Abstract
In this paper, we propose a classification technique for melanocytic lesions based on fundamentals of Information Theory. In particular, we evaluate the accuracy level of the Correntropy Coefficient as a similarity measure in classifying Melanoma and (common and atypical) nevi. These lesions were chosen because they are generally similar to each other, then it can be difficult to carry out a differential diagnosis of the melanocytic lesion type. The effectiveness of the proposed approach was verified through a case study using a public dermoscopic image dataset. The obtained results for performance evaluation and comparison show very high accuracy for melanoma classification which outperforms state-of-the-art approaches. Besides, considering the simplicity of the proposed technique and the results obtained, it is possible to use this approach in developing computational systems to support the medical diagnosis of melanomas.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27:379–423
Amelio L, Janković R, Amelio A (2018) A new dissimilarity measure for clustering with application to dermoscopic images. In: 2018 9th international conference on information, intelligence, systems and applications (IISA), pp 1–8
Bhise V, Rajan SS, Sittig DF, Morgan RO, Chaudhary P, Singh H (2018) Defining and measuring diagnostic uncertainty in medicine: a systematic review. J Gen Intern Med 33:103–115
Liu W, Pokharel PP, Principe JC (2006) Correntropy: a localized similarity measure, Vancouver, BC, Canada
Liu W, Pokharel PP, Principe JC (2007) Correntropy: properties and applications in non-Gaussian signal processing. IEEE Trans Signal Process 55:5286–5298
Jeong K-H, Liu W, Han S, Hasanbelliu E, Principe JC (2009) The correntropy MACE filter. Pattern Recognit 42:871–885
Giotisa I, Moldersb N, Landc S, Biehla M, Jonkmanb MF, Petkova N (2015) MED-NODE: a computer-assisted melanoma diagnosis system using non-dermoscopic images. Expert Syst Appl 42:6578–6585
Mendonça T, Ferreira PM, Marques JS, Marcal ARS, Rozeira J (2013) PH\(^2\)—a dermoscopic image database for research and benchmarking, Osaka, Japan
Araujo IC, Coelho CMS, Saliba GAM et al. (2014) Melanoma cutâneo: aspectos clínicos, epidemiológicos e anatomopatológicos de um centro de formação em Belo Horizonte. Rev Bras Cir Plást 29:497–503
Tovo LFR, Belfort FA, Junior JAS (2005) Melanoma cutâneo primário. Rev Assoc Méd Bras (Série: Diretrizes em foco—Medicina Baseada em Evidências) 51:7–8
Wainstein AJA, Belfort FA (2004) Conduta para o melanoma cutâneo. Rev Col Bras Cir 31:204–214
Castro1 LGM, Messina MC, Loureiro W et al (2015) Diretrizes da sociedade brasileira de dermatologia para diagnóstico, tratamento e acompanhamento do melanoma cutâneo primário—Parte I. An Bras Dermatol 90:851–861
Zager JS, Hochwald SN, Marzban SS et al. (2011) Shave biopsy is a safe and accurate method for the initial evaluation of melanoma. J Am Coll Surg 212:454–462
Câncer de pele melanoma. https://www.inca.gov.br/tipos-de-cancer/cancer-de-pele-melanoma. Accessed 29 May 2020
Silveira Junior LGQ, Gurjão EC, Pinto EL, Assis FM, Medeiros JLA (2003) Critérios para. Retirada de Arcos em Redes Bayesianas 1:668–673
Silveira Junior LGQ, Silveira LFQ, Gurjão EC, Pinto EL, Assis FM (2004) Ordenação de Variáveis em Redes Bayesianas com. Medidas de Informação Mútua de Shannon e Rényi
Li R, Liu W, Príncipe JC (2007) A unifying criterion for instantaneous blind source separation based on correntropy. Signal Process 89:1872–1881
Xu J-W, Bakardjian H, Cichocki A, Principe JC (2008) A new nonlinear similarity measure for multichannel signals. Neural Netw 21:222–231
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66
Barros WKP, Morais DS, Lopes FF, Torquato MF, Barbosa RM, Fernandes MAC (2020) Proposal of the CAD system for melanoma detection using reconfigurable computing. Sensors 20:3168
Acknowledgements
The authors would like to thank the financial support of PROPESQ/UFRN in developing the scientific initiation work carried out by one of the authors, whose results served as the basis for this work. The authors also acknowledge the support of the Group for Researching and Fast Prototyping Solutions for Communication (GPPCOM), of the Federal University of Rio Grande do Norte.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Conflict of Interests
The authors declare that they have no conflicts of interest.
Ethical Approval
This article does not contain any study with human or animal participants done by any of the authors.
Informed Consent
Formal consent is not necessary for this type of study.
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Silveira-Júnior, L.G.d.Q., Beserra, B., de Freitas, Y.K.R. (2022). Information Theory Applied to Classifying Skin Lesions in Supporting the Medical Diagnosis of Melanomas. In: Bastos-Filho, T.F., de Oliveira Caldeira, E.M., Frizera-Neto, A. (eds) XXVII Brazilian Congress on Biomedical Engineering. CBEB 2020. IFMBE Proceedings, vol 83. Springer, Cham. https://doi.org/10.1007/978-3-030-70601-2_258
Download citation
DOI: https://doi.org/10.1007/978-3-030-70601-2_258
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70600-5
Online ISBN: 978-3-030-70601-2
eBook Packages: EngineeringEngineering (R0)