Abstract
Feature extraction is an integral of all Computer Aided Diagnosis (CAD) systems. Due to the presence of fibroglandular tissue however, measurements are perturbed by unwanted influences and therefore, the same descriptor will yield different values for different amounts of occluding structures. To aid the statistical learning used for classification, we need to design features that are invariant to unwanted influences. In this paper, we propose a simple model of the tumour and its surrounding tissue and show how this model can be used to derive descriptors that are invariant to obscuring tissue, rather than heuristically defining a set of descriptors, which is common practice in many CAD papers. We tailor the descriptors to optimally discriminate between tumours and cysts, by assuming a parametric form of the lesions. Results show a significant discriminative improvement over simple, more commonly used contrast features and we obtained an AUC of 0.77 using both CC and MLO images.
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
Geusebroek, J.-M., van den Boomgaard, R., Smeulders, A.W.M., Geerts, H.: Color invariance. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(12), 1338–1350 (2001)
Hu, M.-K.: Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8(2), 179–187 (1962)
Timp, S., Karssemeijer, N.: A new 2D segmentation method based on dynamic programming applied to computer aided detection in mammography. Medical Physics 31(5), 958–971 (2004)
van Engeland, S., Snoeren, P., Huisman, H.-J., Boetes, C., Karssemeijer, N.: Volumetric breast density estimation from full-field digital mammograms. IEEE Transactions on Medical Imaging 25(3), 273–282 (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kooi, T., Karssemeijer, N. (2014). Invariant Features for Discriminating Cysts from Solid Lesions in Mammography. In: Fujita, H., Hara, T., Muramatsu, C. (eds) Breast Imaging. IWDM 2014. Lecture Notes in Computer Science, vol 8539. Springer, Cham. https://doi.org/10.1007/978-3-319-07887-8_80
Download citation
DOI: https://doi.org/10.1007/978-3-319-07887-8_80
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07886-1
Online ISBN: 978-3-319-07887-8
eBook Packages: Computer ScienceComputer Science (R0)