Classification of Vitiligo Based on Convolutional Neural Network

Vitiligo is one of the most intractable skin disease in the world. According to incomplete statistics, there is about 0.5–2% incidence of vitiligo in the world, and the number is still growing, so the early diagnosis of vitiligo is very important. In recent years, deep learning has been successfully applied to medical image classification and has achieved outstanding performance, which helps achieve vitiligo intelligent diagnosis. In this paper, we propose a method base on probability-average value of three convolutional neural network (CNN) models which are same structures, and trained with three different color-space images (RGB, HSV, and YCrCb) for the same vitiligo dataset. The applied strategy is found to achieve the classification performance of 94.2% area under the roc curve (AUC), 87.8% accuracy, 91.9% precision, 90.9% sensitivity, 80.2% specificity which outperforms the individual networks.

[1]  Kouhyar Tavakolian,et al.  Automatic detection and severity measurement of eczema using image processing , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[2]  J. Kanitakis,et al.  Anatomy, histology and immunohistochemistry of normal human skin. , 2002, European journal of dermatology : EJD.

[3]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[4]  Anabik Pal,et al.  Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network , 2018, Comput. Methods Programs Biomed..

[5]  Qi Cui.  Identifying materials of photographic images and photorealistic computer generated graphics based on deep CNNs , 2018 .

[6]  T. Lotti,et al.  Vitiligo as a systemic disease. , 2014, Clinics in dermatology.

[7]  Hao Chen,et al.  Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks , 2017, IEEE Transactions on Medical Imaging.

[8]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[9]  Alex Pentland,et al.  Perceptual Organization and the Representation of Natural Form , 1986, Artif. Intell..

[10]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[11]  Hong Zhou,et al.  An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network , 2017, Scientific Reports.

[12]  René Meier,et al.  Detection and Quantification of Hand Eczema by Visible Spectrum Skin Pattern Analysis , 2014, ECAI.

[13]  Jasjit S. Suri,et al.  A novel and robust Bayesian approach for segmentation of psoriasis lesions and its risk stratification , 2017, Comput. Methods Programs Biomed..

[14]  Anfeng Liu,et al.  Feature Selection Method Based on Class Discriminative Degree for Intelligent Medical Diagnosis , 2018 .

[15]  François Chollet,et al.  Keras: The Python Deep Learning library , 2018 .

[16]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[17]  K. Schallreuter,et al.  A review of the worldwide prevalence of vitiligo in children/adolescents and adults , 2012, International journal of dermatology.