Classification of Melanoma Thickness from Dermoscopic Images using Mobile Devices

Dr. B. Muthusenthil, Valliammai Engineering College; Ravishanker Satish ,Valliammai Engineering College; Sivaraman. V ,Valliammai Engineering College; Srinath. R. M ,Valliammai Engineering College

Melanoma, Dermoscopic images, Image analysis, Classification methods

The survival of patients with melanoma is mainly dependent on the thickness of the melanoma. The depth of the melanoma is usually give in millimeters then calculated using pathological examination following a biopsy of the suspected lesion. To avoid invasive methods in the estimation of the thickness of the melanoma prior to surgery we propose a computational image analysis system from dermoscopic images. A recent interpretable method merging logistic regression along with artificial networks (LIPU) logistic regression using initial variables and product units, which are nominal classification methods, are compared in terms of performance. In case of binary classification LIPU performs with an accuracy of 77.6% compared to all other methods while in case of the second scheme the ordinal classification methods achieve a better balance between the performances of all classes even though LIPU reports the highest overall accuracy.
    [1] P. Guti´errez, M. P´erez-Ortiz, J. S´anchez-Monedero, F. Fernandez- Navarro, and C. Herv´as-Mart´inez, “Ordinal regression methods: survey and experimental study,” IEEE Transactions on Knowledge and Data Engineering, vol. In press, no. 99, 2015. [2] Bag-of-Features Classification Model for the Diagnose of Melanoma in Dermoscopy Images Using Color and Texture Descriptors Catarina Barata1, Jorge S. Marques1, and Teresa Mendon¸ca2 M. Kamel and A. Campilho (Eds.): ICIAR 2013, LNCS 7950, pp. 547–555, 2013.c Springer-Verlag Berlin Heidelberg 2013 [3] Texture Information in Melanocytic Skin Lesion Analysis Based on Standard Camera Images, Pablo G. CavalcantiJacobScharcansk Part of the Series in bioengineering book series (SERBIOENG) 27 September 2013 [4] Evaluation of cutaneous melanoma thickness by digital dermoscopy analysis: a retrospective study. Rubegni P1, Cevenini G, Sbano P, Burroni M, Zalaudek I, Risulo M, Dell'Eva G, Nami N, Martino A, Fimiani M Melanoma Res. 2010 Jun;20(3):212-7. doi: 10.1097/CMR.0b013e328335a8ff [5] P. Cavalcanti and J. Scharcanski, “Texture Information in Melanocytic Skin Lesion Analysis Based on Standard Camera Images,” in Computer Vision Techniques for the Diagnosis of Skin Cancer, J. Scharcanski and M. E. Celebi, Eds. Springer Berlin Heidelberg, 2014, pp. 221–242. [6] G. Argenziano, C. Longo, A. Cameron, S. Cavicchini, J.-Y. Gourhant, A. Lallas, I. McColl, C. Rosendahl, L. Thomas, D. Tiodorovic-Zivkovic, P. Zaballos, and I. Zalaudek, “Blue-black rule: a simple dermoscopic clue to recognize pigmented nodular melanoma,” British Journal of Dermatology, vol. 165, no. 6, pp. 1251–1255, 2011. [7] A review on diagnosis of nutrient deficiency symptoms in plant leaf image using digital image processing s. jeyalakshmi1 and r. radha2, ictact journal on image and video processing, May 2017, volume: 07, issue: 04 [8] Computer-Aided Diagnosis of Melanoma Using Border and Wavelet-Based Texture AnalysisGarnavi R, Aldeen M, Bailey J IEEE Trans InfTechnol Biomed. 2012 Nov; 16(6):1239-52. doi: 10.1109/TITB.2012.2212282. E-pub 2012 Aug 8. [9] A survey on Automatic Analysis of Statistical Properties of Rheumatoid Arthritis using Digital Image Processing Prof G.S. Mate1 , Dr. A. K. Kureshi2 , 30th July,2017 [10] H.-T. Lin and L. Li, “Reduction from cost-sensitive ordinal ranking to weighted binary classification,” Neural Computation, vol. 24, no. 5, pp. 1329–1367, 2012. [11] A survey on deep learning in medical image analysis Author links open overlay panel GeertLitjensThijsKooiBabak Ehteshami Bejnordi LaakBramvan GinnekenClara I.Sánchez,Received 27 February 2017, Revised 24 July 2017, Accepted 25 July 2017, Available online 26 July 2017. [12] Automatic bone boundary detection in hand radiographs by using modified level set method and diffusion filter. Garcia In IEEE 6th International Workshop on Computational Intelligence and Applications, Hiroshima, Japan, July 13, 2013.
Paper ID: GRDJEV03I050069
Published in: Volume : 3, Issue : 5
Publication Date: 2018-05-01
Page(s): 24 - 30