Proper arterial input function (AIF) selection is a critical step for accurate quantification of dynamic susceptibility contrast enhanced (DSC) MRI in brain tumor patients. In this study, we have employed differential evaluation (DE) clustering method on processed perfusion images for accurate AIF selection. The procedure consists of two main steps: preprocessing for eliminating non-arterial curves including tissue, noisy and those contaminated with partial volume effects; and AIF selection using DE clustering method. The performance of this clustering method was compared to K-means and Hierarchical Clustering techniques and the results show the superiority of the proposed approach for accurate AIF selection.
This abstract and the presentation materials are available to members only; a login is required.