Segmentation driven image application to 2D-MRI of kidney

Magnetic Resonance Imaging (MRI) of the kidney requires proper motion correction and segmentation to enable an estimation of glomerular filtration rate through pharmacokinetic modelling. Traditionally, segmentation, and pharmacokinetic modelling have been applied sequentially as separate processing method. A 2D model of segmentation of the full kidney is presented. To demonstrate the model in numerical experiments, we used normalised gradients and a Mahalanobis distance from the time courses of the segmented regions to a training set for supervised segmentation. By applying this framework to the input consisting of 2D image time series, we conduct simultaneous correction of kidney images and two region segmentation into kidney and background. The potential of the new approach is demonstrated on real MRI data from ten healthy volunteers.