Abstract
Mammography associated with clinical breast examination is the only effective method for mass breast screening. Microcalcifications are one of the primary signs for early detection of breast cancer. In this paper we propose a new kernel method for classification of dificult to diagnose regions in mammographic images. It consists of a novel class of Markov Random Fields, using techniques developed within the context of statistical mechanics. This method is used for the classification of positive Region of Interest (ROI’s) containing clustered microcalcifications and negative ROI’s containing normal tissue. We benchmarked the new proposed method with a nearest neighbor classifier and with an artificial neural network, widely used in literature for computer-aided diagnosis. We obtained the best performance using the novel approach.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
D. J. Amit, “Modeling Brain Function”, Cambridge University Press, 1989.
C. M. Bishop, Neural Networks for Pattern Recognition, Claredon Press-Oxford, 1995.
B. Caputo, G. E. Gigante, “Digital Mammography: a Weak Continuity Texture Representation for Detection of Microcalcifications”, Proc. of SPIE Medical Imaging 2001, February 17-22, VOL 4322, PP1705–1716, San Diego, (CA), USA, 2001.
B. Caputo, H. Niemann, “From Markov Random Fields to Associative Memories and Back: Spin Glass Markov Random Fields”, SCTV2001.
J. J. Hopfield, “Neurons with graded response have collective computational properties like those of two-state neurons”, Proc. Natl. Acad. Sci. USA, Vol. 81, pp 3088–3092, 1984.
A. K. Jain, “Fundamental of digital image processing”, Prentice Hall, Englewood Cliffs, 1989.
M. Lanyi, “Diagnosis and Differential Diagnosis of Breast Calcifications”, New York: Springer-Verlag, 1986.
R. P. Lippmann, “An introduction to computing with neural nets”, IEEE ASSP Magazine, pp. 4–22, April 1987.
M. Mezard, G. Parisi, M. Virasoro, “Spin Glass Theory and Beyond”, World Scientific, Singapore, 1987.
S. Morio and S. Kawahara et al., “Expert system for early detection of cancer of the breast”, Comp. Biol. Med., vol. 19, no. 5, pp. 295–305, 1989.
Nishikawa RM, Wolverton DE, Schmidt RA, Papaioannou J, “Radiologists’ ability to discriminate computer-detected true and false positives, from an automated scheme for the detection of clustered microcalcifications on digital mammograms”, Proc SPIE 3036: 198–204, 1997.
D. E. Rumelhart and C.R. Rosemberg, Parallel Distributed Processing, the MIT Press, Cambridge MA, 1986.
B. Schiele, J. L. Crowley, “Recognition without correspondence using multidimensional receptive field histograms”, IJCV, 36 (1), pp. 31–52, 2000.
B. Schölkopf, A. J. Smola, Learning with kernels, 2001, the MIT Press.
L. Shen, R. M. Rangayyan and J. E. L. Desautels, “Application of shape analysis to mammographic calcifications”, IEEE Trans. Med Imag., vol. 13, no. 2, pp. 263–274, 1994.
E. A. Sickles and D. B. Kopans, “Mammographic screening for women aged 40 to 49 years: the primary practitioner’s dilemma”, Anna. Intern. Med., vol. 122, no. 7, pp. 534–538, 1995.
M. Swain, D. Ballard, “color Indexing”, IJCV, 7, pp 11–32, 1991.
V. Vapnik, Statistical learning theory, J. Wiley, New York, 1998.
Zhang W, Doi K, Giger ML, Nishikawa RM, Schmidt RA, “An improved shift-invariant artificial neural network for computerized detection of clustered microcalcifications in digital mammograms”. Med Phys, 23: 595–601, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Caputo, B., La Torre, E., Gigante, G.E. (2002). Microcalcification Detection Using a Kernel Bayes Classifier. In: Colosimo, A., Sirabella, P., Giuliani, A. (eds) Medical Data Analysis. ISMDA 2002. Lecture Notes in Computer Science, vol 2526. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36104-9_3
Download citation
DOI: https://doi.org/10.1007/3-540-36104-9_3
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00044-0
Online ISBN: 978-3-540-36104-6
eBook Packages: Springer Book Archive