Paper
23 October 2018 Vessel extraction from angiography image using dictionary inpainting
Lizhe Xie, Yining Hu, Yang Xia, Bin Yan, Limin Luo, Lin Wang
Author Affiliations +
Abstract
Due to the complex background and varying scanning conditions, extracting the vessel structure from the rotational angiography (RA) image is challenging. Various methods have been proposed for binary vessel segmentation with no gray level information which is essentially for diagnosis. A new method based on background inpainting and image subtraction is introduced in this paper. Instead of providing binary segmentation result, the proposed method estimates the background caused by surrounding tissues, and the vessel structure with gray level is obtained via image subtraction. The experiments verify that the proposed method works well for clinical sequences with different scanning conditions.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lizhe Xie, Yining Hu, Yang Xia, Bin Yan, Limin Luo, and Lin Wang "Vessel extraction from angiography image using dictionary inpainting", Proc. SPIE 10820, Optics in Health Care and Biomedical Optics VIII, 1082013 (23 October 2018); https://doi.org/10.1117/12.2324427
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Associative arrays

Angiography

Image filtering

Feature extraction

Arteries

Back to Top