Abstract
Using mammograms in which signs of breast cancer have been synthesised overcomes the problem of obtaining a sufficiently large volume of real data with known ground truth for training and test purposes. This paper describes a fully automated method for generating synthetic spiculated masses. Statistical methods are used to model the appearance and location of a training set of real masses and their effect on surrounding breast tissue. The models are then used to synthesise the appearance of a malignant mass in an otherwise normal mammogram. By virtue of using generative statistical models, the synthesis process can be fully automated. In an observer study in which 10 expert mammogram readers attempted to distinguish between synthetic masses generated by the method and real masses, we report an area Az = 0.70±0.09 under the receiver operating characteristic.
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
Caulkin, S.: Generating Synthetic Abnormalities in Digital Mammograms Using Statistical Models. Imaging Science and Biological Engineering, PhD. University of Manchester, UK, Manchester, p. 268 (2001)
Ruschin, M., Tingberg, A., Bath, M., et al.: Using simple mathematical functions to simulate pathological structures–input for digital mammography clinical trial. Radiat Prot. Dosimetry 114, 424–431 (2005)
Saunders, R., Samei, E., Baker, J., et al.: Simulation of mammographic lesions. Academic radiology 13, 860–870 (2006)
Berks, M., Caulkin, S., Rahim, R., et al.: Statistical Appearance Models of Mammographic Masses. In: Krupinski, E.A. (ed.) IWDM 2008. LNCS, vol. 5116, pp. 401–408. Springer, Heidelberg (2008)
Cootes, T.F., Taylor, C.J.: Statistical models of appearance for medical image analysis and computer vision. In: Proc. SPIE Medical Imaging, vol. 42, pp. 236–248 (2001)
Kingsbury, N.: Complex wavelets for shift invariant analysis and filtering of signals. Applied and computational harmonic analysis 10, 234 (2001)
Berks, M., Taylor, C.J., Rahim, R., et al.: Modelling Structural Deformations in Mammographic Tissue Using the Dual-Tree Complex Wavelet. In: 10th International Workshop on Digital Mammography. Springer, Girona (2010)
Cootes, T.F., Taylor, C.J., Cooper, D.H., et al.: Training Models of Shape from Sets of Examples. In: 3rd British Machine Vision Conference, pp. 9–18 (1992)
Berks, M., Barbosa Da Silva, D., Boggis, C.R.M., et al.: Evaluating the realism of synthetically generated mammographic lesions: an observer study. In: SPIE Medical Imaging, San Diego, California, USA (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Berks, M., Taylor, C., Rahim, R., da Silva, D.B., Boggis, C., Astley, S. (2010). Synthesising Malignant Breast Masses in Normal Mammograms. In: Martí, J., Oliver, A., Freixenet, J., Martí, R. (eds) Digital Mammography. IWDM 2010. Lecture Notes in Computer Science, vol 6136. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13666-5_68
Download citation
DOI: https://doi.org/10.1007/978-3-642-13666-5_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13665-8
Online ISBN: 978-3-642-13666-5
eBook Packages: Computer ScienceComputer Science (R0)