Automated segmentation of the individual branches of the carotid arteries in contrast-enhanced MR angiography using DeepMedic.

Background: Non-invasive imaging is of interest for tracking the progression of atherosclerosis in the carotid bifurcation, and segmenting this region into its constituent branch arteries is necessary for analyses. The purpose of this study was to validate and demonstrate a method for segmenting the carotid bifurcation into the common, internal, and external carotid arteries (CCA, ICA, ECA) in contrast-enhanced MR angiography (CE-MRA) data.

Methods: A segmentation pipeline utilizing a convolutional neural network (DeepMedic) was tailored and trained for multi-class segmentation of the carotid arteries in CE-MRA data from the Swedish CardioPulmonsary bioImage Study (SCAPIS).

Exploring the Relationships Between Hemodynamic Stresses in the Carotid Arteries.

Atherosclerosis manifests as a focal disease, often affecting areas with complex hemodynamics such as the carotid bifurcation. The magnitude and regularity of the hemodynamic shear stresses acting on the vessel wall are thought to generate risk patterns unique to each patient and play a role in the pathogenesis of atherosclerosis. The involvement of different expressions of shear stress in the pathogenesis of carotid atherosclerosis highlights the need to characterize and compare the differential impact of the various expressions of shear stress in the atherosclerotic carotid bifurcation.