Abstract
This paper describes a new approach to automatic classification of melanocytic tumours based on features extracted from profilometric data. The clinical accuracy of dermatologists in identifying these tumours is only approximately 75%. Automatic classification is based on high resolution skin surface profiles of 4×4 mm2 size with 125 sample points per mm, generated with a laser profilometer. Three categories of profile features are extracted: Textural features, Fourier features and fractal features. Feature selection is performed to determine an optimal feature subset. As a quality measure for a given feature subset, the error rate of the nearest neighbour classifier estimated with the leaving-one-out method is used. With the optimal feature subset, feed forward neural networks with error backpropagation as learning function are trained. Several neural networks with different network topologies and learning parameters were trained to compare the classification performance. A three layer network with one hidden layer consisting of 20 units has shown the best performance of all considered neural networks with a classification error rate of 13.4%. The best results using the nearest neighbour classifier achieved an error rate of 6.8%.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
Literature
C.M. Balch, H.M. Shaw, S.-J. Soong and G.W. Milton, Veränderungen der klinischen und pathologischen Merkmale des Melanoms in den letzten 30 Jahren, in „Hautmelanome“, ed. C.M. Balch and G.W. Milton, Springer (1985).
J.A.H. Lee, Die Entstehung des Melanoms, in „Hautmelanome“, ed. C.M. Balch and G.W. Milton, Springer (1985).
Foley, J., A. van Dam, S. Feiner and J. Hughes, Computer Graphics: Principles and Practice, Addison Wesley (1990).
Ballard, D.H., C.M. Brown, Computer Vision, Prentice-Hall, Englewood Cliffs, NJ (1982).
Haralick, R.M., K.S. Shanmugam and I. Dinstein, Textural Features for Image Classification, IEEE Trans. SMC 3 (November 1973) pp.610–621.
A. Rosenfeld and J.S. Weszka, Picture Recognition, in „Digital Pattern Recognition“, ed. K.S.Fou, Springer, Berlin (1980).
Falconer, K.J., Fraktale Geometrie, Spektrum Akademischer Verlag, Heidelberg (1993).
Rosenfeld, A., A. Kak, Digital Picture Processing, Second Edition, Acadamic Press, San Diego (1982).
A.K. Jain, Advances in statistical pattern recognition, in „Pattern recognition Theory and Applications“, ed. P.A. Devijver and J. Kittler, Springer, Berlin (1986).
Niemann, H., Klassifikation von Mustern, Springer, Berlin (1983).
Jain, A.K, R.C. Dubes, Algorithms for Clustering Data, Prentice Hall, Englewood Cliffs, NJ (1988).
Ritter, H., T. Martinez and K. Schulten, Neuronale Netze, Addison-Wesley, Bonn (1992).
S. Raudys and A.K. Jain, Small sample size problems in designing artificial neural networks, in „Artificial Neural Networks and statistical Pattern Recognition“, ed. I.K. Sethi and A.K. Jain, Elsevier Science Publishers, Amsterdam (1991).
D.E. Rumelhart, G.E. Hinton and R.J. Wiliams, Learning Internal Representations by Error Propagation, pp.318–362 in „Parallel Distributed Processing“, ed. D.E. Rumelhart, A G.E. Hinton, R.J. Wiliams, The MIT Press, Cambridge, Massachusetts (1986).
Zell, A., The SNNS Neural Network Simulator, Proc. of the 13. DAGM-Symposium (1991) pp.454–461.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Roß, T., Handels, H., Kreusch, J., Busche, H., Wolf, H.H., Pöppl, S.J. (1995). Automatic classification of skin tumours with high resolution surface profiles. In: Hlaváč, V., Šára, R. (eds) Computer Analysis of Images and Patterns. CAIP 1995. Lecture Notes in Computer Science, vol 970. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-60268-2_318
Download citation
DOI: https://doi.org/10.1007/3-540-60268-2_318
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-60268-2
Online ISBN: 978-3-540-44781-8
eBook Packages: Springer Book Archive