Unsupervised Inline Analysis of Cardiac Perfusion MRI

• DOI: 10.1007/978-3-642-04271-3_90
• Publication Date: 2009-09-29T10:28:48Z
• Authors: Hui Xue; Sven Zuehlsdorff; Peter Kellman; Andrew Arai; Sonia Nielles-Val...; Christophe Chefdh...; Christine H. Lorenz; Jens Guehring
• Keywords: Image Interpretation, Computer-Assisted; Myocardial Perfusion Imaging; Humans; Reproducibility of Results; Image Enhancement; Online Systems; Sensitivity and Specificity; Algorithms; Magnetic Resonance Angiography; Pattern Recognition, Automated

In this paper we first discuss the technical challenges preventing an automated analysis of cardiac perfusion MR images and subsequently present a fully unsupervised workflow to address the problems. The proposed solution consists of key-frame detection, consecutive motion compensation, surface coil inhomogeneity correction using proton density images and robust generation of pixel-wise perfusion parameter maps. The entire processing chain has been implemented on clinical MR systems to achieve unsupervised inline analysis of perfusion MRI. Validation results are reported for 260 perfusion time series, demonstrating feasibility of the approach.