2 December 2005 A framework for spacial-variant thresholding of digital subtraction angiography images
Author Affiliations +
Proceedings Volume 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications; 60452F (2005) https://doi.org/10.1117/12.651582
Event: MIPPR 2005 SAR and Multispectral Image Processing, 2005, Wuhan, China
Abstract
Vessel segmentation is the base of 3d reconstruction of Digital Subtraction Angiograph (DSA) images. This paper proposes a framework of adaptive local thresholding based on a verification-based approach for vessel segmentation of DSA images. The original DSA image is firstly divided into overlapping subimages according to a priori knowledge of the diameter of vessels. We implement a hypothesis test to determine whether each subimage contains vessels and then choose an optimal threshold respectively for every subimage previously determined to contain vessels, with a secondary verification process to exclude the condition that the subregion only containing the background but misclassified as one containing vessels by the hypothesis test. Finally an overall binarization of the original image is achieved by combining the thresholded subimages. Experiments demonstrate superior performance over global thresholding and some adaptive local thresholding methods.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Nong Sang, Nong Sang, Weixue Peng, Weixue Peng, Heng Li, Heng Li, Tianxu Zhang, Tianxu Zhang, } "A framework for spacial-variant thresholding of digital subtraction angiography images", Proc. SPIE 6045, MIPPR 2005: Geospatial Information, Data Mining, and Applications, 60452F (2 December 2005); doi: 10.1117/12.651582; https://doi.org/10.1117/12.651582
PROCEEDINGS
8 PAGES


SHARE
Back to Top