Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

(531.34KB)
This is an Open Access publication published under CSC-OpenAccess Policy.

PUBLICATIONS BY COUNTRIES

Top researchers from over 74 countries worldwide have trusted us because of quality publications.

United States of America
United Kingdom
Canada
Australia
Malaysia
China
Japan
Saudi Arabia
Egypt
India
Skin Cancer Prognosis Based Pigment Processing
Muthana H. Hamd, Kadhum A. Essa
Pages - 227 - 236     |    Revised - 15-05-2013     |    Published - 30-06-2013
Volume - 7   Issue - 3    |    Publication Date - June 2013  Table of Contents
MORE INFORMATION
KEYWORDS
Melanoma, SCC, BCC, Skin Cancer, Color Matching.
ABSTRACT
This paper develops a new computerized vision of skin cancer prognosis based on symmetry and color matching for lesion pigments. Initially, the lesion/tumor edge is detected and segmented. Then, the symmetrization is computed for all images to isolate benign (mole) tumor. The even symmetry parameter is introduced here to improve the symmetrization computations. The suspicious images would be nominated into one of three categories: melanoma, Basal Cell Carcinoma (BCC), or Squamous Cell Carcinoma (SCC) tumor depending on the symmetrization and pigment-color matching score table. Two matching procedures have been developed for nominating the suspicious images. First procedure matches pigment values with artificial spectrums of Reddish, Yellowish, Brownish, and Blackish. The second procedure matches pigment values with true malignancy/benign pigment database. The results of two procedures are compared over 40 pre-classified images. With Mean Squared Error (MSE) value equals to 0.003, procedure#1 satisfied 80% true classification while 92.5% for procedure#2. These results could be improved if lesion segmentation and/or spectrums/pigment-database are increased.
CITED BY (1)  
1 Nisha, N. R., & Gomathe, M. (2014). Diagnosing Psoriasis Using GLCM and ANFIS. Biometrics and Bioinformatics, 6(4), 115-119.
1 Google Scholar 
2 CiteSeerX 
3 Scribd 
4 SlideShare 
5 PdfSR 
1 M. H. Hamd and L. M. Mohammad. “Skin Cancer Prognosis Based Color Matching and Segmentation of Pigmented Skin Lesion.” journal of engineering and technology, submitted,2012.
2 P. Shetty. “Melanoma Decision Support System for Dermatologist,” International Conference on Recent Trends in Information Technology and Computer Science (IRCTITCS),2011,pp.101-105.
3 L. DANIEL. “American Family Physician.” volume 70, No. 8, October 15 2004,www.aafp.org/afp.
4 S. L. Phung and A. Bouzerdoum. “Skin segmentation using color pixel classification: analysis and comparison.” IEEE Transactions on Pattern Analysis and Machine Intelligence , Vol. 27,No. 1, Jan. 2005.
5 R. G. Gonzalez and E. R. Woods, “Digital Image Processing Using MATLAB.” A John Wiley & Sons, Inc., Publication 4th Edition , 2004, pp. 220-222.
6 G. Blanchet and C Maurice “Digital Signal and Image Processing using MATLAB.”, ISBN 10:1-905209-13-4, 2006, pp. 43-46.
7 M. Thorsten. “Functional Infrared Imaging for Skin-Cancer Screenin,” Proceedings of the 28th IEEE EMBS Annual International Conference New York City, USA, Aug 30-Sept 3,2006.
8 W. Stolz, D. Hölzel, A. Riemann. “Multivariate analysis of criteria given by dermatoscopy for recognition of melanocytic lesions.” Book of Abstracts, Fiftieth Meeting of the American Academy of Dermatology, Dallas, Texas, December 1991.
9 R. A. Fiorini, G. Dacquino and G. Laguteta. “A New Melanoma Diagnosis Active Support System,” Proceedings of the 26th Annual International Conference of the IEEE EMBS San Francisco, CA, September 1-5, 2004, 3206-3209.
10 G. Di. Leo and A. P. Sommella. “Automatic Diagnosis of Melanoma: a Software System based on the 7-Point Check-List,” Proceedings of the 43rd Hawaii International Conference on System Sciences, 2010.
11 M. Ilias and C. N. Doukas, “Overview of Advanced Computer Vision Systems for Skin Lesions Characterization.”, IEEE Transaction on Information Technology in Biomedicine,Vol. 13, NO. 5, September 2009.
12 M. M. Rahman and B. C. Desai , “Image Retrieval-Based Decision Support System for Dermatoscopic Images,” Proceedings of the 19th IEEE, Symposium on Computer-Based Medical Systems, 0-7695-2517-1/06, 2006.
13 C. Fatichah, “Skin Lesion Detection using Fuzzy Region Growing and ABCD Feature Extraction for Melanoma Skin Cancer Diagnosis.” Journal of computing and informatics technology, 2010, www.cs.ui.ac.id/files/icacsis2009/pdf/43.pdf.
14 X. Yuan. “SVM-based Texture Classification and Application to Early Melanoma Detection,”Proceedings of the 28th IEEE EMBS Annual, International Conference New York City, USA,Aug 30-Sept 3, 2006.
15 Y. Zhoul and M. Smith. “Segmentation of Clinical Lesion Images Using Normalized Cut “,IEEE conference, 978-1-4244-3610-1/09/, 2009.
16 R. Cláudio and R. Jung. “Sharpening Dermatological Color Images in the Wavelet Domain.”IEEE journal of Selected Topics in Signal Processing, Vol. 3, No.1, February 2009.
17 M. Sadeghi. “Automated Detection and Analysis of Dermoscopic Structures on Dermoscopy Images,” Congress on Image and Signal Processing, 2008.
18 H. Yu-Chen. International Journal of Image Processing, Book, 2009, Vol. 3, Issue 5,ISSN(online):1985-2304, pp.229-245.
Dr. Muthana H. Hamd
College of Eng. Al Mustansirya University - Iraq
muth700@yahoo.com
Mr. Kadhum A. Essa
Computer & SW Engineering Al Mustansirya Baghdad, Iraq - Iraq