Inferring vascular structures in coronary artery x-ray angiograms based on multi-feature fuzzy recognition algorithm

Authors:
Shoujun Zhou;Wufan Chen;Jiangui Zhang;Yongtian Wang
Affiliations:
School of Information Science and Technology, Beijing Institute of Technology, B.J., China;School of Biomedical Engineering, Southern Medical University, G.Z., China;School of Biomedical Engineering, Southern Medical University, G.Z., China;School of Information Science and Technology, Beijing Institute of Technology, B.J., China
Venue:
Miar'06 Proceedings of the Third international conference on Medical Imaging and Augmented Reality
Year:
2006

Citing 5
Cited 0

Muliscale Vessel Enhancement Filtering

MICCAI '98 Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention
Robust Modelling of Local Image Structures and Its Application to Medical Imagery

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Multiscale centerline extraction of angiogram vessels using gabor filters

CIS'04 Proceedings of the First international conference on Computational and Information Science
Optimal scheduling of tracing computations for real-time vascular landmark extraction from retinal fundus images

IEEE Transactions on Information Technology in Biomedicine
Model-based method for improving the accuracy and repeatability of estimating vascular bifurcations and crossovers from retinal fundus images

IEEE Transactions on Information Technology in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

The multi-feature fuzzy recognition (MFFR) algorithm was presented to infer the vessel structures, in the context of X-Ray Angiograms (XRA) of the coronary artery. In the modeling, a multi-feature metrics (MFM) was firstly established to describe the local configuration; then the membership degree of MFM-based fuzzy subsets was defined, and the fuzzy recognition operator was constructed. The MFFR algorithm can correctly infer four kinds of vessel structures including vascular ends, segments, bifurcations and crossovers. The results are satisfying: on average 91.1% of the testing vessel lengths in medium quality images are automatically delineated as well as their structures being correctly inferred with point-wise.