Early Detection of Melanoma using Color and Shape Geometry Feature
Keywords:skin cancer, image segmentation, melanoma, classification
Melanoma occurrence rates contain be increasing for the earlier 3 decades. The majority folks analyzed with non-melanoma carcinoma contain higher prospects to cure, however malignant melanoma endurance rates are low compare to different carcinoma varieties. It is important that one in 5 Americans will grow skin cancer in their life, and generally, one American expires from skin cancer each hour. A system to obviate this kind of skin cancer is being scheduled and is very in-demand. Initial detection of melanoma is one of the key factors to increment the chance of remedy significantly. Malignant melanomas are asymmetrical and have aberrant borders with rages and notched edges, thus analyzing the form of the skin lesion is consequential for melanoma early detection and aversion. In this paper, we have a tendency to introduce an automatic skin lesion segmentation and analysis for premature detection and obviation predicated on color and shape geometry. The system additionally incorporates extra feature sets such as color to find the wound type. In our planned system, we use PH2 Dermoscopy image information. This image info contains a complete of fifty dermoscopy pictures of lesions, together with traditional, malignant melanoma and atypical cases. Our approach of analyzing the form pure mathematics and therefore the color are going to be subsidiary to detect atypical lesions afore it grows and becomes a melanoma case.
(1) American Cancer Society, Cancer Facts & Figures. Available: http://www.cancer.org/research/cancerfactsstatistics/cancerfactsfigures2014/index
(2) A. Karargyris, et.al "DERMA/care: An advanced image-processing mobile application for monitoring skin cancer," in Tools with Artificial Intelligence (ICTAI), 2012 IEEE 24th International Conference on, 2012, pp.1-7.
(3) C. Doukas, et.al "Automated skin lesion assessment using mobile technologies and cloud platforms," in Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, 2012, pp. 2444-2447.
(4) C. Massone, et. al "Mobile tele dermoscopy—melanoma diagnosis by one click?," in Seminars in cutaneous medicine and surgery, 2009, pp. 203-205.
(5) T. Wadhawan, et, al "SkinScan©: A portable library for melanoma detection on handheld devices," in Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on, 2011, pp. 133-136.
(6) K. Ramlakhan and Y. Shang, "A Mobile Automated Skin Lesion Classification System," in Tools with Artificial Intelligence (ICTAI), 2011 23rd IEEE International Conference on, 2011, pp.138-141.
(7) C. Barata, et, al , "Two Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features," Systems Journal, IEEE, vol. 99, pp. 1-15, 2013.
(8) M. Poulsen, et al., "High-risk Merkel cell carcinoma of the skin treated with synchronous carboplatin/etoposide and radiation: a Trans- Tasman Radiation Oncology Group Study—TROG 96: 07," Journal of Clinical Oncology, vol. 21, pp.4371-4376, 2003.
(9) M. Ichihashi, M. et al., "UV-induced skin damage," Toxicology, vol. 189, pp. 21-39, 2003.
(10) K. Ito and K. Xiong, "Gaussian filters for nonlinear filtering problems," Automatic Control, IEEE Transactions on, vol. 45, pp. 910-927, 2000.
(11) N. Otsu, "A threshold selection method from graylevel histograms," Automatica, vol. 11, pp. 23-27, 1975.
(12) R. Jones and P. Soille, "Periodic lines: Definition, cascades, and application to granulometries,"Pattern Recognition Letters, vol. 17, pp. 1057- 1063, 1996.
(13) R. Adams, "Radial decomposition of disks and spheres," CVGIP: Graphical Models and Image Processing, vol. 55, pp. 325-332, 1993.
(14) P. Soille, Morphological image analysis: principles and applications: Springer-Verlag New York, Inc., 2003.
(15) T. F. Chan and L. A. Vese, "Active contours without edges," Image processing, IEEE transactions on, vol. 10, pp. 266-277, 2001.
(16) R. T. Whitaker, "A level-set approach to 3D reconstruction from range data," InternationalJournal of Computer Vision, vol. 29, pp. 203-231, 1998.
(17) T. Mendonca, P. M. Ferreira, J. S. Marques, A. R. Marcal, and J. Rozeira, "PH 2-A dermoscopic image database for research and benchmarking," in Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, 2013, pp. 5437-5440.
(18) J. S. Walker, Fast fourier transforms vol. 24: CRC press, 1996.
(19) G. Strang, "The discrete cosine transform," SIAM review, vol. 41, pp. 135-147, 1999.
(20) R. D. Keane and R. J. Adrian, "Theory of cross correlation analysis of PIV images," Applied scientific research, vol. 49, pp. 191-215, 1992.