A new color assessment methodology using cluster-based features for skin lesion analysis

Melanoma is considered the most dangerous form of skin cancer, however if detected in early stages there are high success rates of recovery, making prevention essential. The risk assessment of skin lesions usually follows the ABCD rule (asymmetry, border, color and dermoscopic structures). This paper presents a methodology to assess the number of ABCD rule colors of skin lesion images. It starts by extracting 660 color features and several feature selection and machine learning classification methods are tested in order to minimize classification errors. The developed methodology has the advantage of being adaptable to the dataset used. Two publicly available dermoscopic image datasets and one mobile acquired dataset were used to test the methodology, achieving accuracy rates of 77.75%, 81.38% and 93.55%, respectively, for ABCD rule color feature assessment.

[1]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Geoff Holmes,et al.  Benchmarking Attribute Selection Techniques for Discrete Class Data Mining , 2003, IEEE Trans. Knowl. Data Eng..

[3]  Randy H. Moss,et al.  A methodological approach to the classification of dermoscopy images , 2007, Comput. Medical Imaging Graph..

[4]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[5]  Michael Landthaler,et al.  SKIN SURFACE MICROSCOPY , 1989, The Lancet.

[6]  Reinhard Dummer,et al.  Skin cancer : a world-wide perspective , 2011 .

[7]  V I Kustov,et al.  [Epidemiology of malignant melanoma]. , 1987, Voprosy onkologii.

[8]  J. Scharcanski,et al.  Computer Vision Techniques for the Diagnosis of Skin Cancer , 2013 .

[9]  Rahil Garnavi,et al.  Computer-aided diagnosis of melanoma , 2011 .

[10]  Huan Liu,et al.  Toward integrating feature selection algorithms for classification and clustering , 2005, IEEE Transactions on Knowledge and Data Engineering.

[11]  Luís Rosado,et al.  Automatic Segmentation Methodology for Dermatological Images Acquired via Mobile Devices , 2015, HEALTHINF.

[12]  R. H. Moss,et al.  Skin lesion classification using relative color features , 2007, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

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

[14]  Ammara Masood,et al.  Computer Aided Diagnostic Support System for Skin Cancer: A Review of Techniques and Algorithms , 2013, Int. J. Biomed. Imaging.

[15]  Joost van de Weijer,et al.  Color in Computer Vision: Fundamentals and Applications , 2012 .

[16]  G Pellacani,et al.  Computer description of colours in dermoscopic melanocytic lesion images reproducing clinical assessment. , 2003, The British journal of dermatology.

[17]  Pedro M. Ferreira,et al.  PH2 - A dermoscopic image database for research and benchmarking , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

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

[19]  Begoña García Zapirain,et al.  Automated Detection of Melanoma in Dermoscopic Images , 2014 .