Abstract
In this paper we present a new feature extraction technique for digital mammograms. Our approach uses Independent Component Analysis to find the source regions that generate the observed regions of suspicion in mammograms. The linear transformation coefficients, which result from the source regions, are used as features that describe the observed regions in an effective way. A Principal Component Analysis preprocessing step is used to reduce dramatically the features vector dimensionality and improve the classification accuracy of a Radial Basis Function neural classifier. Extensive experiments in the MIAS database using a very small dimensioned feature vector gave a recognition accuracy of 88.23% when detecting all kinds of abnormalities which outperforms significantly the accuracy of the commonly used statistical texture descriptors.
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
Preview
Unable to display preview. Download preview PDF.
References
Martin, J., Moskowitz, M. and Milbrath, J.: Breast cancer missed by mammography. AJR, Vol. 132. (1979) 737
Kalisher, L.: Factors influencing false negative rates in xero-mammography. Radiology, Vol.133. (1979) 297
Tabar, L. and Dean, B.P.: Teaching Atlas of Mammography. 2nd edition, Thieme, NY (1985)
Christoyianni, I., Dermatas, E., and Kokkinakis, G.: Fast Detection of Masses in Computer-Aided Mammography. IEEE Signal Processing Magazine, vol. 17, no 1. (2000) 54–64
Meersman, D., Scheunders, P. and Dyck, Van D.: Detection of Microcalcifications using Neural Networks. Proc. of the 3rd Int. Workshop on Digital Mammograph, Chicago, IL (1996) 97–103
Dhawan, P.A., Chite, Y., Bonasso, C. and Wheeler K.: Radial-Basis-Function Based Classification of Mammographic Microcalcifications Using Texture Features. IEEE Engineering in Medicine and Biology & CMBEC (1995) 535–536
Doi, K., Giger, M., Nishikawa, R., and Schmidt, R. (eds.): Digital Mammography 96. Elsevier Amsterdam (1996)
Christoyianni, I., Dermatas, E., and Kokkinakis, G.: Neural Classification of Abnormal tissue in Digital Mammography Using Statistical Features of the Texture. IEEE International Conference on Electronics, Circuits and Systems, vol 1. (1999) 117–120
Lee, Te-Won: Independent Component Analysis: Theory and Applications. Kluwer Academic Publishers (1998)
Bartlett, M., Lades, M., Sejnowski, T.: Independent component representation for face recognition. Proc. SPIE Symposium on Electronic Imaging: Science and Technology (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Koutras, A., Christoyianni, I., Dermatas, E., Kokkinakis, G. (2001). Feature Extraction in Digital Mammography: An Independent Component Analysis Approach. In: Mira, J., Prieto, A. (eds) Bio-Inspired Applications of Connectionism. IWANN 2001. Lecture Notes in Computer Science, vol 2085. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45723-2_96
Download citation
DOI: https://doi.org/10.1007/3-540-45723-2_96
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42237-2
Online ISBN: 978-3-540-45723-7
eBook Packages: Springer Book Archive