Abstract
Lumen segmentation from clinical intravascular optical coherence tomography (IV-OCT) images has clinical relevance as it provides a full three-dimensional perspective of diseased coronary artery sections. Inaccurate segmentation may occur when there are artifacts in the image, resulting from issues such as inadequate blood clearance. This study proposes a transmittance-based lumen intensity enhancement method that ensures only lumen regions are highlighted. A level-set-based active contour method that utilizes the local speckle distribution properties of the image is then employed to drive an image-specific active contour toward the true lumen boundaries. By utilizing local speckle properties, the intensity variation issues within the image are resolved. This combined approach has been successfully applied to challenging clinical IV-OCT datasets that contains multiple lumens, residual blood flow, and its shadowing artifact. A method to identify the guide-wire and interpolate the lost lumen segments has been implemented. This approach is fast and can be performed even when guide-wire boundaries are not easily identified. Lumen enhancement also makes it easy to identify vessel side branches. This automated approach is not only able to extract the arterial lumen, but also the smaller microvascular lumens that are associated with the vasa vasorum and with atherosclerotic plaque.
Highlights
Intravascular optical coherence tomography (IV-OCT) is widely used for the clinical assessment of atherosclerotic plaque, as this technology provides high-resolution cross-sectional images of the coronary arterial wall.[1]
The lumen enhancement method enabled the identification of guide-wire artifacts and side-branch openings, which were compensated after the lumen contour was obtained
The difference in the radial distances between the computed and manually segmented lumens showed an average error of −1.82 Æ 18.6 and −1.43 Æ 18.8
Summary
Intravascular optical coherence tomography (IV-OCT) is widely used for the clinical assessment of atherosclerotic plaque, as this technology provides high-resolution (axially ≈15 μm resolution) cross-sectional images of the coronary arterial wall.[1]. Various techniques have been reported for lumen segmentation,[1,2,3,4,5,6,7,8] stent strut detection,[7] and plaque characterization.[1,9] These approaches are either semi or fully automated. Some of the methods previously employed include image thresholding,[1] A-line intensity-variation analysis,[2,3] intensity difference-dependent cost function and its minimization approach,[4,5] and labeling methods using Markov random field (MRF).[7] Alternatively, a combination approach with expectation maximization (EM) for labeling and graph-cut for lumen segmentation has been reported.[8] All these techniques use the tissue region as the reference from which to determine the boundary. The lumen geometry generated can be refined using an active contour method (ACM).[6,8]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.