A vectorial image classification method based on neighborhood weighted Gaussian mixture model

Enhancing the convex analysis of mixtures technique for estimating DCE-MRI pharmacokinetic parameters

Dynamic-contrast enhanced magnetic resonance imaging (DCE-MRI) is a useful noninvasive tool for monitoring tumor angiogenesis and assessing therapeutic response. One major problem that prevents an accurate estimation of pharmacokinetic parameters is partial-volume effect (PVE). A multi-tissue compartmental modeling (CM) technique supported by convex analysis of mixtures (CAM) is used to overcome the PVE by clustering pixels and constructing a simplex whose vertices are of a single compartment type. CAM uses the identified pure-volume pixels to estimate the kinetics of the tissues under investigation. This paper reports an enhanced version of CAM-CM to identify pure-volume pixels more accurately. This includes the consideration of the neighborhood effect on each pixel and the use of a barycentric coordinate system to identify more pure-volume pixels and to test those identified by CAM. The enhanced CAM achieved root mean square error (RMSE) of 0.00348 ± 0.000019, lower than the RMSE of 0.05409 ± 0.00496 achieved by CAM.