Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image

Port wine stain (PWS) is the benign congenital capillary malformation of skin, occurring in 0.3% to 0.5% of the population. In this paper, we build two automated support vector machine (SVM) based classifiers by extracting quantitative features from normal and PWS tissue images recorded by optical c...

Full description

Saved in:
Bibliographic Details
Published inIEEE photonics journal Vol. 11; no. 6; pp. 1 - 11
Main Authors Ai, Shengnan, Gu, Ying, Xue, Ping, Wang, Chengming, Zhang, Wenxin, Liao, Wenchao, Hsieh, Juicheng, Chen, Zhenyu, He, Bin, Zhang, Xiao, Zhang, Ning
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.12.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Classifiers
Feature extraction
Lesions
Machine learning
Optical Coherence Tomography
Port wine stain
Sensitivity
Skin
Support vector machines
Tomography
Online AccessGet full text

Cover

More Information
Summary:Port wine stain (PWS) is the benign congenital capillary malformation of skin, occurring in 0.3% to 0.5% of the population. In this paper, we build two automated support vector machine (SVM) based classifiers by extracting quantitative features from normal and PWS tissue images recorded by optical coherence tomography (OCT). We use both full feature set and simplified feature set for training. Accuracy of 92.7%, sensitivity of 92.3% and specificity of 93.8% were obtained for classifier with full feature set. Accuracy of 92.7%, sensitivity of 94.9% and specificity of 87.5% were obtained for classifier with simplified feature set. Our results suggest that extracting quantitative features from optical coherence tomographic images could be a potentially powerful method for accurately and automatically identifying PWS margins during laser therapy.
ISSN:1943-0655
1943-0655
1943-0647
DOI:10.1109/JPHOT.2019.2952903