tracking of back-reflected secondary speckle patterns generated while illuminating the affected area with a laser and applying periodic pressure to the surface via a controlled vibration source. When applied to pigmented lesions, the technique is superior to visual examination in avoiding many false positives and resultant unnecessary biopsies. Applying a series of different vibration frequencies at the examined tissue and analyzing the 2-D time varying speckle patterns in response to the applied periodic pressure creates a unique signature for each and different pigmented lesion. Analyzing these signatures is the first step toward detection of malignant melanoma. In this paper we present preliminary experiments that show the validity of the developed sensor for the classification of pigmented lesions.