Automatic analysis of pediatric renal ultrasound using shape, anatomical and image acquisition priors

In this paper we present a segmentation method for ultrasound (US) images of the pediatric kidney, a difficult and barely studied problem. Our method segments the kidney on 2D sagittal US images and relies on minimal user intervention and a combination of improvements made to the Active Shape Model (ASM) framework. Our contributions include particle swarm initialization and profile training with rotation correction. We also introduce our methodology for segmentation of the kidney's collecting system (CS), based on graph-cuts (GC) with intensity and positional priors. Our intensity model corrects for intensity bias by comparison with other biased versions of the most similar kidneys in the training set. We prove significant improvements (p < 0.001) with respect to classic ASM and GC for kidney and CS segmentation, respectively. We use our semi-automatic method to compute the hydronephrosis index (HI) with an average error of 2.67 +/- 5.22 percentage points similar to the error of manual HI between different operators of 2.31 +/- 4.54 percentage points.