Image processing methods for the detection of acute rejection after kidney transplantation.

摘要

Acute rejection is the most important cause of renal dysfunction after kidney transplantation, but the currently used noninvasive techniques are not specific enough to detect acute rejection. This thesis investigates the potentials of Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) as a noninvasive imaging technique to differentiate acute rejection transplants from normal functioning transplants; and focuses on finding image analysis techniques for the registration and segmentation of renal images. In the image analysis framework of this study, mutual information registration is used to correct the motion due to patient movements. For the segmentation of the kidney from the abdomen images, a novel deformable model energy is proposed. With this new energy, the deformable model evolves using both prior shape and current gray level information. To further segment the kidney into cortex and medulla structures, another deformable model energy is proposed based only on gray level information. At the end of the segmentation, average intensity vs. time curves are plotted to evaluate the perfusion patterns of acute rejection patients and normal functioning transplants. The outcome of this research is an image analysis framework embedded into a graphical user interface to be easily tested by the doctors.