Intra-vascular Optical Coherence Tomography (IV-OCT) is an appropriate imaging modality for the evaluation of stent
struts apposition and coverage in the coronary arteries. Most often, image analysis is performed by a time-consuming
manual contour tracing process. Recently, we proposed an algorithm for fully automated lumen morphology and
individual stent struts apposition/coverage quantification. In this manuscript further developments allowing for automatic
segmentation of the stent contour are presented. As such, quantification of in-stent area, malapposition cross-sectional
area (i.e. the area representing the space from the stent surface to the vessel wall) and coverage cross-sectional area (i.e.
the area of the tissue covering the stent surface) are automatically obtained. Volumetric measurements of malapposition
and coverage are then achieved through the analysis of equally-spaced consecutive IV-OCT cross-sectional images. In
addition, uncovered and malapposed struts are automatically clustered through consecutive slices according to their
three-dimensional spatial position. Finally, properties of each cluster (e.g. malapposition/coverage volumes and struts
spatial location and distribution) are quantified allowing for a volumetric analysis of the implanted device.
Validation of the algorithm was obtained taking as a reference manual measurements performed by an expert
cardiologist. 102 in-vivo images, taken at random from 8 different patients, were both automatically and manually
analyzed quantifying lumen and stent area. High Pearson's correlation coefficients (Rarea = 0.99) and Bland-Altman
statistics, showing no significant bias and good limits of agreement, proved that the presented algorithm provides a
robust and fast tool to automatically estimate apposition and coverage of stent through an entire in-vivo IV-OCT
pullback. Such a tool will be important for the integration of this technology in clinical routine and large clinical trials.