Abstract
Breast cancer is the second leading cause of female mortality in the world [1],[2]. In Brazil, annually, about 10,000 deaths are detected in female population. Mammographic screening is the most efficient method to identify early breast cancer. However, of all previously diagnosed suspicions lesions and sent to biopsy, only 25% were confirmed malignant lesions, and about 75% were diagnosed benign lesions. This high rate of false-positive is related with the difficulty in the obtainment of an accurate diagnosis [2],[3]. Several works have been proposed for automated detection and classification of masses in digital mammograms. These works present an investigation of shape and texture features in the characterization of masses. The purpose of this work is to apply a combination of both feature types (shape and texture) and classification between malignant and benign breast lesions. We chose the artificial neural network for the classification stage because there are many resources: its implementation is very easy, it has ability to generalization, and it’s intrinsically fault-tolerance [4].
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
References
Boring, C.C; Squires, T.S & Tong, T; Cancer Statistics, 1992. CA 1992, v.42, p.19–38, 1992.
Andersson, I.; “What can we learn from interval carcinomas?. Recent Results Cancer Res., v.90, pp. 161–163, 1984.
Cancer Facts and Figures. American Cancer Society, 1991.
Beale, LER & Jackson, T.; Neural computing: an introduction. Adam-Hilger, Inst. of Physics Publishing Ltd, Bristol, 1990.
R.M. Nishikawa; M.L. Giger; K. Doi; C.J. Vyborny & R.A. Schmidt; “Computer-aided detection of agrupamamentoed microcalcifications: an improved method for grouping detected signals”. Medical Physics 20(6), pp. 1661–1666, 1993.
H.P. Chan; K. Doi; C.J. Vyborny; R.A. Schmidt & C.E. Metz; “Digital characterization of clinical mammographic microcalcifications: applications in computer-aided detection”. Proc. SPIE Medical Imaging, v.914, pp.591–593, 1988.
A.S. Pereira; A.F. Frère; P.M. A Marques; H. Schiabel; H.J.Q. Oliveira & M.a Marques; “Mammographic images: processing by Hough Transform”. SPIE 96: Int.Symp. on Optical Science, Eng. And Instr., Denver, USA, Aug. 04–09, pp. 540–547, 1996.
J. Dengler; S. Behrens & J.F. Desaga; “Segmentation of microcalcifications in mammograms”. IEEE MI 12(4), pp.634–642, 1993.
El-Faramawy, N.M.; Rangayyan, R.M.; Desautels, J.E.L. & Alim, O.A.; “Shape factors for analysis of breast tumors in mammograms.” IEEE Proc. Canadian Conf. on Electrical and Computer Eng., pp.355–358, 1996.
Kilday, J.; Palmieri, F. & Fox, M.D.; “Classifying mammographie lesions using computerized image analysis”. IEEE Trans. on Medical Imaging, v. 12(4), pp.664–669, 1993.
R.M. Haralick; K. Shanmugan & I. Dinstein; “Textural features of images classification”. IEEE Trans. system. Man Cybernetics SMC-3. pp.610–621, 1973.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Kinoshita, S.K., Marques, P.M.A., Slaets, A.F.F., Marana, H.R.C., Ferrari, R.J., Villela, R.L. (1998). Detection and Characterization of Mammographic Masses by Artificial Neural Network. In: Karssemeijer, N., Thijssen, M., Hendriks, J., van Erning, L. (eds) Digital Mammography. Computational Imaging and Vision, vol 13. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-5318-8_85
Download citation
DOI: https://doi.org/10.1007/978-94-011-5318-8_85
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-6234-3
Online ISBN: 978-94-011-5318-8
eBook Packages: Springer Book Archive