Color Models for Skin Lesion Classification from Dermatoscopic Images

In this paper, we present an architecture for classification of pigmented skin lesions from dermatoscopic images. The architecture is using image preprocessing for natural hair removal and image segmentation for extraction of the skin lesion area followed by computation of statistical values of colors as features. The color-based features were extracted from several well-known and widely used color models. Several classification algorithms were evaluated with the best performing classification algorithm being the AdaBoost with random forest classifier with classification accuracy equal to 73.08% when using RGB-based features only and 74.26% when combining RGB, HSV, and YIQ color model-based features.

[1]  John C. Beatty,et al.  An experimental comparison of RGB, YIQ, LAB, HSV, and opponent color models , 1987, TOGS.

[2]  James M. Rehg,et al.  Statistical Color Models with Application to Skin Detection , 2004, International Journal of Computer Vision.

[3]  Umit Topaloglu,et al.  Statistical comparison of color model-classifier pairs in hematoxylin and eosin stained histological images , 2009, 2009 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology.

[4]  Mai S. Mabrouk,et al.  Automated Imaging System for Pigmented Skin Lesion Diagnosis , 2016 .

[5]  Gerard de Haan,et al.  Automatic imaging sysem with decision support for inspection of pigmented skin lesions and melanoma diagnosis. , 2009 .

[6]  Saroj Kumar Lenka,et al.  Comparative Analysis of Skin Color Based Models for Face Detection , 2013 .

[7]  W. Stolz,et al.  The ABCD rule of dermatoscopy. High prospective value in the diagnosis of doubtful melanocytic skin lesions. , 1994, Journal of the American Academy of Dermatology.

[8]  D. Whiteman,et al.  Diagnostic accuracy in skin cancer clinics: the Australian experience , 2006, International journal of dermatology.

[9]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[10]  S. Sathiya Keerthi,et al.  Improvements to Platt's SMO Algorithm for SVM Classifier Design , 2001, Neural Computation.

[11]  J. L. Tecpanecatl-Xihuitl,et al.  A Comparison of Color Models for Color Face Segmentation , 2013 .

[12]  A. Jerant,et al.  Early detection and treatment of skin cancer. , 2000, American family physician.

[13]  T Lee,et al.  Dullrazor®: A software approach to hair removal from images , 1997, Comput. Biol. Medicine.

[14]  Pietro Rubegni,et al.  Automated diagnosis of pigmented skin lesions , 2002, International journal of cancer.

[15]  M. Binder,et al.  Epiluminescence microscopy. A useful tool for the diagnosis of pigmented skin lesions for formally trained dermatologists. , 1995, Archives of dermatology.

[16]  D. S. Guru,et al.  Segmentation and Classification of Skin Lesions for Disease Diagnosis , 2016, ArXiv.

[17]  Xiaoxiao Li,et al.  Skin Lesion Classification Via Combining Deep Learning Features and Clinical Criteria Representations , 2018 .

[18]  I. Weatherall,et al.  Skin color measurements in terms of CIELAB color space values. , 1992, The Journal of investigative dermatology.

[19]  Harald Kittler,et al.  Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018 .

[20]  W. Chang,et al.  Computer-Aided Diagnosis of Skin Lesions Using Conventional Digital Photography: A Reliability and Feasibility Study , 2013, PloS one.

[21]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[22]  J. Ross Quinlan,et al.  Simplifying Decision Trees , 1987, Int. J. Man Mach. Stud..

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

[24]  Achmad Benny Mutiara,et al.  Classification of Melanoma Skin Cancer using Convolutional Neural Network , 2019, International Journal of Advanced Computer Science and Applications.

[25]  Yasser Baleghi,et al.  Skin lesion images classification using new color pigmented boundary descriptors , 2017, 2017 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA).

[26]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[27]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[28]  Josiane Zerubia,et al.  Classification of skin hyper-pigmentation lesions with multi-spectral images , 2012 .

[29]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[30]  Ghassan Hamarneh,et al.  Deep features to classify skin lesions , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[31]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[32]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[33]  S. Kolkur,et al.  Human Skin Detection Using RGB, HSV and YCbCr Color Models , 2017, Proceedings of the International Conference on Communication and Signal Processing 2016 (ICCASP 2016).

[34]  Julie Ann A. Salido,et al.  HAIR ARTIFACT REMOVAL AND SKIN LESION SEGMENTATION OF DERMOSCOPY IMAGES , 2018 .

[35]  Marko Robnik-Sikonja,et al.  An adaptation of Relief for attribute estimation in regression , 1997, ICML.