Automatic extraction of aortic aneurysm from thoracic CTA based on Fuzzy-based 3-D region growing method

Computer-Aided Diagnosis (CAD) system that helps medical staffs to diagnose patient´s disease conditions has been used in a variety fields of medicine. For cardiovascular surgery, radiologists manually construct 3-D volume model of patient organ and provide this information to cardiovascular surgeons, therefore automation technique for image processing of building patient 3-D volume model is highly requested from clinical site. The 3-D volume model is used in not only diagnosing patient disease condition, but also making a surgical plan before an operation. In the case of using CAD system for a cardiovascular disease patient, computed tomography angiography (CTA) has been used as the source data that clearly indicates the region of blood flow on the image due to contrast agent. However, sufficient information for the diagnosis is not obtained from CTA, because the regions of aneurysm and aortic wall tissue can not distinguished correctly even using the latest CAD system. Then, this study proposes Fuzzy-based region growing method that enables a computer to have the ability of reading radiogram. We focused on the skill of reading radiogram of experienced doctors, because they know the boundary line between aneurysm and aortic wall tissue on CTA image. Hence, Fuzzy inference has been employed to express doctor´s skill of reading radiogram and used as the growing criteria. The proposed method is applied to one patient CTA data and its result is shown and discussed in this paper.