Abstract
Classification of breast tumors in perfusion DCE-MRI solely based on dynamic contrast enhanced magnetic resonance data is a challenge. Many studies employ grouping of voxels into regions via clustering for further analysis. However, the clustering result strongly depends on the chosen clustering algorithm and its parameter settings. In this paper, we explain how spectral clustering can be adapted to breast tumor data and suggest how the clustering parameters can be automatically derived such that no pre-defined user input, e.g., cluster number, is necessary. The presented spectral clustering approach has the great advantage of generating spatially connected regions. Furthermore, it can be enabled for automatic classification and yields similar results as previous approaches.
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
Schnall MD, Blume J, Bluemke DA, et al. Diagnostic architectural and dynamic features at breast MR imaging: multicenter study. Radiology. 2006;238(1):42–53.
Glaßer S, Niemann U, Preim B, et al. Can we distinguish between benign and malignant breast tumors in DCE-MRI by studying a tumors most suspect region only? Proc CBMS. 2013; p. 59–64.
Glaßer S, Preim U, T¨onnies K, et al. A visual analytics approach to diagnosis of breast DCE-MRI data. Comput Graph. 2010;34(5):602–11.
Preim U, Glaßer S, Preim B, et al. Computer-aided diagnosis in breast DCE-MRI: quantification of the heterogeneity of breast lesions. Eur J Radiol. 2012;81(7):1532–8.
Chen W, Giger ML, Bick U, et al. Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI. Med Phys. 2006;33(8):2878–87.
Rueckert D, Sonoda L, Hayes C, et al. Nonrigid registration using free-form deformations: application to breast MR images. IEEE Trans Med Imaging. 1999;18(8):712–21.
Degani H, Gusis V, Weinstein D, et al. Mapping pathophysiological features of breast tumors by MRI at high spatial resolution. Nat Med. 1997;3:780–2.
Von Luxburg U. A tutorial on spectral clustering. Stat Comput. 2007;17(4):395–416.
Zelnik-Manor L, Perona P. Self-tuning spectral clustering. Adv Neural Inf Process Syst. 2004; p. 1601–8.
Rendon E, Abundez I, Arizmendi A, et al. Internal versus external cluster validation Indexes. Int J Comput Commun. 2011;5(1):27–34.
Holmes G, Donkin A, Witten IH. WEKA: a machine learning workbench. Proc IIS. 1994; p. 357–61.
Quinlan JR. C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers; 1993.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Glaßer, S., Roscher, S., Preim, B. (2014). Adapted Spectral Clustering for Evaluation and Classification of DCE-MRI Breast Tumors. In: Deserno, T., Handels, H., Meinzer, HP., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2014. Informatik aktuell. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54111-7_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-54111-7_39
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54110-0
Online ISBN: 978-3-642-54111-7
eBook Packages: Computer Science and Engineering (German Language)