Mobile Application for diagnosis of malignant melanoma using ID3 algorithm and border irregularity and asymmetry
DOI:
https://doi.org/10.30973/progmat/2017.9.1/4Keywords:
ID3, Asymmetry, decision tree, malignant melanoma, AndroidAbstract
In this paper, an application developed on Android platform for diagnosis of malignant melanoma is presented. Clinical features used for diagnosis of malignant melanoma are based on: Asymmetry, Border, Color and Diameter or ABCD rule of the cutaneous lesion. In this research the asymmetry and the border irregularity are considered. Image processing techniques applied are morphological operations and edge detectors which allow calculate the border irregularity and asymmetry index such as IC and AL. A decision tree was built to generate rules and classify the type of skin lesions. The classification precision was 76% obtained with thirty tests and evaluated through cross-validation, which implies that it can be improved.
References
Zaballos, P., Carrera, C., Puig, S., Malvehy, J. Criterios dermatoscópicos para el diagnóstico del melanoma. Medicina Cutánea Ibero-Latino-Americana. 2004, 32 (1), 3-17.
Lee, T. K., McLean, D. I., Atkins, M. S. Irregularity index: a new border irregularity measure for cutaneous melanocytic lesions. Medical image analysis. 2003, 7(1), 47-64. https://doi.org/10.1016/S1361-8415(02)00090-7
Celebi, M. E., Kingravi, H. A., Uddin, B., Iyatomi, H., Aslandogan, Y. A., Stoecker, W. V., Moss, R. H. A methodological approach to the classification of dermoscopy images. Computerized Medical Imaging and Graphics. 2007,31(6), 362-373. https://doi.org/10.1016/j.compmedimag.2007.01.003
Ogorzałek, M., Alekseenko, A., Surówka, G., Nowak, L. Modern techniques for computer-aided melanoma diagnosis. INTECH Open Access Publisher, 2011. https://doi.org/10.5772/23388
Sánchez-Hernández, J. P., Hernández-Rabadán, D. L. Comparison of classification methods applied to the diagnosis of malignant melanoma using asymmetry. Programación Matemática y Software. 2014, 6(2), 51-56. http://doi.org/10.30973/progmat/2014.6.2/7
Patel, S., Eluri, M., Boyers, L. N., Karimkhani, C., & Dellavalle, R. Update on mobile applications in dermatology. Dermatology Online Journal. 2015, 21(2), 1-5.
Vañó-Galván, S., Paoli, J., Ríos-Buceta, L., Jaén, P. Skin self-examination using smartphone photography to improve the early diagnosis of melanoma. Actas Dermo-Sifiliográficas. 2015, 106(1), 75-77. https://doi.org/10.1016/j.ad.2014.05.009
University of Michigan Health System (UMHS). Skin Cancer Self-Exam Mobile App. Recuperado el 17 de diciembre de 2015 de http://www.uofmhealth.org/patient%20and%20visitor%20guide/myskin-check-app, 2015.
Cardiff University (CU). Virtual Dermatoscope – iPhone App. Recuperado el 17 de diciembre de 2015 de http://sites.cardiff.ac.uk/dermatology/courses/an-introduction-to-dermoscopy/virtual-dermatoscope-iphone-app/, 2015.
Cook, W. Is that little mole a big problem? Ask Doctor Mole, the smartphone app that checks for signs of skin cancer [en línea]. Daily mail seccion science. Recuperado el 17 de diciembre de 2015 de http://www.dailymail.co.uk/sciencetech/article-2212200/DoctorMole-The-smartphone-app-checks-signs-skin-cancer.html, 2012.
Ávila de Tomas, J.F. APP´s Medicina, Dermomap. Recuperado el 17 de Diciembre de 2015 de https://appsmedicina.com/es/apps/detalle_app.php?id=16, 2014.
Quinlan, J. R. Induction of decision trees. Machine Learning. 1986, 1(1), 81-106. https://doi.org/10.1007/BF00116251
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2017 Juan Paulo Sánchez Hernández, Alma Delia Nieto Yañez, Miguel Ángel Velasco Castillo, Deny Lizbeth Hernández Rabadán
This work is licensed under a Creative Commons Attribution 4.0 International License.
Usted es libre de:
Compartir — compartir y redistribuir el material publicado en cualquier medio o formato. |
Adaptar — combinar, transformar y construir sobre el material para cualquier propósito, incluso comercialmente. |
Bajo las siguientes condiciones:
Atribución — Debe otorgar el crédito correspondiente, proporcionar un enlace a la licencia e indicar si se realizaron cambios. Puede hacerlo de cualquier manera razonable, pero de ninguna manera que sugiera que el licenciador lo respalda a usted o a su uso. |
Sin restricciones adicionales: no puede aplicar términos legales o medidas tecnológicas que restrinjan legalmente a otros a hacer cualquier cosa que permita la licencia. |