Segmentation Strategies in Dermoscopy to Follow-up Melanoma: Combined Segmentation Scheme

Year 2015, Volume: 5 Issue: 3, 56 - 61, 23.07.2016

Jorge Pereira Rui Fonseca-pinto

Abstract

— Image processing techniques constitutes an important tool to improve skin cancer diagnose, whose early detection is still the most relevant prognostic factor. Nowadays, the follow-up of suspicious melanocytic skin lesions using standard protocols is possible after the development of digital image technology, enhancing the early detection strategy of the skin cancer diagnose. The correct selection of the borders in these particular images of skin microscopy is sometimes demanding, as these images possess particular artifacts (hairs and air bubbles).A stable algorithm to segment the border of the lesion is also important when the following up of suspicious melanocytic lesions uses quantitative markers, as accessing the geometry of the growth border, symmetry, area, among others. In this paper a new strategy to segment dermoscopy images is presented by merging two different approaches in image processing, the Empirical Mode Decomposition of the HilbertHuang Transform to remove common artifacts, followed by a Local Normalization to improve segmentation

Keywords

Segmentation, Local Normalization, Hilbert-Huang Transform, Dermoscopy, Melanoma

References

• Baumert, J., Schmidt, M., Giehl, K.A. (2009), Time trends in tumor thickness vary in sub- groups: analysis of 6475 patients by age, tumour site and melanoma subtype. Melanoma Res 2009; 19:24-30.
• Boyle, P., Doré. J.F., Autier, P., Ringborg, U. (2004). Cancer of the skin: a forgotten problem in Europe. Annals of Oncology 15:5-6.
• Celebi, M. E., Iyatomi, H., Schaefer, G., Stoecker, W. (2007). Lesion border detection in dermoscopy images. Computerized Medical Imaging and Graphics, vol 33, Issue 2, pp 148-153.
• Celebi, M. E., Aslandogan,Y. A., Stoecker,W.V., Iyatomi, H., Oka, H., Chen, X. (2006). Unsupervised Border Detection in Dermoscopy Images, SkinResearch and Technology.
• Erkol, B., Moss, R.H., Stanley, R.J., Stoecker, W.V., Hvatum, E.(2005). Automatic Lesion Boundary Detection in Dermoscopy Images Using Gradient Vector Flow Snakes, Skin Research and Technology, 11(1): 17-26.
• Ferlay, J., Steliarova-Foucher, E., Lortet-Tieulent, J., Rosso, S., Coebergh, J.W.W., Comber, H., Forman, D., Bray, F.(2012). Cancer incidence and mortality patterns in Europe: estimates for 40 countries in 2012. Eur J Cancer.
• Fonseca-Pinto, R., Ducla-Soares, J. L., Araújo, F., Aguiar, P., Andrade, A. (2009). On the influence of timeseries length in EMD to extract frequency content: Simulations and models in biomedical signals, Medical Engineering & Physics 31 713–719.
• Fonseca-Pinto, R., Caseiro, P., Andrade, A. (2010). Bi-dimensional Empirical Mode Decomposition (BEMD) in dermoscopic images: artefact removal and border lesion detection. Proceedings of the 7th IASTED international Conference Signal Processing, Pattern Recognition and Applications; 341-345.
• Haylo, N., Rahman. Z., Park, S. (2001). Information content in nonlinear local normalization processing of digital images, Proc. SPIE 4388, Visual Information Processing X, 129.
• Holterhues, C., Vries, E., Louwman, M.W. (2010). Incidence and trends of cutaneous malignancies in the Netherlands, 1989-2005, J Invest Dermatol 2010; 130:1807-12.
• Huang, N.E., Shen, Z., Long, S.R., Wu, M.C., Shih, H.H., Zheng, Q., Yen, N-C., Tung, C.C., Liu, HH., (1998).
• The Empirical mode decomposition and the Hilbert spectrum for nonlinear and nonstationary time-series analysis. Proc R Soc Lond A 454: 903- 995.
• Iyatomi, H., Oka, H., Saito, M. (2006). Quantitative Assessment of Tumor Extraction from Dermoscopy Images and Evaluation of Computer-based Extraction Methods for Automatic Melanoma Diagnostic System. Melanoma Research, 16(2): 183-190, 2006.
• Kasper, Dennis L; Braunwald, Eugene; Fauci, Anthony; et al. Harrison’s Principles of Internal Medicine, 16th ed. New York: McGraw-Hill, 2005.
• Melli, R., Grana, C., Cucchiara, R.(2006). Comparison of Color Clustering Algorithms for Segmentation of Dermatological Image, Proc. of the SPIE Medical Imaging Conf., 6144: 3S1-9.
• Pereira, J. M., A. Nogueira, C. Baptista, D. Fonseca-Pinto, R. (2015). An adaptive approach for skin lesion segmentation in dermoscopy images using a multiscale Local Normalization. Proceedings of the CIM series in Mathematical Sciences, Springer-Verlang (accepted)
• Sant, M., Allemani, C., Santaquilani, M. (2009). EUROCARE-4.Survival of cancer patients diagnosed in 1995- 1999. Results and commentary, Eur J Cancer, 45:931-91.