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...

Full description

Saved in:
Bibliographic Details
Main Authors: Shengnan Ai, Chengming Wang, Wenxin Zhang, Wenchao Liao, Juicheng Hsieh, Zhenyu Chen, Bin He, Xiao Zhang, Ning Zhang, Ying Gu, Ping Xue
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8896069/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849417283502342144
author Shengnan Ai
Chengming Wang
Wenxin Zhang
Wenchao Liao
Juicheng Hsieh
Zhenyu Chen
Bin He
Xiao Zhang
Ning Zhang
Ying Gu
Ping Xue
author_facet Shengnan Ai
Chengming Wang
Wenxin Zhang
Wenchao Liao
Juicheng Hsieh
Zhenyu Chen
Bin He
Xiao Zhang
Ning Zhang
Ying Gu
Ping Xue
author_sort Shengnan Ai
collection DOAJ
description 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.
format Article
id doaj-art-c90cf3e40ca9415683c636bfdd921695
institution Kabale University
issn 1943-0655
language English
publishDate 2019-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-c90cf3e40ca9415683c636bfdd9216952025-08-20T03:32:54ZengIEEEIEEE Photonics Journal1943-06552019-01-0111611110.1109/JPHOT.2019.29529038896069Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography ImageShengnan Ai0https://orcid.org/0000-0002-5070-3906Chengming Wang1Wenxin Zhang2https://orcid.org/0000-0003-0568-7369Wenchao Liao3Juicheng Hsieh4Zhenyu Chen5Bin He6Xiao Zhang7Ning Zhang8Ying Gu9Ping Xue10https://orcid.org/0000-0002-2210-7402State Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaSchool of Life Science, Beijing Institute of Technology, Beijing, ChinaInstitute of Forensic Science, Ministry of Public Security, Beijing, ChinaDepartment of Laser Medicine, Chinese PLA General Hospital, Beijing, ChinaState Key Laboratory of Low-Dimensional Quantum Physics, Department of Physics, Tsinghua University, Beijing, ChinaPort 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.https://ieeexplore.ieee.org/document/8896069/Port wine stainoptical coherence tomographymachine learning.
spellingShingle Shengnan Ai
Chengming Wang
Wenxin Zhang
Wenchao Liao
Juicheng Hsieh
Zhenyu Chen
Bin He
Xiao Zhang
Ning Zhang
Ying Gu
Ping Xue
Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image
IEEE Photonics Journal
Port wine stain
optical coherence tomography
machine learning.
title Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image
title_full Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image
title_fullStr Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image
title_full_unstemmed Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image
title_short Machine-Learning Classification of Port Wine Stain With Quantitative Features of Optical Coherence Tomography Image
title_sort machine learning classification of port wine stain with quantitative features of optical coherence tomography image
topic Port wine stain
optical coherence tomography
machine learning.
url https://ieeexplore.ieee.org/document/8896069/
work_keys_str_mv AT shengnanai machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT chengmingwang machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT wenxinzhang machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT wenchaoliao machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT juichenghsieh machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT zhenyuchen machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT binhe machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT xiaozhang machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT ningzhang machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT yinggu machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage
AT pingxue machinelearningclassificationofportwinestainwithquantitativefeaturesofopticalcoherencetomographyimage