Automated Abdominal Aortic Aneurysm segmentation using MATLAB

Abdominal Aortic Aneurysms (AAA) are the 10th leading cause of death in older men. It is estimated that about 5% of men over 50 have AAA but the prevalence and risk of death due to rupture increase with age to estimated 10% prevalence and almost 1% of male deaths over the age of 65. AAA is defined as a focal dilation of the artery at least 50% larger than the normal diameter. If the defect is not surgically repaired prior to rupture, the mortality is about 80%. The role of clotted blood (thrombus) lining the walls of the AAA has been speculated to play a role in aneurysm expansion. Although aneurysm diameter is easily measured from a CT scan, accurately measuring the relative amount of clotted blood (thrombus load) cannot be readily done with a ruler. This paper presents a process to segment the relative thrombus area and aneurysmal area from CT images using computer algorithms. We have developed an image processing based technique, using MATLAB, to aid in the detection of a threatening AAA condition. This technique uses segmentation-based techniques to extract the desired data. The process of segmentation involves several steps to obtain desirable results. This algorithm uses primarily thresholding techniques, erosion, and dilation filters to segment the wall and determine the bounds of the aorta; then segmentation is done to enhance and isolate areas of interest.