Aortic annulus sizing using watershed transform and morphological approach for CT images

• Main Authors: Norhasmira, Mohammad, Zaid, Omar, Mus’ab, Sahrim
• Format: Article
• Language: English
• Published: AIP Publishing. 2018
• Subjects: QA76 Computer software; RA0421 Public health. Hygiene. Preventive Medicine
• Online Access: http://ir.unimas.my/id/eprint/46027/1/020048_1_online.pdf; http://ir.unimas.my/id/eprint/46027/; https://pubs.aip.org/aip/acp/article/1930/1/020048/783735/Aortic-annulus-sizing-using-watershed-transform; https://doi.org/10.1063/1.5022942
• Institution: Universiti Malaysia Sarawak

Aortic valve disease occurs due to calcification deposits on the area of leaflets within the human heart. It is progressive over time where it can affect the mechanism of the heart valve. To avoid the risk of surgery for vulnerable patients especially senior citizens, a new method has been introduced: Transcatheter Aortic Valve Implantation (TAVI), which places a synthetic catheter within the patient’s valve. This entails a procedure of aortic annulus sizing, which requires manual measurement of the scanned images acquired from Computed Tomographic (CT) by experts. The step requires intensive efforts, though human error may still eventually lead to false measurement. In this research, image processing techniques are implemented onto cardiac CT images to achieve an automated and accurate measurement of the heart annulus. The image is first put through pre-processing for noise filtration and image enhancement. Then, a marker image is computed using the combination of opening and closing operations where the foreground image is marked as a feature while the background image is set to zero. Marker image is used to control the watershed transformation and also to prevent oversegmentation. This transformation has the advantage of fast computational and oversegmentation problems, which usually appear with the watershed transform can be solved with the introduction of marker image. Finally, the measurement of aortic annulus from the image data is obtained through morphological operations. Results affirm the approach’s ability to achieve accurate annulus measurements compared to conventional techniques.