Abstract
The increasing incidence of melanoma skin cancer is alarming. The lack of objective diagnostic procedures encourages development of computer aided approaches. Presented research uses three different machine learning methods, namely the Naive Bayes classifier, the Random Forest and the K* instance-based classifier together with two meta-learning algorithms: the Bootstrap Aggregating (Bagging) and the Vote Ensemble Classifier. Diagnostic accuracy of the selected methods, such as sensitivity and specificity and the area under the ROC curve, are discussed. The obtained results confirm that clinical history context and dermoscopic structures present in the images are important and can give accurate diagnostic classification of the lesions.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Abder-Rahman, A.A., Deserno, T.M.: A systematic review of automated melanoma detection in dermatoscopic images and its ground truth data. In: Proceedings of the SPIE 8318, Medical Imaging: Image Perception, Observer Performance, and Technology Assessment, 83181 (2012)
Alcn, J.F., Ciuhu, C., Kate, W., et al.: Automatic imaging system with decision support for inspection of pigmented skin lesions and melanoma diagnosis. IEEE J. Sel. Top. Sign. Proces. 3(1), 14–25 (2009)
American Cancer Society, Cancer Facts & Figures (2014). http://www.cancer.org/acs/groups/content/@research/documents/webcontent/acspc-042151.pdf. Accessed 16 Nov 2014
Argenziano, G., Soyer, H.P., Chimenti, S., et al.: Dermoscopy of pigmented skin lesions: results of a consensus meeting via the Internet. J. Am. Acad. Dermatol. 48, 679–693 (2003)
Argenziano, G., Soyer, H.P., De Giorgio, V., et al.: Interactive Atlas of Dermoscopy. Edra Medical Publishing & New Media, Milan (2000)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Carli, P., Quercioli, E., Sestini, S., et al.: Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology. Br. J. Dermatol. 148(5), 981–984 (2003)
Cleary, J.G., Trigg, L.E.: K*: An instance-based learner using an entropic distance measure. In: 12th International Conference on Machine Learning, pp. 108–114 (1995)
Codella, N., Cai, J., Abedini, M., et al.: Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. In: Zhou, L., Wang, L., Wang, Q., Shi, Y. (eds.) MLMI 2015. LNCS, pp. 118–126. Springer, Switzerland (2015)
van Erkel, A.R., Pattynama, P.M.: Th: Receiver operating characteristic (ROC) analysis: Basic principles and applications in radiology. Eur. J. Radiol. 27(2), 88–94 (1997)
Gachon, J., Beaulieu, P., Sei, J.F., Gouvernet, J., et al.: First prospective study of the recognition process of melanoma in dermatological practice. Arch. Dermatol. 141(4), 434–438 (2005)
Grzesiak-Kopeć, K., Nowak, L., Ogorzałek, M.: Automatic diagnosis of melanoid skin lesions using machine learning methods. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2015, pp. 577–585. Springer, Switzerland (2015)
Hall, M., Frank, E., Holmes, G., et al.: The WEKA data mining software: an update. SIGKDD Explor. 11(1), 10–18 (2009)
International Society for Digital Imaging of the Skin. http://www.ifcc.org/ifccfiles/docs/190404200805.pdf. Accessed 20 Dec 2015
Jia, S., Hu, X., Sun, L.: The comparison between random forest and support vector machine algorithm for predicting-hairpin motifs in proteins. Engineering 5, 391–395 (2013)
Johr, R.H.: Dermoscopy: alternative melanocytic algorithms - the ABCD rule of dermatoscopy, menzies scoring method, and 7-point checklist. Clin. Dermatol. 20, 240–247 (2002)
Madooei, A., Drew, M.S., Sadeghi, M., Atkins, M.S.: Automatic detection of blue-white veil by discrete colour matching in dermoscopy images. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013, Part III. LNCS, vol. 8151, pp. 453–460. Springer, Heidelberg (2013)
Manousaki, A.G., Manios, A.G., Tsompanaki, E.I., et al.: A simple digital image processing system to aid in melanoma diagnosis in an everyday melanocytic skin lesion unit: a preliminary report. Int. J. Dermatol. 45(4), 402–410 (2006)
Melanoma research gathers momentum: The Lancet, 385(9985): 2323 (2015)
Menzies, S.W., Bischof, L., Talbot, H., et al.: The performance of solarscan: an automated dermoscopy image analysis instrument for the diagnosis of primary melanoma. Arch. Dermatol. 141, 1388–1396 (2005)
Michalski, R.S., Kaufman, K., Pietrzykowski, J., et al.: Natural Induction and Conceptual Clustering: A Review of Applications, Reports of the Machine Learning and Inference Laboratory, MLI 06–3, George Mason University, Fairfax, VA, (Updated: 23 August 2006) June 2006
Nowak, L.A., Pawłowski, M.P., Grzesiak-Kopeć, G.-K., Ogorzałek, M.J.: Color calibration model of skin lesion images for computer-aided diagnostic. In: Proceedings of the Operations Research and its Applications in Engineering, Technology and Management 2013 (ISORA 2013), pp. 1–5 (2013)
Nowak, L., Grzesiak-Kopeć, K., Ogorzałek, M.: Melanocytic globules detection in skin lesion images. In: Proceedings of the ISORA 2015, Luoyang, China, 21–24 August, pp. 215–219 (2015)
Obuchowski, N.A.: Receiver operating characteristic curves and their use in radiology. Radiology 229, 3–8 (2003)
Oliveria, S.A., Selvam, N., Mehregan, D., et al.: Biopsies of nevi in children and adolescents in the United States, 2009 through 2013. JAMA Dermatol. 151(4), 447–448 (2015)
Ogorzałek, M., Surówka, G., Nowak, L., Merkwirth, C.: Computational intelligence and image processing methods for applications in skin cancer diagnosis. In: Fred, A., Filipe, J., Gamboa, H. (eds.) BIOSTEC 2009. CCIS, vol. 52, pp. 3–20. Springer, Heidelberg (2010)
Ogorzałek, M.J., Nowak, L., Surówka, G., Alekseenko, A.: Modern Techniques for Computer-Aided Melanoma Diagnosis, Melanoma in the Clinic - Diagnosis, Management and Complications of Malignancy, Prof. Mandi Murph (Ed.). InTech (2011). ISBN: 978-953-307-571-6
Rajpara, S.M., Botello, A.P., Townend, J., Ormerod, A.D.: Systematic review of dermoscopy and digital dermoscopy/artificial intelligence for the diagnosis of melanoma. Br. J. Dermatol. 161(3), 591–604 (2009)
Statnikov, A., Aliferis, C.F.: Are random forests better than support vector machines for microarray-based cancer classification? In: Proceedings of the AMIA Annual Symposium 2007, pp. 686–690 (2007)
Surówka, G., Grzesiak-Kopeć, K.: Different learning paradigms for the classification of melanoid skin lesions using wavelets. In: Conference Proceedings of the IEEE Engineering in Medicine and Biology Society, pp. 3136–3139 (2007)
Imundić, A.M.: Measures of diagnostic accuracy: basic definitions. http://www.ifcc.org/ifccfiles/docs/190404200805.pdf. Accessed 20 Dec (2015)
Zhang, H.: The optimality of naive bayes. In: FLAIRS Conference (2004)
Acknowledgment
This research has been supported by The National Centre for Research and Development (NCBR) grant TANGO1/266877/NCBR/2015.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Grzesiak-Kopeć, K., Ogorzałek, M., Nowak, L. (2016). Computational Classification of Melanocytic Skin Lesions. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2016. Lecture Notes in Computer Science(), vol 9693. Springer, Cham. https://doi.org/10.1007/978-3-319-39384-1_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-39384-1_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-39383-4
Online ISBN: 978-3-319-39384-1
eBook Packages: Computer ScienceComputer Science (R0)