Table of Contents Author Guidelines Submit a Manuscript
Computational and Mathematical Methods in Medicine
Volume 2013, Article ID 107871, 7 pages
Research Article

Automated Detection of Healthy and Diseased Aortae from Images Obtained by Contrast-Enhanced CT Scan

Department of Environment and Information Science, Yokohama National University, Yokohama 240-8501, Japan

Received 21 December 2012; Revised 30 January 2013; Accepted 30 January 2013

Academic Editor: Kumar Durai

Copyright © 2013 Michael Gayhart and Hiroshi Arisawa. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Purpose. We developed the next stage of our computer assisted diagnosis (CAD) system to aid radiologists in evaluating CT images for aortic disease by removing innocuous images and highlighting signs of aortic disease. Materials and Methods. Segmented data of patient’s contrast-enhanced CT scan was analyzed for aortic dissection and penetrating aortic ulcer (PAU). Aortic dissection was detected by checking for an abnormal shape of the aorta using edge oriented methods. PAU was recognized through abnormally high intensities with interest point operators. Results. The aortic dissection detection process had a sensitivity of 0.8218 and a specificity of 0.9907. The PAU detection process scored a sensitivity of 0.7587 and a specificity of 0.9700. Conclusion. The aortic dissection detection process and the PAU detection process were successful in removing innocuous images, but additional methods are necessary for improving recognition of images with aortic disease.