A level set-based framework for 3D kidney segmentation from diffusion MR images

Developing any non-invasive computer-aided diagnostic (CAD) system for the diagnosis of kidney diseases essentially requires the extraction of the kidney from medical images. We propose a shape based level-set framework for 3D kidney segmentation from diffusion-weighted magnetic resonance imaging (DW-MRI). A stochastic speed relationship is used to control the deformable model evolutions. This speed relationship is based on an adaptive shape prior guided by the first- and second-order visual appearance features of the DW-MRI data. These pre-mentioned image features are integrated into a joint Markov-Gibbs random field (MGRF) model of the kidney and its background. DW-MRI data sets from eight subjects acquired at different b-values ranging from 0 to 1000 s/mm² are tested using a leave-one-subject-out method to evaluate the proposed segmentation approach, and to compare its performance with other segmentation methods using three evaluation metrics: the Dice similarity coefficient (DSC), the 95-percentile modified Hausdorff distance, and the absolute kidney volume difference. Robustness and accuracy of the proposed approach are confirmed through the experimental results´ evaluation between manually drawn and automatically segmented contours.