An automatic labeling bifurcation method for intracoronary optical coherence tomography images

ABSTRACT Vessel branchings are critical vascular locations from the clinical point of view. In these sites, the arterialhemodynamic plays a relevant role in the progression of atherosclerosis, an important vascular pathology. In thispaper, a fully automatic approach for the bifurcation classi cation in human Intravascular Optical CoherenceTomography (IV-OCT) sequences is introduced. Given the lumen contours, the method is capable of labelingthe bifurcation slices. A geometric feature extraction was performed and the Forward Regression OrthogonalLeast Squares method (FROLS) was applied to analyze the best features and to determine the appropriatedweights in a binary classi er. A cross-validation scheme is applied in order to evaluate the performance of theclassi cation approach and the results have shown a sensitivity of 86% and speci city of 92% to FROLS.Keywords: lumen contour, optical coherence, bifurcation, feature extraction, classi cation 1. INTRODUCTION Intravascular Optical Coherence Tomography (IV-OCT) is a catheter-based imaging modality that has beenproposed as a feasible method to visualize coronary plaque microstructure in patients.