Back to Search
Start Over
Automated detection of healthy and diseased aortae from images obtained by contrast-enhanced CT scan.
- Source :
-
Computational and mathematical methods in medicine [Comput Math Methods Med] 2013; Vol. 2013, pp. 107871. Date of Electronic Publication: 2013 Mar 31. - Publication Year :
- 2013
-
Abstract
- 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.<br />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.<br />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.<br />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.
- Subjects :
- Algorithms
Aortic Dissection diagnostic imaging
Aortic Aneurysm diagnostic imaging
Computational Biology
Contrast Media
Humans
Ulcer diagnostic imaging
Aortic Diseases diagnostic imaging
Aortography statistics & numerical data
Radiographic Image Interpretation, Computer-Assisted methods
Tomography, X-Ray Computed statistics & numerical data
Subjects
Details
- Language :
- English
- ISSN :
- 1748-6718
- Volume :
- 2013
- Database :
- MEDLINE
- Journal :
- Computational and mathematical methods in medicine
- Publication Type :
- Academic Journal
- Accession number :
- 23606895
- Full Text :
- https://doi.org/10.1155/2013/107871