A robust system for melanoma diagnosis using heterogeneous image databases

DOI: 10.4236/jbise.2010.36080   PDF   HTML     4,368 Downloads   8,765 Views   Citations


Early diagnosis of melanoma is essential for the fight against this skin cancer. Many melanoma detection systems have been developed in recent years. The growth of interest in telemedicine pushes for the development of offsite CADs. These tools might be used by general physicians and dermatologists as a second advice on submission of skin lesion slides via internet. They also can be used for indexation in medical content image base retrieval. A key issue inherent to these CADs is non-heterogeneity of databases obtained with different apparatuses and acquisition techniques and conditions. We hereafter address the problem of training database heterogeneity by developing a robust methodology for analysis and decision that deals with this problem by accurate choice of features according to the relevance of their discriminative attributes for neural network classification. The digitized lesion image is first of all segmented using a hybrid approach based on morphological treatments and active contours. Then, clinical descriptions of malignancy signs are quantified in a set of features that summarize the geometric and photometric features of the lesion. Sequential forward selection (SFS) method is applied to this set to select the most relevant features. A general regression network (GRNN) is then used for the classification of lesions. We tested this approach with color skin lesion images from digitized slides data base selected by expert dermatologists from the hospital “CHU de Rouen-France” and from the hospital “CHU Hédi Chaker de Sfax-Tunisia”. The performance of the system is assessed using the index area (Az) of the ROC curve (Receiver Operating Characteristic curve). The classification permitted to have an Az score of 89,10%.

Share and Cite:

Taouil, K. , Chtourou, Z. and Romdhane, N. (2010) A robust system for melanoma diagnosis using heterogeneous image databases. Journal of Biomedical Science and Engineering, 3, 576-583. doi: 10.4236/jbise.2010.36080.

Conflicts of Interest

The authors declare no conflicts of interest.


[1] (2006) Solar ultraviolet radiation: Global burden of disease from solar ultraviolet radiation. Environmental Burden of Disease Series, World Health Organization, 13.
[2] (2009) Cancer Facts and Figures. American Cancer Society, Atlanta.
[3] Friedman, R.J. (1985) Early detection of malignant melanoma: the role of the physician examination and self examination of the skin. Cancer Journal for Clinicians, 35, 130-151.
[4] Schmid-Saugeon, P., Guillod, J. and Thiran, J.P. (2003) Towards a computer-aided diagnosis system for pigmented skin lesions. Computerized Medical Imaging and Graphics, 27, 65-78.
[5] Blanzieri, E. (2000) Exploiting classifier combination for early melanoma diagnosis support. Proceedings of the 11th European Conference on Machine Learning, Barcelona, 31 May-2 June 2000, 55-62.
[6] Cascinelli, N., Ferrario, M., Tonelli, T., et al. (1987) A possible new tool for clinical diagnosis of melanoma. Journal of the American Academy of Dermatology, 16, 361-367.
[7] Ercal, F., Chawla, A., Stoecker, W.V., Lee, H.C. and Moss, R.H. (1994) Neural network diagnosis of malignant melanoma from color images. IEEE Transactions on Biomedical Engineering, 41(9), 837-845.
[8] Ganster, H., Pinz, A., Röhrer, R., et al. (2001) Automated melanoma recognition. IEEE Transactions on Medical Imaging, 20(3), 233-238.
[9] Burroni, M. (2004) Melanoma computer-aided diagnosis: Reliability and feasibility study. Clinical Cancer Research, 10, 1881-1886.
[10] Guillod, J., Schmid-Saugeon, P., Déccaillet, F., et al. (2003) An open internet platform to distributed image processing applied to dermoscopy. Studies in Health Technology and Informatics, 95, 107-112.
[11] Oka, H., Hashimoto, M., Iyatomi, H. and Tanaka, M. (2004) Internet-based program for automatic discrimination of dermoscopic images between melanoma and Clark nevi. British Journal of Dermatology, 150(5), 1041.
[12] Maglogiannis, I. and Charalampos, N.D. (2003) Overview of advanced computer vision systems for skin lesions characterization. IEEE Transaction on Information Technology in Biomedicine, 13(5), 721-733.
[13] Hall, P.N., Claridge, E. and Morris Smith, J.D. (1995) Computer screening for early detection of melanoma- Is there a future? British Journal of Dermatology, 132, 325-338.
[14] White, R., Rigel, D.S. and Friedman, R.J. (1991) Computer applications in the diagnosis and prognosis of malignant melanoma. Dermatologic Clinics, 9, 695-702.
[15] Taouil, K. and Romdhane, N.B. (2006) A new automatic approach for edge detection of skin lesion images. International Conference on Information & Communication Technologies: From Theory to Applications, Damascus.
[16] Kass, M., Witkin, A. and Terzopoulos, D. (1987) Snakes: Active contour models. International Journal of Computer Vision, 1, 321-331.
[17] Xu, C.Y. and Prince, J.L. (1998) Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing, 7(3), 359.
[18] Taouil, K., Bouhlel, M.S., Elloumi, M. and Kamoun, L. (2002) Quantification des caractéristiques de mélanomes en vue d'une classification. JTEA'2002, Sousse, 179-185.
[19] Zagrouba, E. and Barhoumi, W. (2004) A prelimary approach for the automated recognition of malignant melanoma. Image Analysis and Stereology Journal, 23(2), 121-135.
[20] Taouil, K. and Romdhane, N.B. (2006) Automatic segmentation and classification of skin lesion images. The 2nd International Conferences on Distributed Frameworks for Multimedica Applications, Pulau Pinang.
[21] Pudil, P., Novoviovca, J. and Kittler, J. (1994) Floating search methods in feature selection. Pattern Recognition Letters, 15, 1119-1125.
[22] Specht, D.F. (1991) A general regression neural network. IEEE Transactions on Neural Networks, 2, 568-576.
[23] Romdhane, N.B., Taouil, K., Boudaya, S. Turki, H. and Bouhlel, M.S. (2007) Sélection des Variables et Classification par Réseaux de Neurones des Lésions Dermatologiques. 4th International Conference: Sciences of Electronic, Technologies of Information and Telecommunications, Tunisia.
[24] Tokan, F., Türker, N. and Yıldırım, T. (2006) ROC analysis as a useful tool for performance evaluation of artificial neural networks. Artificial Neural Networks- ICANN 2006, 4132, 923-931.
[25] Zagrouba, E. and Barhoumi, W. (2005) An accelerated system for melanoma diagnosis based on subset feature selection. Journal of Computing and Information Technology, 13(1), 69-82.
[26] Vannoorenberghe, P., Colot, O. and de Brucq, D. (1999) Dempster-shafer’s theory as an aid to color information processing application to melanoma detection in dermatology. Proceedings of the 10th International Conference on Image Analysis and Processing, Venice, 774-779.
[27] Lefevre, E., Colot, O., Vannoorenberghe, P. and de Brucq, D. (2000) Knowledge modeling methods in the framework of evidence theory: An experimental comparison for melanoma detection Systems. 2000 IEEE International Conference on Man and Cybernetics, Nashville, 4, 2806- 2811.
[28] Sezgin, M. and Sankur, B. (2004) Survey over image thresholding techniques and quantitative performance evaluation. Journal of Electronic Imaging, 13(1), 146- 165.

comments powered by Disqus

Copyright © 2020 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.