An intraluminal coronary stent is a metal mesh tube deployed in a stenotic artery during Percutaneous Coronary Intervention (PCI), in order to prevent acute vessel occlusion.
The identification of struts location and the definition of the stent shape are relevant for PCI planning and for patient follow-up. We developed a fully-automatic framework for
Computer-Aided Detection (CAD) of intra-coronary stents in Intravascular Ultrasound (IVUS) image sequences. The CAD system is able to detect stent struts and estimate the stent shape.
The proposed CAD uses machine learning to provide a comprehensive interpretation of the local structure of the vessel by means of semantic classification. The output of the classification stage is then used to detect struts and to estimate the stent shape. The proposed approach is validated using a multi-centric data-set of 1,015 images from 107 IVUS sequences containing both metallic and bio-absorbable stents.
The method was able to detect structs in both metallic stents with an overall F-measure of 77.7% and a mean distance of 0.15 mm from manually annotated struts, and in bio-absorbable stents with an overall F-measure of 77.4% and a mean distance of 0.09 mm from manually annotated struts.
Related publications:
– F. Ciompi, S. Balocco, J. Rigla, X. Carrillo, J. Mauri, P. Radeva «Computer-Aided Detection of Intra-Coronary Stent in Intravascular Ultrasound Sequences» Medical Physics. Volume 43, Issue 10, October 2016
The publication was choosen as front page of the review Medical Physics.
The project is related with the following workshop CVII-STENT part of the prestigious MICCAI Conference
http://campar.in.tum.de/CVIISTENT2016/WebHome