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

Abstract

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.

Domain adaptive and fully automated carotid artery atherosclerotic lesion detection using an artificial intelligence approach (LATTE) on 3D MRI

“…The patch size was selected empirically based on carotid artery size and computational costs. In order to select the specific artery wall for classification when multiple artery walls exist in region of interest, (for example, ECA and ICA co‐existing on image slices in the bifurcation region), vessel walls were segmented using a convolutional neural network (CNN) model 23 for each carotid artery before classification. The binary segmented region, as an attention mask, was concatenated with the original patch in the channel dimension of the image.…”

“…Artery localization: a tracking-by-detection algorithm was used to refine the 2D bounding box detection results in step 3 and generate artery centerlines of interest. 23,24 Then the CCA/ICA/ECA were identified based on relative locations. 6.…”

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

“…Artery detection might initially include false objects or missed popliteal arteries in certain images. A tracklet refinement step 19 is thus used to combine the neighboring detection information to generate the centerline of the popliteal artery of interest. Patches along the centerline are extracted for vessel wall segmentation.…”

“…Adam optimizer 22 is used to control the learning rate. Please refer to Chen et al 19 for detailed descriptions for techniques of artery localization and vessel wall segmentation.…”

“…Transfer learning techniques were applied to train the localization and segmentation models, aided by limited human annotations. Initiated from previous models for carotid artery applications 19 where human annotations of 32,591 image slices from 1157 subjects are available, models could be trained using a relatively small dataset of popliteal artery images to reduce the need for tedious human labeling.…”