No abstract

Thickening of intima-media complex in the common carotid artery is a biomarker of atherosclerosis. To automatically measure this thickness, we propose a region-based segmentation method, involving a supervised deep-learning approach based on the dilated U-net architecture, named caroSegDeep. It was trained and evaluated using 5-fold cross-validation on two open-access databases containing a total of 2676 annotated images. Compared with the methods already evaluated on these databases, caroSegDeep established a new benchmark and achieved a mean absolute error twice smaller than the interobserver variability.

The intima-media complex of the common carotid artery is considered the sentinel of a silent killer disease called atherosclerosis. Morphological biomarkers such as the intimamedia thickness are already exploitable, but dynamic biomarkers, which reflect tissue deformation over the cardiac cycle, remain to be validated. Recent motion estimation methods seek to quantify compression, shear, and elongation coefficients, but their clinical applicability has not yet been well defined, and their actual accuracy is difficult to assess due to the absence of ground truth. This lack of reference also is the main limitation to explore fully supervised deep learning methods that have shown great potential in other applications. With this in mind, we propose a simulation pipeline to produce realistic in silico sequences, by combining a physics-based simulator with a post-processing based on a generative adversarial network.