Dynamic contrast‐enhanced MRI diagnostics in oncology via principal component analysis

Abstract This paper proposes the use of latent variable models based on principal component analysis (PCA) as a robust alternative to pharmacokinetic modeling for the analysis of the dynamic contrast‐enhanced magnetic resonance images (DCE‐MRI) often obtained during oncological studies. Theoretical and practical justifications are provided for the advantages of the PCA approach. A pilot study using clinical DCE‐MRI data on prostate patients is presented to demonstrate the method. Copyright © 2008 John Wiley & Sons, Ltd.