Fast segmentation of the femoral arteries from 3D MR images: A tool for rapid assessment of peripheral arterial disease

Chen, Weifu; Xu, Jianrong; Chiu, Bernard

doi:10.1118/1.4916803

Cited by 6 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also found that the tortuosity of the BA was significantly correlated with the Mean WT of the BA. Mean WT represents one of the metrics for plaque burden (24,25). Previous studies showed that higher curvature of the superficial femoral artery might lead to larger area ratios of low WSS (8).…”

Section: Discussionmentioning

confidence: 99%

Geometrical characteristics associated with atherosclerotic disease in the basilar artery: a magnetic resonance vessel wall imaging study

Deng

Zheng

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Vascular geometry may play an important role in the development of atherosclerosis. This study aimed to investigate the relationships between the geometrical characteristics of basilar artery (BA) and the presence, burden, and distribution of BA plaques using magnetic resonance vessel wall imaging.Methods: Patients with cerebrovascular symptoms in the posterior circulation were recruited and underwent magnetic resonance imaging. The BA's geometrical characteristics, including actual length, straightened length, tortuosity, lateral basilar artery-vertebral artery (VA) angle, lateral mid-BA angle, and BA convexity, were measured. The presence of plaques, stenosis, and plaque burden, including mean and maximal wall thickness, were evaluated. The BA's cross-sectional vessel wall was divided into 4 quadrants: dorsal, ventral, right, and left quadrant. The distribution of BA plaques was analyzed.Results: Of 344 recruited patients (mean age: 68.1±11.1 years; 200 males), 100 (29.1%) had BA plaques.Patients with BA plaques had higher tortuosity of the BA (13.6±9.0 vs. 9.7±7.7, P<0.001) compared to those without BA plaques. Multivariate regression analysis showed that tortuosity of the BA was associated with the presence of BA plaques (OR, 1.641; 95% CI, 1.232 to 2.186; P=0.001) and mean wall thickness (β, 0.045; 95% CI, 0.008 to 0.081; P=0.017). The plaque distribution in the left wall and right wall of BA was more frequent in patients with right (P=0.006) and left (P<0.001) convex BA, respectively.Conclusions: The BA's geometrical characteristics, particularly tortuosity and convexity, are independently associated with the presence, burden, and distribution of plaques in the BA.

show abstract

Section: Discussionmentioning

confidence: 99%

Geometrical characteristics associated with atherosclerotic disease in the basilar artery: a magnetic resonance vessel wall imaging study

Deng

Zheng

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…Unfortunately, despite the relevant improvements [45], the derived patient-specific information results in limited resolution and the reconstruction errors, if not corrected, may highly affect the CFD results, in particular along the stented regions. Moreover, to avoid operator-dependence in the correction phase, a semi-automatic correction of the reconstruction errors could reduce the processing time and the variability of the reconstructed models [46] . In this work, a semi-automatic method for the 3D reconstruction of stented SFA starting from CT images was developed.…”

Section: Discussionmentioning

confidence: 99%

Computing patient-specific hemodynamics in stented femoral artery models obtained from computed tomography using a validated 3D reconstruction method

Colombo

Bologna

Garbey

et al. 2020

Medical Engineering & Physics

View full text Add to dashboard Cite

“…In our experiment, K = 4 and the longitudinal coverage of the segment is 3.2mm. The assumption can be made as the segment is much smaller than the 10mm ISD by which previous studies 1,5 quantified femoral vessel wall burden.…”

Section: Pseudo-label Generationmentioning

confidence: 99%

“…A related issue is that it takes too long to segment hundreds of axial images acquired for a superficial femoral artery. In order to reduce the workload, expert reviewers segmented the 30cm artery with a 1cm interslice distance (ISD) in our previous studies 1,5 and the segmentation of the vessel wall on the 30 slices already took 70-80 mins. The development of an automated segmentation algorithm would reduce the time required for segmentation, thereby allowing more slices to be segmented with a smaller ISD.…”

Section: Introductionmentioning

confidence: 99%

Semi-supervised vessel wall detection and segmentation from 3D femoral MR images

Yan

Chiu

2023

Medical Imaging 2023: Image Processing

View full text Add to dashboard Cite

Vessel wall volume (VWV) for the femoral arteries is a sensitive indicator of coexistent generalized atherosclerosis. Measuring VWV requires the segmentation of lumen and outer wall boundaries from 3D MR images. The main challenge for vessel wall segmentation is the small size of femoral artery in a 3D MR image and the existence of objects mimicking arteries. Besides, due to the long span of the femoral artery and time-consuming manual segmentation, a large number of image slices are not manually segmented, and therefore, cannot be used to train fully supervised methods. We proposed a semi-supervised end-to-end artery localization and segmentation model that improves segmentation performance through the use of axial image slices that are not manually segmented (unlabeled slices). The method localizes femoral arteries with bounding boxes and performs segmentation over the selected regions. A mean teacher framework was trained to generate high-quality segmentation for unlabeled slices, serving as pseudo-labels to improve the student model's performance in arterial detection and vessel wall segmentation. A new continuity score was developed to further improve the quality of the vessel wall segmentation on unlabeled image slices. Our experiments show that the semi-supervised approach and the proposed continuity score independently improve the femoral vessel wall segmentation.

show abstract

Fast segmentation of the femoral arteries from 3D MR images: A tool for rapid assessment of peripheral arterial disease

Abstract: The proposed semiautomatic algorithm generated accurate lumen and outer wall boundaries from 3D black-blood MR images with few user interactions, thereby allowing rapid and streamlined assessment of plaque burden in the femoral arteries.

Cited by 6 publications

References 29 publications

Geometrical characteristics associated with atherosclerotic disease in the basilar artery: a magnetic resonance vessel wall imaging study

Geometrical characteristics associated with atherosclerotic disease in the basilar artery: a magnetic resonance vessel wall imaging study

Computing patient-specific hemodynamics in stented femoral artery models obtained from computed tomography using a validated 3D reconstruction method

Semi-supervised vessel wall detection and segmentation from 3D femoral MR images

Contact Info

Product

Resources

About