Building of Readable Decision Trees for Automated Melanoma Discrimination
Even expert dermatologists cannot easily diagnose a melanoma, because its appearance is often similar to that of a nevus, in particular in its early stage. For this reason, studies of automated melanoma discrimination using image analysis have been conducted. However, no systematic studies exist that offer grounds for the discrimination result in a readable form. In this paper, we propose an automated melanoma discrimination system that it is capable of providing not only the discrimination results but also their grounds by means of utilizing a Random Forest (RF) technique. Our system was constructed based on a total of 1,148 dermoscopy images (168 melanomas and 980 nevi) and uses only their color features in order to ensure the readability of the grounds for the discrimination results. By virtue of our efficient feature selection procedure, our system provides accurate discrimination results (a sensitivity of 79.8 % and a specificity of 80.7 % with 10-fold cross-validation) under human-oriented limitations and presents the grounds for the results in an intelligible format.
KeywordsRandom Forest Feature Selection Method Weak Learner Random Forest Classifier Good Classification Performance
This research was partially supported by the Ministry of Education, Culture, Science and Technology of Japan (Grant in-Aid for Fundamental research program (C), 26461666, 2014-2017).
- 1.National Cancer Institute: SEER Cancer Statistics Review 1975–2012. NCI, Bethesda, MD (2015)Google Scholar
- 3.Stolz, W., Riemann, A., Cognetta, A.B., Pillet, L., Abmayr, W., Holzel, D., et al.: ABCD rule of dermoscopy: a new practical method for early recognition of malignant melanoma. Eur. J. Dermatol. 4(7), 521–527 (1993)Google Scholar
- 4.Argenziano, G., Fabbrocini, G., Carli, P., Giorgi, V.D., et al.: Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis. Arch. Dermatol. 134(12), 1563–1570 (1998)Google Scholar
- 5.Stolz, W., Falco, O.B., Bliek, P., Kandthaler, M., Burgdorf, W.H.C., Cognetta, A.B.: Color Atlas of Dermatoscopy, 2nd enlarged and completely revised edn. Blackwell Publishing, Berlin (2002)Google Scholar
- 11.Iyatomi, H., Oka, H., Celebi, M.E., Tanaka, M., Ogawa, K.: Parameterization of dermoscopic findings for the Internet-based melanoma diagnostic system. In: Proceedings of the IEEE CIISP 2007, pp. 183–193 (2007)Google Scholar