A kidney segmentation framework for dynamic contrast enhanced magnetic resonance imaging

In the United States, more than 12000 renal transplantations are performed annually; but the transplanted kidneys face a number of surgical and medical complications that cause a decrease in their functionality. In an effort to understand the reasons for this functionality decrease, considerable attention has recently been focused on Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) due to its superior functional and anatomical information. The biggest challenge in the analysis of DCE-MRI is the segmentation of kidneys from abdomen images because of the high noise and partial volume effects introduced during the rapid and repeated scanning process. In this paper, a general framework is introduced for the segmentation of kidneys from DCE-MR images of the abdomen. The proposed segmentation algorithm consists of three main steps. In the first step, an average kidney shape is constructed from a dataset of previously segmented kidneys, and an average signed distance map density is obtained describing the shape of the kidneys. In the second step, the gray level density is calculated for a given new kidney image using a modified expectation maximization (EM) algorithm. In the third step, a deformable model is evolved based on the two density functions obtained from the previous two steps: the first one describes the prior shape of the kidney, and the second one describes the distribution of the gray level inside and outside the kidney region. The new deformable model is able to handle intricate shapes without getting stuck in edge points; and gives very promising results that are comparable to radiologists' segmentation.