Title :
Automatic anatomical labeling of abdominal arteries for small bowel evaluation on 3D CT scans
Author :
Weidong Zhang ; Jiamin Liu ; Jianhua Yao ; Summers, R.M.
Author_Institution :
Imaging Biomarkers & Comput.-Aided Diagnosis Lab., Nat. Inst. of Health Clinical Center, Bethesda, MD, USA
Abstract :
While segmentation of the small bowel on CT scans is helpful for diagnosis and surgery planning, it is challenging to reproducibly identify specific locations within the small bowel. Assigning anatomical names to the individual mesenteric arteries supplying the small bowel may enable more precise lesion localization. It also enables registration of the small bowel from CT scans before and after surgery. In this study, an automated anatomical labeling method was introduced for the mesenteric arterial vasculature. After segmenting the mesenteric vascular tree, features including blood vessel size, direction, relative position and branching pattern were calculated. Known anatomic names were assigned to the major abdominal arteries, and names encoding order and direction were assigned to the arteries arising from the superior mesenteric artery. Five CT scans were analyzed and experimental results showed 73% recall and 79% precision rate. To our knowledge, this is the first reported method to label the smaller branches of the mesenteric vasculature and will have applications for diagnosis and treatment of small bowel disease.
Keywords :
blood vessels; computerised tomography; diseases; image segmentation; medical image processing; surgery; 3D CT scans; abdominal arteries; automated anatomical labeling method; automatic anatomical labeling; blood vessel size; bowel disease; branching pattern; mesenteric arterial vasculature; relative position; small bowel segmentation; surgery planning; Arteries; Bifurcation; Biomedical imaging; Colon; Computed tomography; Image segmentation; Labeling; anatomical labeling; image segmentation; small bowel evaluation;
Conference_Titel :
Biomedical Imaging (ISBI), 2013 IEEE 10th International Symposium on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4673-6456-0
DOI :
10.1109/ISBI.2013.6556449