Comparison of Manual versus Semi-Automatic Segmentations of the Stenotic Carotid Artery Bifurcation

Abstract

Background: The image reconstruction of stenotic carotid bifurcation can be managed by medical practitioners and non-medical investigators with semi-automatic or manual segmentation. The outcome of blood flow simulations may vary because of a single mean voxel difference along the examined section, possibly more in the stenotic lesions, which can lead to conflicting results regarding other research findings. The aim of our project is computational geometry reconstruction for blood flow simulations to make it suitable for comparison with plaque image analysis performed by commercially available software. In this paper, a comparison is made between the manual and semi-automatic segmentations performed by non-medical and medical investigators, respectively. Methods: 30 patients were classified into three homogeneous groups. Our group classification was based on the following parameters: plaque calcification score, thickness, extent, remodeling and plaque localization. The images in the first group were segmented individually by medical practitioners and experienced non-medical investigators, the second group was segmented collectively, and the last group was segmented individually again. Cross-sections along the centerline were extracted, then geometrical and statistical analyses were performed. Exploratory flow simulations were carried out on two patients to showcase the effect of geometrical differences on the hemodynamic flow field. Results: The largest centerline-averaged voxel difference between the medical and non-medical investigators occurred in the first group with a positive difference of 1.16 voxels. In the second and third groups, the average voxel difference decreased to 0.65 and 0.75, respectively. The example case from the first group showed that the difference in maximum wall shear stress in the middle of the stenosis is 30% with an average voxel difference of 1.73. Meanwhile, it can decrease to 4% when the average voxel difference is 0.64 for the example case from the third group. Conclusions: A collective review of the medical images should preceded the manual segmentations before applying them in computational simulations in order to ensure a proper comparison with plaque image analysis. Especially complex pathology such as calcifications should be segmented under medical supervision or after specific training. Non-significant differences in the segmentation can lead to significant differences in the computed flow field.