Univ Lyon / INSA-Lyon / CREATIS (Laine et al.)
Model weights not public. Contact creators for more information.
Dilated U-Net model for fully automatic segmentation of the intima-media complex (IMC) of the common carotid artery on longitudinal B-mode ultrasound images, used to measure carotid intima-media thickness (cIMT) -- a standard imaging biomarker of subclinical atherosclerosis. A far-wall detection step first localizes the region of interest, and the dilated U-Net then segments the near- and far-wall IMC boundaries within it. Trained and evaluated with 5-fold cross-validation on a multicenter database of 2,176 images annotated by two experts, the method reached a mean absolute thickness difference of under 120 micrometres versus the reference annotations -- smaller than the approximately 180-micrometre inter-observer variability -- with a 98.7% fully-automatic success rate (only 1.3% of cases required manual correction).
Architecture
CNN (2D)
Dilated U-Net (2D CNN) for pixel-wise segmentation of the carotid intima-media complex, preceded by a separate far-wall localization network
Added to catalog
2026-08-12
Multicenter Carotid Ultrasound IMT Database (CREATIS / Univ Lyon)
2,176 longitudinal B-mode common carotid artery ultrasound images from a multicenter database, each annotated by two experts for intima-media complex boundaries.
Segmentation of the intima-media complex (near and far wall) of the common carotid artery on longitudinal B-mode ultrasound images, used to measure intima-media thickness (IMT)