Automatic detection of bioabsorbable coronary stents in IVUS images using a cascade of classifiers

Authors:
David Rotger;Petia Radeva;Nico Bruining
Affiliations:
Medical Imaging Laboratory, Computer Vision Center and the Computer Science Department, Autonomous University of Barcelona, Barcelona, Spain;MILab, CVC and the Applied Mathematics and Analysis Department, University of Barcelona, Barcelona, Spain;Erasmus Medical Center, Thoraxcenter, Rotterdam, The Netherlands
Venue:
IEEE Transactions on Information Technology in Biomedicine - Special section on affective and pervasive computing for healthcare
Year:
2010

Citing 1
Cited 1

Blood Detection In IVUS Longitudinal Cuts Using AdaBoost With a Novel Feature Stability Criterion

Proceedings of the 2007 conference on Artificial Intelligence Research and Development

Compensation of in-plane rigid motion for in vivo intracoronary ultrasound image sequence

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Bioabsorbable drug-eluting coronary stents present a very promising improvement to the common metallic ones solving some of the most important problems of stent implantation: the late restenosis. These stents made of poly-L-lactic acid cause a very subtle acoustic shadow (compared to the metallic ones) making difficult the automatic detection and measurements in images. In this paper, we propose a novel approach based on a cascade of GentleBoost classifiers to detect the stent struts using structural features to code the information of the different subregions of the struts. A stochastic gradient descent method is applied to optimize the overall performance of the detector. Validation results of struts detection are very encouraging with an average F-measure of 81%.