A Novel Texture based Skin Melanoma Detection using Color GLCM and CS-LBP Feature

Microscopic analysis of skin cancer images for detection of melanoma or lesion has drawn significant medical interest over last few years. Various kinds of skin abnormalities are not well detectable from mear observation of the microscopic images. Most of the detection of skin abnormality has been relied on the variation of the texture of a specific region of the skin in comparison to the neighborhood of the area. Therefore image processing has been widely used for such detection techniques. However such detection technique fails to distinguish between different types of abnormalities. In case of a blister in the skin which appears the same abnormal way that a probable tumor or a sun burn in a specific area in the skin. Due to variation of the skin texture in the presence of any common abnormality like sun burn, blister, etc, it is extremely difficult for the present systems to differentiate a melanoma or a skin tumor or a cancer from the other skin diseases. Therefore in this work a unique system is developed to detect skin abnormality using a machine learning framework to classify a skin abnormality as melanoma more effectively. The proposed machine learning system relies on extraction of advanced texture features such as harlick GLCM features and CS LBP features in order to detect melanoma in the dermoscopy skin images. A total of 300 images from standard dataset dermquest.com are considered to carry out experimentation, and accuracy of the system using KNN is 79.7315% and SVM is 84.7615%.

[1]  Juan Chen,et al.  A generalized fusion approach for segmenting dermoscopy images using Markov random field , 2013, 2013 6th International Congress on Image and Signal Processing (CISP).

[2]  Giovanna Castellano,et al.  Adaptive segmentation of gray areas in dermoscopy images , 2011, 2011 IEEE International Symposium on Medical Measurements and Applications.

[3]  Jorge S. Marques,et al.  On the role of texture and color in the classification of dermoscopy images , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Reda Kasmi,et al.  Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule , 2016, IET Image Process..

[5]  Jorge S. Marques,et al.  Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features , 2014, IEEE Systems Journal.

[6]  David Dagan Feng,et al.  Automatic melanoma detection via multi-scale lesion-biased representation and joint reverse classification , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[7]  Hamid Gholamhosseini,et al.  Lesion border detection using deep learning , 2016, 2016 IEEE Congress on Evolutionary Computation (CEC).

[8]  Mário A. T. Figueiredo,et al.  Color identification in dermoscopy images using Gaussian mixture models , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[9]  M. Faezipour,et al.  A comparison of feature sets for an automated skin lesion analysis system for melanoma early detection and prevention , 2015, 2015 Long Island Systems, Applications and Technology.

[10]  Masaru Tanaka,et al.  Classification of melanocytic skin lesions from non-melanocytic lesions , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[11]  R. Suganya,et al.  An automated computer aided diagnosis of skin lesions detection and classification for dermoscopy images , 2016, 2016 International Conference on Recent Trends in Information Technology (ICRTIT).

[12]  Fred Godtliebsen,et al.  A computer aided diagnostic system for malignant melanomas , 2010, 2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies (ISABEL 2010).

[13]  Rui Hu,et al.  Detection of blue-whitish veil in melanoma using color descriptors , 2012, Proceedings of 2012 IEEE-EMBS International Conference on Biomedical and Health Informatics.

[14]  Saudamini S. Jivtode,et al.  Neural Network Based Detection of Melanoma Skin Cancer , 2016 .

[15]  Omid Sarrafzade,et al.  Skin lesion detection in dermoscopy images using wavelet transform and morphology operations , 2010, 2010 17th Iranian Conference of Biomedical Engineering (ICBME).

[16]  Mohammad Aldeen,et al.  Automated colour identification in melanocytic lesions , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[17]  Joanna Jaworek-Korjakowska,et al.  Determination of border irregularity in dermoscopic color images of pigmented skin lesions , 2014, EMBC.

[18]  Mai S. Mabrouk,et al.  Automatic Detection of Melanoma Skin Cancer using Texture Analysis , 2012 .

[19]  David I. McLean,et al.  Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions , 2013, IEEE Transactions on Medical Imaging.