Classification of Non-Tumorous Facial Pigmentation Disorders using Deep Learning and SMOTE

Non-tumorous facial pigmentation, though not fatal, adversely affects one's quality of life and may indicate concurrence of systemic diseases. Automatic diagnosis method such as voting-based probabilistic discriminant analysis (V-PLDA) has been explored, but the accuracy of classification is not satisfactory due to the limited number of data for training. This paper proposes to use the pre-trained deep learning network of Inception-ResNet-v2 so that information from similar datasets can be utilized. Furthermore, data augmentation using synthetic minority over-sampling technique (SMOTE) is also applied to make full use of available training data. A clinical dataset of five most common types of non-tumorous facial pigmentation disorders in Asia, namely freckles, lentigines, melasma, Hori's nevus, and nevus of Ota, is used for training and testing. The classification accuracy has shown significant improvement (> 7%) compared to the state-of-the-art method.

[1]  Matthew J. McAuliffe,et al.  Medical Image Processing, Analysis and Visualization in clinical research , 2001, Proceedings 14th IEEE Symposium on Computer-Based Medical Systems. CBMS 2001.

[2]  Hongfei Lin,et al.  Deep Transfer Learning for Modality Classification of Medical Images , 2017, Inf..

[3]  LinLin Shen,et al.  A review on Gabor wavelets for face recognition , 2006, Pattern Analysis and Applications.

[4]  Francesco Bianconi,et al.  Evaluation of the effects of Gabor filter parameters on texture classification , 2007, Pattern Recognit..

[5]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[6]  Germán Capdehourat,et al.  Pigmented Skin Lesions Classification Using Dermatoscopic Images , 2009, CIARP.

[7]  João Manuel R. S. Tavares,et al.  A Review of the Quantification and Classification of Pigmented Skin Lesions: From Dedicated to Hand-Held Devices , 2015, Journal of Medical Systems.

[8]  S. Ho,et al.  The Asian Dermatologic Patient , 2009, American journal of clinical dermatology.

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

[10]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[11]  G. Dougherty,et al.  Image analysis in medical imaging: recent advances in selected examples , 2010, Biomedical imaging and intervention journal.

[12]  Zhiping Lin,et al.  Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation , 2018, 2018 IEEE International Symposium on Circuits and Systems (ISCAS).

[13]  Taghi M. Khoshgoftaar,et al.  Deep learning applications and challenges in big data analytics , 2015, Journal of Big Data.

[14]  Feng Lin,et al.  Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis , 2018, Comput. Biol. Medicine.

[15]  Francisco Herrera,et al.  SMOTE-RSB*: a hybrid preprocessing approach based on oversampling and undersampling for high imbalanced data-sets using SMOTE and rough sets theory , 2012, Knowledge and Information Systems.

[16]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[18]  Fernando Bação,et al.  Oversampling for Imbalanced Learning Based on K-Means and SMOTE , 2017, Inf. Sci..

[19]  Sergey Ioffe,et al.  Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning , 2016, AAAI.