Fully Automatic Prediction for Efficacy of Photodynamic Therapy in Clinical Port-Wine Stains Treatment: A Pilot Study

Shengnan Ai; Ping Xue; Chengming Wang; Wenxin Zhang; Jui Cheng Hsieh; Zhengyu Chen; Bin He; Xiao Zhang; Ning Zhang; Ying Gu

doi:10.1109/ACCESS.2020.2972275

Fully Automatic Prediction for Efficacy of Photodynamic Therapy in Clinical Port-Wine Stains Treatment: A Pilot Study

Shengnan Ai, Ping Xue^*, Chengming Wang, Wenxin Zhang, Jui Cheng Hsieh, Zhengyu Chen, Bin He, Xiao Zhang, Ning Zhang, Ying Gu

^*Corresponding author for this work

School of Medical and Technology

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

In this paper, we report a fully automatic method for the prediction of the treatment efficacy of photodynamic therapy during the clinical treatment in port-wine stains. Histogram of oriented gradients (HOG) features were extracted from optical coherence tomography images. Isolation forest (iForest) was used to build classifier based on these features, achieving a sensitivity of 84% and specificity of 91%. Our dataset consists of 336 PWS lesions of 121 patients. We aim to build a comprehensive computational model for the patients who respond positively to the photodynamic therapy, which could be used to sort and identify patients who respond poorly to photodynamic therapy before treatment and prevent them from unnecessary treatment.

Original language	English
Article number	8986618
Pages (from-to)	31227-31233
Number of pages	7
Journal	IEEE Access
Volume	8
DOIs	https://doi.org/10.1109/ACCESS.2020.2972275
Publication status	Published - 2020

Keywords

Anomaly detection
machine learning
optical coherence tomography
port-wine stain
support vector data description

Access to Document

10.1109/ACCESS.2020.2972275

Cite this

Ai, S., Xue, P., Wang, C., Zhang, W., Hsieh, J. C., Chen, Z., He, B., Zhang, X., Zhang, N., & Gu, Y. (2020). Fully Automatic Prediction for Efficacy of Photodynamic Therapy in Clinical Port-Wine Stains Treatment: A Pilot Study. IEEE Access, 8, 31227-31233. Article 8986618. https://doi.org/10.1109/ACCESS.2020.2972275

@article{6e0f2aa7d30c469db31ec940290b3af2,

title = "Fully Automatic Prediction for Efficacy of Photodynamic Therapy in Clinical Port-Wine Stains Treatment: A Pilot Study",

abstract = "In this paper, we report a fully automatic method for the prediction of the treatment efficacy of photodynamic therapy during the clinical treatment in port-wine stains. Histogram of oriented gradients (HOG) features were extracted from optical coherence tomography images. Isolation forest (iForest) was used to build classifier based on these features, achieving a sensitivity of 84% and specificity of 91%. Our dataset consists of 336 PWS lesions of 121 patients. We aim to build a comprehensive computational model for the patients who respond positively to the photodynamic therapy, which could be used to sort and identify patients who respond poorly to photodynamic therapy before treatment and prevent them from unnecessary treatment.",

keywords = "Anomaly detection, machine learning, optical coherence tomography, port-wine stain, support vector data description",

author = "Shengnan Ai and Ping Xue and Chengming Wang and Wenxin Zhang and Hsieh, {Jui Cheng} and Zhengyu Chen and Bin He and Xiao Zhang and Ning Zhang and Ying Gu",

note = "Publisher Copyright: {\textcopyright} 2013 IEEE.",

year = "2020",

doi = "10.1109/ACCESS.2020.2972275",

language = "English",

volume = "8",

pages = "31227--31233",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Fully Automatic Prediction for Efficacy of Photodynamic Therapy in Clinical Port-Wine Stains Treatment

T2 - A Pilot Study

AU - Ai, Shengnan

AU - Xue, Ping

AU - Wang, Chengming

AU - Zhang, Wenxin

AU - Hsieh, Jui Cheng

AU - Chen, Zhengyu

AU - He, Bin

AU - Zhang, Xiao

AU - Zhang, Ning

AU - Gu, Ying

PY - 2020

Y1 - 2020

N2 - In this paper, we report a fully automatic method for the prediction of the treatment efficacy of photodynamic therapy during the clinical treatment in port-wine stains. Histogram of oriented gradients (HOG) features were extracted from optical coherence tomography images. Isolation forest (iForest) was used to build classifier based on these features, achieving a sensitivity of 84% and specificity of 91%. Our dataset consists of 336 PWS lesions of 121 patients. We aim to build a comprehensive computational model for the patients who respond positively to the photodynamic therapy, which could be used to sort and identify patients who respond poorly to photodynamic therapy before treatment and prevent them from unnecessary treatment.

AB - In this paper, we report a fully automatic method for the prediction of the treatment efficacy of photodynamic therapy during the clinical treatment in port-wine stains. Histogram of oriented gradients (HOG) features were extracted from optical coherence tomography images. Isolation forest (iForest) was used to build classifier based on these features, achieving a sensitivity of 84% and specificity of 91%. Our dataset consists of 336 PWS lesions of 121 patients. We aim to build a comprehensive computational model for the patients who respond positively to the photodynamic therapy, which could be used to sort and identify patients who respond poorly to photodynamic therapy before treatment and prevent them from unnecessary treatment.

KW - Anomaly detection

KW - machine learning

KW - optical coherence tomography

KW - port-wine stain

KW - support vector data description

UR - http://www.scopus.com/inward/record.url?scp=85081058010&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2020.2972275

DO - 10.1109/ACCESS.2020.2972275

M3 - Article

AN - SCOPUS:85081058010

SN - 2169-3536

VL - 8

SP - 31227

EP - 31233

JO - IEEE Access

JF - IEEE Access

M1 - 8986618

ER -

Fully Automatic Prediction for Efficacy of Photodynamic Therapy in Clinical Port-Wine Stains Treatment: A Pilot Study

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this