Correlation analysis of coronary artery tortuosity and calcification score

Tortuosity in non-atherosclerotic vascular diseases is associated with age, arterial aneurysms, and hypertension

BACKGROUND

Increased arterial tortuosity has been associated with various cardiovascular complications. However, the extent and role of arterial tortuosity in non-atherosclerotic vascular diseases remain to be fully elucidated. This study aimed to assess arterial tortuosity index (ATI) in patients with non-atherosclerotic vascular diseases and the associated factors.

METHODS

This is a retrospective analysis of patients with non-atherosclerotic vascular diseases referred to the Malformation and Rare Vascular Disease Center at the University Hospital in Lausanne (Switzerland). Computed tomography angiography (CTA) images performed between October 2010 and April 2022 were retrieved and the aortic tortuosity index (ATI) was calculated. Patients were classified based on diagnosis into the following groups: arterial dissection & aneurysm, arteritis & autoimmune disease, hereditary connective tissue diseases, and fibromuscular dysplasia (FMD). Univariate and multivariate logistic regression analysis was used to determine potentially relevant predictors of aortic tortuosity.

RESULTS

The mean age upon computed tomography angiography (CTA) was 46.8 (standard deviation [SD] 14.6) years and 59.1% of the patients were female. Mean ATI was higher in patients over 60 years old (1.27), in those with arterial aneurysms (mean: 1.11), and in those diagnosed with hypertension (mean: 1.13). When only patients over 60 years old were considered, those diagnosed with connective tissue diseases had the highest ATI. At multivariate regression analysis, increasing age (p < 0.05), presence of arterial aneurysms (p < 0.05), and hypertension (p < 0.05) were independently associated with ATI.

CONCLUSIONS

The ATI may be a promising tool in diagnostic evaluation, cardiovascular risk stratification, medical or surgical management, and prognostic assessment in several non-atherosclerotic vascular conditions. Further studies with longitudinal design and larger cohorts are needed to validate the role of ATI in the full spectrum of vascular diseases.

A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization

Coronary computed tomography angiography (CCTA) allows detailed assessment of early markers associated with coronary artery disease (CAD), such as coronary artery calcium (CAC) and tortuosity (CorT). However, their analysis can be time-demanding and biased. We present a fully automated pipeline that performs (i) coronary artery segmentation and (ii) CAC and CorT objective analysis. Our method exploits supervised learning for the segmentation of the lumen, and then, CAC and CorT are automatically quantified. 281 manually annotated CCTA images were used to train a two-stage U-Net-based architecture. The first stage employed a 2.5D U-Net trained on axial, coronal, and sagittal slices for preliminary segmentation, while the second stage utilized a multichannel 3D U-Net for refinement. Then, a geometric post-processing was implemented: vessel centerlines were extracted, and tortuosity score was quantified as the count of branches with three or more bends with change in direction forming an angle >45°. CAC scoring relied on image attenuation. CAC was detected by setting a patient specific threshold, then a region growing algorithm was applied for refinement. The application of the complete pipeline required <5 min per patient. The model trained for coronary segmentation yielded a Dice score of 0.896 and a mean surface distance of 1.027 mm compared to the reference ground truth. Tracts that presented stenosis were correctly segmented. The vessel tortuosity significantly increased locally, moving from proximal, to distal regions (p < 0.001). Calcium volume score exhibited an opposite trend (p < 0.001), with larger plaques in the proximal regions. Volume score was lower in patients with a higher tortuosity score (p < 0.001). Our results suggest a linked negative correlation between tortuosity and calcific plaque formation. We implemented a fast and objective tool, suitable for population studies, that can help clinician in the quantification of CAC and various coronary morphological parameters, which is helpful for CAD risk assessment.