Understanding Atherosclerosis Through an Osteoarthritis Data Set

Liu, Wenjin; Balu, Niranjan; Cantón, Gádor; Hippe, Daniel S.; Watase, Hiroko; Waterton, John C.; Hatsukami, Thomas S.; Yuan, Chun

doi:10.1161/atvbaha.119.312513

Cited by 11 publications

(7 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method proposed to segment carotid arteries is also applicable to other vascular beds. One example was the popliteal arteries [43]. We used a publicly accessible popliteal artery dataset [44] to test the generalizability of our model on a large popliteal artery dataset in which there are challenging cases where some vessel wall boundaries are unclear and vein/branching artery co-exists near the artery of interest.…”

Section: Discussionmentioning

confidence: 99%

Automated Artery Localization and Vessel Wall Segmentation Using Tracklet Refinement and Polar Conversion

et al. 2020

Self Cite

View full text Add to dashboard Cite

Quantitative analysis of blood vessel wall structures is important to study atherosclerotic diseases and assess cardiovascular event risks. To achieve this, accurate identification of vessel luminal and outer wall contours is needed. Computer-assisted tools exist, but manual preprocessing steps, such as region of interest identification and/or boundary initialization, are still needed. In addition, prior knowledge of the ring shape of vessel walls has not been fully explored in designing segmentation methods. In this work, a fully automated artery localization and vessel wall segmentation system is proposed. A tracklet refinement algorithm was adapted to robustly identify the artery of interest from a neural network-based artery centerline identification architecture. Image patches were extracted from the centerlines and converted in a polar coordinate system for vessel wall segmentation. The segmentation method used 3D polar information and overcame problems such as contour discontinuity, complex vessel geometry, and interference from neighboring vessels. Verified by a large (>32000 images) carotid artery dataset collected from multiple sites, the proposed system was shown to better automatically segment the vessel wall than traditional vessel wall segmentation methods or standard convolutional neural network approaches. In addition, a segmentation uncertainty score was estimated to effectively identify slices likely to have errors and prompt manual confirmation of the segmentation. This robust vessel wall segmentation system has applications in different vascular beds and will facilitate vessel wall feature extraction and cardiovascular risk assessment.

show abstract

Section: Discussionmentioning

confidence: 99%

Automated Artery Localization and Vessel Wall Segmentation Using Tracklet Refinement and Polar Conversion

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Subjects underwent bilateral knee MRI with 1 of 4 identical Siemens 3T MRI scanners, which used standardized acquisition protocols across all sites. Vessel wall analysis was performed using 3‐dimensional double‐echo steady‐state (DESS) sequence acquired in the sagittal orientation, 14 with the following imaging parameters: repetition time/echo time: 16.32/4.7 ms, field of view: 140×140 mm, 0.7 mm slice thickness, and 0.37×0.46 mm in‐plane resolution. Coverage was 10 cm above and below the knee, including proximal and distal segments of the popliteal artery.…”

Section: Methodsmentioning

confidence: 99%

“…DESS has been demonstrated to provide good vessel wall delineation of lower‐limb arteries. 14 , 16 Detailed imaging parameters for the OAI 3‐dimensional DESS sequences can be found in the work by Peterfy et al 17 …”

Section: Methodsmentioning

confidence: 99%

“… 10 , 11 , 13 An additional advantage of using the OAI population relies on the number of shared risk factors between osteoarthritis and atherosclerosis, such as age and obesity, and the added risk factors to atherosclerosis from osteoarthritis, such as impaired mobility and use of nonsteroidal anti‐inflammatory drugs. 14 However, the challenge of analyzing this large data set lies on the time required for accurate manual delineation of the luminal and wall boundaries on the magnetic resonance (MR) images. To overcome this, we propose to use an artificial intelligence‐based, fully automated vessel wall segmentation tool, Fully Automated and Robust Analysis Technique for Popliteal Artery Evaluation (FRAPPE), able to efficiently analyze population‐based MR data sets.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Atherosclerotic Burden and Remodeling Patterns of the Popliteal Artery as Detected in the Magnetic Resonance Imaging Osteoarthritis Initiative Data Set

Cantón

Hippe

Chen

et al. 2021

JAHA

Self Cite

View full text Add to dashboard Cite

Background An artificial intelligence vessel segmentation tool, Fully Automated and Robust Analysis Technique for Popliteal Artery Evaluation (FRAPPE), was used to analyze a large databank of popliteal arteries imaged through the OAI (Osteoarthritis Initiative) to study the impact of atherosclerosis risk factors on vessel dimensions and characterize remodeling patterns. Methods and Results Magnetic resonance images from 4668 subjects contributing 9189 popliteal arteries were analyzed using FRAPPE. Age ranged from 45 to 79 years (median, 61), and 58% were women. Mean lumen diameter, mean outer wall diameter, and mean wall thickness (MWT) were measured per artery. Their median values were 5.8 mm (interquartile range, 5.2–6.5 mm), 7.3 mm (interquartile range, 6.7–8.1 mm), and 0.78 mm (interquartile range, 0.73–0.84 mm) respectively. MWT was associated with multiple cardiovascular risk factors, with age (4.2% increase in MWT per 10‐year increase in age; 95% CI, 3.9%–4.5%) and sex (8.6% higher MWT in men than women; 95% CI, 7.7%–9.3%) being predominant. On average, lumen and outer wall diameters increased with increasing MWT until the thickness was 0.92 mm for men and 0.84 mm for women. After this point, lumen diameter decreased steadily, more rapidly in men than women (−7.9% versus −6.1% per 25% increase in MWT; P <0.001), with little change in outer wall diameter. Conclusions FRAPPE has enabled the analysis of the large OAI knee magnetic resonance imaging data set, successfully showing that popliteal atherosclerosis is predominantly associated with age and sex. The average vessel remodeling pattern consisted of an early phase of compensatory enlargement, followed by a negative remodeling, which is more pronounced in men.

show abstract

“…This massive dataset (bilateral knee MRI in 4796 subjects up to eight timepoints over a period of 96 mo, over three million images in total) provides high‐quality 3D VW MRI images with the popliteal artery wall (in axial view) clearly visible on the 3D DESS sequence. Therefore, it is ideal for research on vessel wall features as MR biomarkers 8 and the relationship of these biomarkers with cardiovascular risk 9 …”

Section: Introductionmentioning

confidence: 99%

Fully automated and robust analysis technique for popliteal artery vessel wall evaluation (FRAPPE) using neural network models from standardized knee MRI

Chen

Cantón

Liu

et al. 2020

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Purpose To develop a fully automated vessel wall (VW) analysis workflow (fully automated and robust analysis technique for popliteal artery evaluation, FRAPPE) on the popliteal artery in standardized knee MR images. Methods Popliteal artery locations were detected from each MR slice by a deep neural network model and connected into a 3D artery centerline. Vessel wall regions around the centerline were then segmented using another neural network model for segmentation in polar coordinate system. Contours from vessel wall segmentations were used for vascular feature calculation, such as mean wall thickness and wall area. A transfer learning and active learning framework was applied in training the localization and segmentation neural network models to maintain accuracy while reducing manual annotations. This new popliteal artery analysis technique (FRAPPE) was validated against manual segmentation qualitatively and quantitatively in a series of 225 cases from the Osteoarthritis Initiative (OAI) dataset. Results FRAPPE demonstrated high accuracy and robustness in locating popliteal arteries, segmenting artery walls, and quantifying arterial features. Qualitative evaluations showed 1.2% of slices had noticeable major errors, including segmenting the wrong target and irregular vessel wall contours. The mean Dice similarity coefficient with manual segmentation was 0.79, which is comparable to inter‐rater variations. Repeatability evaluations show most of the vascular features have good to excellent repeatability from repeated scans of same subjects, with intra‐class coefficient ranging from 0.80 to 0.98. Conclusion This technique can be used in large population‐based studies, such as OAI, to efficiently assess the burden of atherosclerosis from routine MR knee scans.

show abstract

Understanding Atherosclerosis Through an Osteoarthritis Data Set

Cited by 11 publications

References 101 publications

Automated Artery Localization and Vessel Wall Segmentation Using Tracklet Refinement and Polar Conversion

Automated Artery Localization and Vessel Wall Segmentation Using Tracklet Refinement and Polar Conversion

Atherosclerotic Burden and Remodeling Patterns of the Popliteal Artery as Detected in the Magnetic Resonance Imaging Osteoarthritis Initiative Data Set

Fully automated and robust analysis technique for popliteal artery vessel wall evaluation (FRAPPE) using neural network models from standardized knee MRI

Contact Info

Product

Resources

About