Abstract
Intravascular ultrasound (IVUS) imaging is a catheter-based medical methodology establishing itself as a useful modality for studying atherosclerosis. The detection of lumen and media-adventitia boundaries in IVUS images constitutes an essential step towards the reliable quantitative diagnosis of atherosclerosis. In this paper, a novel scheme is proposed to automatically detect lumen and media-adventitia borders. This segmentation method is based on the level-set model and the contourlet multiresolution analysis. The contourlet transform decomposes the original image into low-pass components and band-pass directional bands. The circular hough transform (CHT) is adopted in low-pass bands to yield the initial lumen and media-adventitia contours. The anisotropic diffusion filtering is then used in band-pass subbands to suppress noise and preserve arterial edges. Finally, the curve evolution in the level-set functions is used to obtain final contours. The proposed method is experimentally evaluated via 20 simulated images and 30 real images from human coronary arteries. It is demonstrated that the mean distance error and the relative mean distance error have increased by 5.30 pixels and 7.45%, respectively, as compared with those of a recently traditional level-set model. These results reveal that the proposed method can automatically and accurately extract two vascular boundaries.
Highlights
Intravascular ultrasound (IVUS), one of the most recent developments in medical imaging, is a new method for coronary heart disease diagnosis and endovascular surgery
It is demonstrated that the mean distance error and the relative mean distance error have increased by 5.30 pixels and 7.45%, respectively, as compared with those of a recently traditional level-set model
This paper presents a new IVUS plaque image segmentation method based on level-set model and contourlet transform
Summary
Intravascular ultrasound (IVUS), one of the most recent developments in medical imaging, is a new method for coronary heart disease diagnosis and endovascular surgery. It renders real-time, cross-sectional and high-resolution images of blood vessels and provides information concerning the vascular lumen and wall. A typical intravascular ultrasound pull-back sequence generally produces several hundreds of images, which has the effect of making nonautomatic analysis of the data long, fastidious and subject to high intra- and interobserver variability. These could be serious limitations against the medical usage of IVUS technique. Because of poor IVUS image quality due to the existence of speckle, imaging artefacts, calcification shadowing, and rupture of parts of the arterial wall [1], it is necessary to develop efficient segmentation methods taking into account the nature of IVUS images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
