A Combined Bayesian Approach to Classifying Venous Flow during Contrast-Agent Injection using Doppler Ultrasound
Conference paper
Abstract
The administration of intravenous contrast media during CT examinations is routine, but carries with it a risk of extravasation. With a new Doppler ultrasound monitoring technique, we propose a method for automatic classification of injection flow states. The method combines a Bayesian network and a sparse kernel classifier. The network captures the dependencies between latent variables, observations and previous system states. The sparse kernel classifier is a Relevance Vector Machine that is well suited for spectral analysis and which provides a probabilistic estimate. We present preliminary results showing a challenging input signal variance and how the method applies to empirical data.
Keywords
classification Bayesian sparse kernel relevance vector machine Doppler ultrasound extravasation accuracy spectral analysisPreview
Unable to display preview. Download preview PDF.
References
- 1.Birnbaum B. et al. “Extravasation detection accessory: Clinical evaluation in 500 patients.”, Radiology 212:22, 431–438Google Scholar
- 2.Cohan RH, Ellis JH, Garner WL. “Extravasation of radiologic contrast material: recognition, prevention and treatment.” Radiology 1996;199:697–701Google Scholar
- 3.www.neorad.noGoogle Scholar
- 4.“MEDRAD Introduces New Extravasation Detector Technology”, http://www.medrad.com/newsroom/display-pressrelease.html?PRid=205Google Scholar
- 5.Hoff L. et al. “An ultrasound transducer to monitor CT contrast media injections”, forthcoming 2008 Google Scholar
- 6.Ruping S., “SVM Kernels for Time Series Analysis” in Klinkenberg et al., “LLWA 01-Tagungsband der GI-Workshop-Woche Lernen-Lehren-Wissen-Adaptivität”, pp. 43–50, Dortmund, Germany, 2001Google Scholar
- 7.Tipping, M. E., “Sparse Bayesian learning and the relevance vector machine”. Journal of Machine Learning Research 1, 211–244. 2001MathSciNetMATHGoogle Scholar
- 8.Guler I. and Ubeyli E., “A recurrent neural network classifier for Doppler ultrasound blood flow signals”, Pattern Recognition Letters, Volume 27, Issue 13, 1 October 2006, Pages 1560–1571CrossRefGoogle Scholar
- 9.Übeyli E, “Doppler ultrasound signals analysis using multiclass support vector machines with error correcting output codes.”, Expert Syst. Appl. 33(3): 725–733 (2007)CrossRefGoogle Scholar
- 10.Bishop C., “Pattern Recognition and Machine Learning”, Springer 2006, ISBN 0-387-31073-8Google Scholar
- 11.Malek J., “Bayesian Classifier for Medical Data from Doppler Unit”, Acta Polytecnica, Vol. 46, no. 4/2006Google Scholar
- 12.Herment A. et al., “Improved Characterization of Non-Stationary Flows Using a Regularized Spectral Analysis of Ultrasound Doppler Signals”, J. Phys. III France 7 (1997) 2079–2102CrossRefGoogle Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 2008