Open AccessClassification of basal cell carcinoma in human skin using machine learning and quantitative features captured by polarization sensitive optical coherence tomography
Author(s) -
Tahereh Marvdashti,
Lian Duan,
Sumaira Z. Aasi,
Jean Y. Tang,
Audrey K. Bowden
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.7.003721
Subject(s) - optical coherence tomography , basal cell carcinoma , artificial intelligence , computer science , classifier (uml) , skin cancer , pattern recognition (psychology) , human skin , tomography , support vector machine , basal cell , pathology , medicine , radiology , cancer , biology , genetics
We report the first fully automated detection of basal cell carcinoma (BCC), the most commonly occurring type of skin cancer, in human skin using polarization-sensitive optical coherence tomography (PS-OCT). Our proposed automated procedure entails building a machine-learning based classifier by extracting image features from the two complementary image contrasts offered by PS-OCT, intensity and phase retardation (PR), and selecting a subset of features that yields a classifier with the highest accuracy. Our classifier achieved 95.4% sensitivity and specificity, validated by leave-one-patient-out cross validation (LOPOCV), in detecting BCC in human skin samples collected from 42 patients. Moreover, we show the superiority of our classifier over the best possible classifier based on features extracted from intensity-only data, which demonstrates the significance of PR data in detecting BCC.