Skin lesion classification from dermoscopy images using color and shape features

Subject Areas : Renewable energy

hamid reza  javadi ¹ (MSc. - Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Najafabad, Iran)
Hossein  Pourghasem ² (Assistant Professor/Najafabad Branch, Islamic Azad University)

Received: 2016-03-22 Accepted : 2017-02-25 Published : 2017-04-21

Keywords: : Skin cancer, dermoscopy image, Skin lesion,

Abstract :

In this study, a new algorithm for dermoscopy image classification into two types of malignant and benign is presented. At first, one preprocessing step to remove noise and also enhance image quality is performed. After that using Otsu thresholding, the lesion is separated from the healthy area. Then color and shape features are extracted from the segmented image. The colored features based on statistical moments of quantized grayscale and quantized color histogram are defined. These features demonastrare distribution of color components. Moreover, the shape features are extracted information of the segmented regions with two scenarios. In the first scenario, the features are represented the expantion of region and in the second scenario, the features are represented the edge variations of the extracted regions. Finally, the classification procedure is performed using K-Neasert Neighbor (KNN), Decision Tree, Support Vector Machine (SVM) and Adaboost. The proposed algorithm is evaluated on a standard database consisting of 200 images. The results show that classification using Adaboost classifier obtains the precision rate, accuracy rate and sensitivity rate of 96%, 96.7% and 95%, respectively.

References:

[1]  A. Noori Hoshyar, A. Al- Jumaily and R. Sulaiman, "Review on automatic early skin cancer detection", Proceeding of the IEEE/CSSS, pp. 4036 – 4039, Nanjing, China, June 2011.

[2]  M. Zortea, R. Schopf, K. Thon; "Performance of a dermoscopy-based computer vision system for the diagnosis of pigmented skin lesions compared with visual evaluation by experienced dermatologists", Artificial Intelligence in Medicine. Vol. 60, No. 1, pp. 13–26, Jan. 2014.

[3]  J. Abdul Jaleel, S. Salim, "Computer aided detection for skin cancer", Proceeding of the IEEE/ICCPCT, pp. 1137 – 1142,  Nagercoil, India, March, March 2013.

[4]  C. Barata, M. Ruela, M. Francisco, T.Mendonça,J. Marques, "Two systems for the detection of melanomas in dermoscopy images using texture and color features", IEEE Systems Journal, Vol. 8, No. 99, pp. 1 – 15, 2013

[5]  M. Ruela, C. Barata, T. Mendonca, J. Marques, "On the role of shape in the detection of melanomas",Proceeding of the IEEE/ISPA, pp. 268 – 273, Trieste, Italy, Sep. 2013.

[6]  J. Marques, C. Barata, T. Mendonca, "On the role of texture and color in the classification of dermoscopy images", Proceeding of the IEEE/EMBC, pp. 4402 – 4405, San Diego, CA, USA, Aug. 2012.

[7]  M. Celebi, A. Zornberg, "Automated quantification of clinically significant colors in dermoscopy images and its application to skin lesion classification", IEEE Systems Journal, Vol. 8, No. 3, pp 980-984, Sep. 2014.

[8]  A. Sáez, C. Serrano, B. Acha, "Model-based classification methods of global patterns in dermoscopic images", IEEE Trans. on Medical Imaging, Vol. 33, No. 5, pp. 1137 – 1147, Sep. 2014.

[9]  O. Abuzaghleh, B. Barkana, M. Faezipour, "SKINcure: A real time image analysis system to aid in the malignant melanoma prevention and early detection", Proceeding of the IEEE/SSIAI, pp. 85 – 88, San Diego, CA, USA, April 2014.

[10] O. Abuzaghleh, B. Barkana, M. Faezipour, "Automated skin lesion analysis based on color and shape melanoma early detection and prevention", Proceeding of the IEEE/LISAT, pp. 1 – 6, Farmingdale, NY, USA, 2014.

[11] H. Iyatomi, M. Celebi, G.Schaefer, M. Tanaka, "Automated color normalization for dermoscopy images", Proceeding of the IEEE/ICIP, pp. 4357 – 4360, Hong Kong, China, Sep. 2010.

[12] H. Zhou, G. Schaefer, A. Sadka, M. Celebi, "Anisotropic mean shift based fuzzy C-means segmentation of dermoscopy images", IEEE Journal of Selected Topics in Signal Processing, Vol. 3, No. 1, pp. 26 – 34, 2009.

[13] H. Zhou, G. Schaefer, M. Celebi, H. Iyatomi, K. Norton, T. Lin, "Skin lesion segmentation using an improved snake model", Proceeding of the IEEE/EMBC, pp. 1974 – 1977, Buenos Aires, Argentina, Aug./Sep. 2010.

[14]  R. Chakravarti, X. Meng, "A study of color histogram based image retrieval", Proceeding of the IEEE/ITNG, pp. 1323 – 1328, Las Vegas, NV, USA, April 2009.

[15] Y. Mingqiang, K. Kidiyo, R Joseph, "A survey of shape feature extraction techniques", INTECH Open Access Publisher, pp. 44 – 90, 2008.

[16] M. Ramezani, A. Karimian, P. Moallem, "Automatic detection of malignant melanoma using macroscopic images", Journal of Medical Signals and Sensors, Vol. 4, No .4, pp. 281–290, 2014.

[17] M. Normohamadi, H. Pourghasem, "A novel eigenborder-based melanoma diagnosis and classification algorithm in dermoscopy images", International Journal of Imaging and Robotics, Vol. 8, No. 2, pp. 61 – 84, 2012.