Automatic Segmentation of Dermoscopy Images Using Histogram Thresholding on Optimal Color Channels

Authors: Rahil Garnavi, Mohammad Aldeen, M. Emre Celebi, Alauddin Bhuiyan, Constantinos Dolianitis, George Varigos

Abstract:

Automatic segmentation of skin lesions is the first step towards development of a computer-aided diagnosis of melanoma. Although numerous segmentation methods have been developed, few studies have focused on determining the most discriminative and effective color space for melanoma application. This paper proposes a novel automatic segmentation algorithm using color space analysis and clustering-based histogram thresholding, which is able to determine the optimal color channel for segmentation of skin lesions. To demonstrate the validity of the algorithm, it is tested on a set of 30 high resolution dermoscopy images and a comprehensive evaluation of the results is provided, where borders manually drawn by four dermatologists, are compared to automated borders detected by the proposed algorithm. The evaluation is carried out by applying three previously used metrics of accuracy, sensitivity, and specificity and a new metric of similarity. Through ROC analysis and ranking the metrics, it is shown that the best results are obtained with the X and XoYoR color channels which results in an accuracy of approximately 97%. The proposed method is also compared with two state-ofthe- art skin lesion segmentation methods, which demonstrates the effectiveness and superiority of the proposed segmentation method.

Keywords: Border detection, Color space analysis, Dermoscopy, Histogram thresholding, Melanoma, Segmentation.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1058449

References:

[1] G. Argenziano, H. P. Soyer, S. Chimenti, and R. T. et al., "Dermoscopy of pigmented skin lesions: Results of a consensus meeting via the Internet," Journal of the American Academy of Dermatology, vol. 48, pp. 679-693, 2003.
[2] P. Braun, H. Rabinovitz, M. Oliviero, A. Kopf, and J. Saurat, "Dermoscopy of pigmented lesions," Journal of the American Academy of Dermatology, vol. 52, no. 1, pp. 109-121, 2005.
[3] A. Perrinaud, O. Gaide, L. French, J.-H. Saurat, A. Marghoob, and R. Braun, "Can automated dermoscopy image analysis instruments provide added benefit for the dermatologist? A study comparing the results of three systems," British Journal of Dermatology, vol. 157, pp. 926-933, 2007.
[4] M. E. Celebi, H. Iyatomi, G. Schaefer, and W. V. Stoecker, "Lesion border detection in dermoscopy images," Computerized Medical Imaging and Graphics, vol. 33, no. 2, pp. 148-153, 2009.
[5] H. Iyatomi, H. Oka, M. E. Celebi, M. Hashimoto, M. Hagiwara, M. Tanaka, and K. Ogawa, "An improved internet-based melanoma screening system with dermatologist-like tumor area extraction algorithm," Computerized Medical Imaging and Graphics, vol. 32, no. 7, pp. 566-579, 2008.
[6] M. Hintz-Madsen, L. K. Hansen, J. Larsen, and K. T. Drzewiecki, "A probabilistic neural network framework for the detection of malignant melanoma." Artificial neural networks in cancer diagnosis. Prognosis and Patient Management, pp. 141-183, 2001.
[7] R. Melli, C. Grana, and R. Cucchiara, "Comparison of color clustering algorithms for segmentation of dermatological images," in SPIE Medical Imaging, vol. 6144, 2006, pp. 3S1-3S9.
[8] G. Hance, S. Umbaugh, R. Moss, and W. V. Stoecker, "Unsupervised color image segmentation:With application to skin tumor borders," IEEE Engineering in Medicine and Biology Magazine, vol. 15, pp. 104-111, 1996.
[9] P. Schmid, "Segmentation of digitized dermatoscopic images by twodimensional color clustering," IEEE Transactions on Medical Imaging, vol. 18, no. 2, pp. 164-171, 1999.
[10] M. E. Celebi, Y. A. Aslandogan, W. V. Stoecker, H. Iyatomi, H. Oka, and X. Chen, "Unsupervised border detection in dermoscopy images," Skin Research and Technology, vol. 13, pp. 454-462, 2007.
[11] M. E. Celebi, H. A. Kingravi, H. Iyatomi, Y. A. Aslandogan, W. V. Stoecker, R. H. Moss, J. M. Malters, J. M. Grichnik, A. A. Marghoob, H. S. Rabinovitz, and S. W. Menzies, "Border detection in dermoscopy images using statistical region merging," Skin Research and Technology, vol. 14, pp. 347-353, 2008.
[12] T. Lee, , V. Ng, R. Gallagher, A. Coldman, and D. McLean, "Dullrazor: A software approach to hair removal from images," Computers in Biology and Medicine, vol. 27, pp. 533-543, 1997.
[13] L. Lucchese and S. Mitra, "Color image segmentation: A state-of-theart survey," in Proceedings of Indian National Science Academy Part A, PINSA2001, 2001, pp. 207-221.
[14] K. N. Plataniotis and A. N. Venetsanopoulos, Color Image Processing and Applications. Springer, 2000.
[15] N. Otsu, "A threshold selection method from gray-level histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, 1979.
[16] R. M. Haralick and L. G. Shapiro, Computer and Robot Vision. Addison-Wesley, 1992, vol. 1.
[17] M. E. Celebi, G. Schaefer, H. Iyatomi, W. V. Stoecker, J. M. Malters, and J. M. Grichnik, "An improved objective evaluation measure for border detection in dermoscopy images," to appear in Skin Research and Technology.
[18] T. Sorensen, "A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on danish commons." Royal Danish Academy of Sciences and Letters, vol. 5, pp. 1-34, 1948.
[19] J. Davis and M. Goadrich, "The relationship between precision-recall and roc curves," in Proceeding of 23rd International Conference on Machine Learning (ICML), vol. 148, 2006, pp. 233-240.