Improved Stent Localization Using Shape-Based Similarity Scores

Stent placement is a procedure to cure the narrowing of the coronary artery lumen due to plaque progression. In recent years, many solutions have been proposed on adopting computer assisted stent positioning systems for proper placement of the stent and apposition on the vessel wall. However, fast and accurate localization and tracking of the stents in conventional X-ray images is not sufficiently investigated in the literature. In this paper, a new method is proposed which is based on automatic detection of two radio-opaque landmarks of the stent. It improves the stent localization and tracking by filtering spurious markers and artifacts, causing a significant reduction in the number of outliers and misdetections. The validation results show that the proposed algorithm is suitable to be applied in routine clinical procedures.