Email this article 
Open Access
Subscription or Fee Access
A Novel Approach for Detection of Skin Cancer Using Neural Network
Abstract
Skin cancers are the most common form of cancers in
humans. It is a deadly type of cancer. Most of the skin cancers are cure able at initial stages. So an premature detection of skin is possible. The automatic diagnosis can help to increase the accuracy of detection. The diagnosing methodology uses Image processing techniques and Artificial Intelligence. Automated image segmentation and classification of skin lesions as malignant or benign. The dermoscopy image of skin cancer is taken and it is subjected to pre-processing for noise removal and image enhancement. Then the image is undergone image segmentation using Thresholding. There are certain features unique for skin cancer regions. Such features are extracted. These features are given as the input nodes to the neural network. Back-Propagation Neural (BPN) Network is used for classification purpose. It classifies the given data set into cancerous or non-cancerous.
Keywords
References
A.W. Kopf, T.G. Salopek, J. Slade, A.A. Marghood, R.S.Bart, Techuniques of cutaneous examination for the detection of skin cancer, Cancer Supplement 75 (2) (1994) 684-690.
D.E. Elder, Skin cancer: Melanoma and other specific nonmelanoma skin cancers, Cancer Supplement 75 (1) (1994) 245-256.
A.J. Sober, T.B. Fitzpatrick, M.C. Mihm, Early recognition ofcutaneous melanoma, JAMA 242 (1979) 2795-2799.
M.M. Wick, A.J. Sober, T.B. Fitzpatrick, Clinical characteristics of early utaneous melanoma, Cancer 45 (1980) 2684-2686.
NIH Consensus Conference, Diagnosis and treatment of early melanoma, JAMA 268 (10) (1992) 1314-1319.
W.V. Stoecker, W.W. Li, R.H. Moss, Automatic detection of asymmetry in skin tumors, Computerized Medical Imaging and Graphics 16 (3) (1992) 191-197.
M. Kaas, A. Witkins, D. Terzopolus, “Snakes-active contour models”, International Journal of Computer Vision, Vol. 1,No. 4, pp.321-330, 1987
C. Grana, G. Pellacani, R. Cucchiara and S. Seidenari. A new algorithm for border description of polarized light surface microscopic images of pigmented skin lesions". IEEE Trans on Medical Imaging, Vol.22, no.8, 959-964, 2003.
Otsu N. A Threshold Selection Method from Gray-Level Histograms. IEEE Transactions on Systems, Man, and Cybernetics. 1979. Vol. 9 Issue 1:62-66.
J. Liang, T. McInerney, and D. Terzopoulos, “United snakes”, Computer Vision. The Proceedings of the Seventh IEEE International Conference Vol. 2, pp. 933 –940,1999
F. Leymarie and M. D. Levine ”Tracking Deformable Objects in the Plane Using an Active Contour Model”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol. 15, No. 6, pp. 617-634, June 1993
P. Radeva, and E. Marti, ”An Improved Model of Snakes for Model- Based Segmentation,” Proc. 6th Int. Conf. Computer Analysis of Images and Patterns (CAIP '95, Prague), Springer - Verlag, pp. 515-520, September 1995
R. Ronfard “Region Based Strategies for Active Contour Models”, International Journal of Computer Visison, Vol.13,No. 2,pp.229-251 1994
J. Wang, X. Li., A. Bradely, “Boundary Searching Snakes for Segmenting Noisy Images”, Proceedings of VI-1998, Vision Interface, 18-21 June 1998, Vancouver, Canada, pp.107-114.
D. Metaxas and T. N. Jones, “Image Segmentation Based on the Integration of Pixel Affinity and Deformable Models”, Computer Vision and Pattern Recognition, 1998.Proceedings. 1998 IEEE Computer Society Conference, 1998, pp.: 330 –337.
R. S. Gunn, and M.S. Nixon, “A Robust Snake Implementation: a Dual Active Contour”, IEEE Transaction on Pattern Analysis and Machine Intelligence,Vol. 19, No. 1, pp. 63-68,1997
P. M Prenter. “Splines and Variational Methods”, Willey Classics Library, 1975, Reprinted in 1989Lyon, R.F., “A computational model of filtering detection and compression in the cochlea”, Proc. ICASSP, 1982, pp. 1282-1285.
Milan Sonka, Vaclav Hlavac, Roger Boyle- “Image Processing, Analysis, and Machine Vision.”
R.L. Graham (1972), “An efficient algorithm for determining the convex hull of a finite planar set.”, Info. Proc. Lett. 1, 132-133
Shape Analysis & Measurement CIS 6320
(http://www.uoguelph.ca/~mwirth/CIS6320/lecture10.pdf)
Celebi ME, Kingravi HA, Stoecker WV, Moss RH, Aslandogan YA. Fast and accurate border detection in dermoscopy images using statistical region merging to appear in the Proceedings of the SPIE Medical Imaging 2007 Conference, San Diego, CA, February 2007.
Argenziano G, Soyer HP, De Giorgi V, Piccolo D, Carli P, Delfino M, et al.Dermoscopy:ATutorial. Milan: EDRA Medical
Publishing&NewMedia; 2002.
Lee TK, Ng V, Gallagher R, Coldman A, McLean D. Dullrazor—A software approach to hair removal from images. Comput Biol Med 1997;27(6):533–43.
Celebi ME, Kingravi HA, AslandoganYA, StoeckerWV. Detection of bluewhite veil areas in dermoscopy images using machine learning techniques. In: Proceedings of the SPIE Medical Imaging 2006 Conference, Vol. 6144. 2006. p. 1861–8.
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution 3.0 License.