Semi-automated Diagnosis of Melanoma through the Analysis of Dermatological Images

Melanoma is the deadliest kind of skin cancer, but it can be 100% cured if recognized early in advance. This paper proposes a non-invasive automated skin lesion classifier based on digitized dermatological images. In the proposed approach, the lesion is initially segmented using snakes guided by an edge map based on the Wavelet Transform (WT) computed at different resolutions. A set of features is extracted from lesion pixels, and a probabilistic classifier is used to identify melanoma lesions. The detection rate of the proposed system can be adjusted to control the tradeoff between false positives and false negatives, and experimental results indicated that a false negative rate of 1.89% can be achieved, in a total accuracy rate of 82.55%.

[1]  Scott T. Acton,et al.  Ankle cartilage surface segmentation using directional gradient vector flow snakes , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[2]  V. Devita,et al.  Cancer : Principles and Practice of Oncology , 1982 .

[3]  J. Todd.  Book Review: Digital image processing (second edition). By R. C. Gonzalez and P. Wintz, Addison-Wesley, 1987. 503 pp. Price: £29.95. (ISBN 0-201-11026-1) , 1988 .

[4]  Jacob Scharcanski,et al.  Sharpening Dermatological Color Images in the Wavelet Domain , 2009, IEEE Journal of Selected Topics in Signal Processing.

[5]  Masafumi Hagiwara,et al.  An improved Internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm , 2008, Comput. Medical Imaging Graph..

[6]  Steven A. Rosenberg,et al.  Cancer: Principles & Practice of Oncology: Annual Advances in Oncology , 2012 .

[7]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[8]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  A. Kopf,et al.  Early detection of malignant melanoma: The role of physician examination and self‐examination of the skin , 1985, CA: a cancer journal for clinicians.

[10]  Ashfaq A Marghoob,et al.  Instruments and new technologies for the in vivo diagnosis of melanoma. , 2003, Journal of the American Academy of Dermatology.

[11]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques with Java implementations , 2002, SGMD.

[12]  Zhao Zhang,et al.  Neural networks skin tumor diagnostic system , 2003, International Conference on Neural Networks and Signal Processing, 2003. Proceedings of the 2003.

[13]  Francisco J. Prieto,et al.  Multivariate Outlier Detection and Robust Covariance Matrix Estimation , 2001, Technometrics.

[14]  H. Peter Soyer,et al.  Mobile teledermatology coming of age , 2006, Elektrotech. Informationstechnik.

[15]  Benyamin Kusumoputro,et al.  Neural network diagnosis of malignant skin cancers using principal component analysis as a preprocessor , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

[16]  R. H. Moss,et al.  Neural network diagnosis of malignant melanoma from color images , 1994, IEEE Transactions on Biomedical Engineering.

[17]  Terence Sim,et al.  Discriminant Subspace Analysis: A Fukunaga-Koontz Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Jerry L. Prince,et al.  Gradient vector flow: a new external force for snakes , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Zhong Linghui,et al.  Pre‐diagnostic digital imaging prediction model to discriminate between malignant melanoma and benign pigmented skin lesion , 2010, 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.

[20]  O. Yanez-Suarez,et al.  Automatic initialization for a snakes-based cardiac contour extraction , 2000, Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No.00CH37143).

[21]  Arash Taheri,et al.  Computer-aided dermoscopy for diagnosis of melanoma , 2005, BMC dermatology.

[22]  Stéphane Mallat,et al.  Characterization of Signals from Multiscale Edges , 2011, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Ian Witten,et al.  Data Mining , 2000 .

[24]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[25]  Ilias Maglogiannis,et al.  An integrated computer supported acquisition, handling, and characterization system for pigmented skin lesions in dermatological images , 2005, IEEE Transactions on Information Technology in Biomedicine.

[26]  Zhe Wang,et al.  Contour extraction based on improved GVF snake model in ASAR images , 2007, 2007 International Conference on Wavelet Analysis and Pattern Recognition.