Abstract
This paper presents an application of multi-layered networks to medical images analysis. Different architectures of networks are tested for a detection task on mammograms. Their training with the Gradient Back Propagation algorithm is realized on small images extracted from digitized mammograms and labeled according to the presence of microcalcifications amongst the breast parenchyma background structures. The classification performances we obtain demonstrate that an appropriate network architecture for this task should involve local connections, probably combined with shared weights, and also suggest that some adequate preprocessing might lead to more efficient results.
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
Bottou L. Y.: “Reconnaissance de la parole par réseaux multi-couches”, Proc. NeuroNîmes 88, EC2 eds (1988).
Bottou L. Y., Le Cun Y.: “SN, un simulateur pour réseaux connexionnistes”, Proc. Neurîmes 88, EC2 eds (1988).
Gorman R. P., Sejnowski T. J.: Analysis of hidden units in a layered network trained to classify sonar targets, Neural networks, vol. 1, n° 1, 75–89, (1988).
Lamarque J. L.: Le Sein, radiodiagnostic clinique, Medsi (1981).
Le Cun Y.: Modèles Connexionnistes de l’Apprentissage, Thesis, Paris (1987).
Le Cun Y.: “Character recognition”, unpublished manuscript.
Lehky S. R., Sejnowski T. J.: Extracting curvatures of 3-D objects using a neural network, Soc. for Neuroscience Abstracts, 13, (1987), 1451.
Obellianne C.: Mise au point d’un système connexionniste pour la détection de microcalcifications dans des images mammographiques numérisées. Internai report EHEI (January, 1989).
Rosenfeld A., Kak A. C.: Digital Picture Processing, Academic Press, Vol. 1 (1982).
Tabâr L., Dean P. B.: Teaching Atlas of Mammography, Georg Thieme Verlag (1985).
Waibel A., Hanazawa T., Hinton G., Shikano K.: “Phoneme recognition using time-delay neural networks”, Tech. Report TR-I-0006, Adv. Telecom. Res. Inst., Japan (1987).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bourrely, C., Muller, S. (1990). Detection of microcalcifications in mammographic images. In: Soulié, F.F., Hérault, J. (eds) Neurocomputing. NATO ASI Series, vol 68. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76153-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-76153-9_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-76155-3
Online ISBN: 978-3-642-76153-9
eBook Packages: Springer Book Archive