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

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.

[1]  William T. Freeman,et al.  Orientation Histograms for Hand Gesture Recognition , 1995 .

[2]  Tahereh Marvdashti,et al.  Classification of basal cell carcinoma in human skin using machine learning and quantitative features captured by polarization sensitive optical coherence tomography. , 2016, Biomedical optics express.

[3]  Dalip Singh Mehta,et al.  In vivo classification of human skin burns using machine learning and quantitative features captured by optical coherence tomography , 2018 .

[4]  Guillermo Aguilar,et al.  An overview of clinical and experimental treatment modalities for port wine stains. , 2012, Journal of the American Academy of Dermatology.

[5]  K. Laws.  Textured Image Segmentation , 1980 .

[6]  Ya-dong Yang,et al.  Photodynamic therapy of port-wine stains , 2010, The Journal of dermatological treatment.

[7]  Fei Tony Liu,et al.  Isolation-Based Anomaly Detection , 2012, TKDD.

[8]  Chih-Jen Lin,et al.  A Revisit to Support Vector Data Description , 2015 .

[9]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[11]  Murray H Loew,et al.  Computer recognition of cancer in the urinary bladder using optical coherence tomography and texture analysis. , 2008, Journal of biomedical optics.

[12]  J. Park,et al.  Clinical application of copper vapor laser. , 1993 .

[13]  Sina Farsiu,et al.  Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. , 2014, Biomedical optics express.

[14]  Silvia Conforto,et al.  Textural analysis of optical coherence tomography skin images: quantitative differentiation between healthy and cancerous tissues , 2017, BiOS.

[15]  H. Hotelling.  Analysis of a complex of statistical variables into principal components. , 1933 .

[16]  Rémy Mullot,et al.  Texture feature evaluation for segmentation of historical document images , 2013, HIP '13.

[17]  Hossein Rabbani,et al.  Classification of dry age-related macular degeneration and diabetic macular edema from optical coherence tomography images using dictionary learning , 2019, IET Image Process..

[18]  Ning Zhang,et al.  AUTOMATED ASSESSMENT OF EPIDERMAL THICKNESS AND VASCULAR DENSITY OF PORT WINE STAINS OCT IMAGE , 2014 .

[19]  S. Barsky,et al.  Healing of port-wine stains after argon laser therapy. , 1981, Archives of dermatology.

[20]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[21]  H. Lv,et al.  Analysis of quality of life and influencing factors in 197 Chinese patients with port-wine stains , 2017, Medicine.

[22]  Mark J J P van Grinsven,et al.  Automated Staging of Age-Related Macular Degeneration Using Optical Coherence Tomography. , 2017, Investigative ophthalmology & visual science.

[23]  P. Xue,et al.  Handheld optical coherence tomography device for photodynamic therapy , 2012 .

[24]  B. Cheng,et al.  Photodynamic therapy of port‐wine stains: Long‐term efficacy and complication in Chinese patients , 2011, The Journal of dermatology.

[25]  T. Tkaczyk,et al.  Texture analysis of optical coherence tomography images: feasibility for tissue classification. , 2003, Journal of biomedical optics.

[26]  Li Zhang,et al.  Imaging port wine stains by fiber optical coherence tomography. , 2010, Journal of biomedical optics.

[27]  Y. Tu,et al.  Hemoporfin Photodynamic Therapy for Port-Wine Stain: A Randomized Controlled Trial , 2016, PloS one.