Carotid Artery Wall Segmentation in Multispectral MRI by Coupled Optimal Surface Graph Cuts

Abstract

We present a new three-dimensional coupled optimal surface graph-cut algorithm to segment the wall of the carotid artery bifurcation from Magnetic Resonance (MR) images. The method combines the search for both inner and outer borders into a single graph cut and uses cost functions that integrate information from multiple sequences. Our approach requires manual localization of only three seed points indicating the start and end points of the segmentation in the internal, external, and common carotid artery. We performed a quantitative validation using images of 57 carotid arteries. Dice overlap of 0.86 ± 0.06 for the complete vessel and 0.89 ± 0.05 for the lumen compared to manual annotation were obtained. Reproducibility tests were performed in 60 scans acquired with an interval of 15 ± 9 days, showing good agreement between baseline and follow-up segmentations with intraclass correlations of 0.96 and 0.74 for the lumen and complete vessel volumes respectively.

Deep morphology aided diagnosis network for segmentation of carotid artery vessel wall and diagnosis of carotid atherosclerosis on black‐blood vessel wall MRI

“…However, due to the complex signal characteristics found near the vessel walls, the slice-by-slice analysis of the VW-MRI images with moderate interreader reproducibility is cumbersome for the plaque burden assessment. 16 Some automated or semi-automated segmentation methods have been proposed for the carotid artery, and the lumen and the outer wall boundaries are typically segmented in a two-dimensional (2D) slice-by-slice mode [17][18][19][20][21][22] or three-dimensional (3D) mode, [23][24][25][26][27] where the lumen and the outer wall boundaries are depicted as the contours to calculate the plaque burden metrics for the diagnosis of atherosclerosis. The 2D parametric deformable model-based methods (e.g., the snake contour 17 and the discrete dynamic contour 18 ) segment the carotid lumen boundary and the outer wall boundary on each transverse slice, but they require considerable manual interaction (initial contours).…”

Comparison of CT and CMR for detection and quantification of carotid artery calcification: the Rotterdam Study

“…We manually annotated and segmented calcification in all plaques using a standardized approach. First, we pre-processed all images using a method that has been described extensively before [15]. This starts with a bias correction to reduce the intensity inhomogeneity characteristic in CMR [15].…”

“…First, we pre-processed all images using a method that has been described extensively before [15]. This starts with a bias correction to reduce the intensity inhomogeneity characteristic in CMR [15]. Subsequently, the carotid artery in all images was rigidly registered to the black-blood image space using the Elastix tool [15].…”

“…This starts with a bias correction to reduce the intensity inhomogeneity characteristic in CMR [15]. Subsequently, the carotid artery in all images was rigidly registered to the black-blood image space using the Elastix tool [15]. For the registration of the sequences, a Region Of Interest (ROI) around the artery in black-blood was used.…”

“…For the registration of the sequences, a Region Of Interest (ROI) around the artery in black-blood was used. This ROI was obtained semi-automatically by uniformly growing an extracted carotid artery centerline, which requires three marked seed points at the common, internal and external parts of the artery [15]. Then calcification was manually delineated in every consecutive slice using an annotation tool developed in Mevislab (MeVisLab, MeVis Medical Solutions AG).…”