In diagnosing diseases and planning surgeries the structure and length of blood vessels is of great importance. In this research we develop a novel method for the segmentation of 2-D and 3-D images with an application to blood vessel length measurements in 3-D abdominal MRI images. Our approach is robust to noise and does not require contrast enhanced images for segmentation. We use an effective algorithm for skeletonization, graph construction and shortest path estimation to measure the length of blood vessels of interest.