Carotid wall volume quantification from magnetic resonance images using deformable model fitting and learning-based correction of systematic errors

Cascaded residual U-net for fully automatic segmentation of 3D carotid artery in high-resolution multi-contrast MR images

Accurate and automatic carotid artery segmentation for magnetic resonance (MR) images is eagerly expected, which can greatly assist a comprehensive study of atherosclerosis and accelerate the translation. Although many efforts have been made, identification of the inner lumen and outer wall in diseased vessels is still a challenging task due to complex vascular deformation, blurred wall boundary, and confusing componential expression. In this paper, we introduce a novel fully automatic 3D framework for simultaneously segmenting the carotid artery from high-resolution multi-contrast MR sequences based on deep learning. First, an optimal channel fitting structure is designed for identity mapping, and a novel 3D residual U-net is used as a basic network. Second, high-resolution MR images are trained using both patch-level and global-level strategies, and the two pre-segmentation results are optimized based on structural characteristics. Third, the optimized pre-segmentation results are cascaded with the patch-cropped MR volume data and trained to segment the carotid lumen and wall. Extensive experiments demonstrate the proposed method outperforms the state-of-the-art 3D Unet-based segmentation models.

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

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.

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

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.

A deep learning oriented method for automated 3D reconstruction of carotid arterial trees from MR imaging

The scope of this paper is to present a new carotid vessel segmentation algorithm implementing the U-net based convolutional neural network architecture. With carotid atherosclerosis being the major cause of stroke in Europe, new methods that can provide more accurate image segmentation of the carotid arterial tree and plaque tissue can help improve early diagnosis, prevention and treatment of carotid disease. Herein, we present a novel methodology combining the U-net model and morphological active contours in an iterative framework that accurately segments the carotid lumen and outer wall. The method automatically produces a 3D meshed model of the carotid bifurcation and smaller branches, using multispectral MR image series obtained from two clinical centres of the TAXINOMISIS study. As indicated by a validation study, the algorithm succeeds high accuracy (99.1% for lumen area and 92.6% for the perimeter) for lumen segmentation. The proposed algorithm will be used in the TAXINOMISIS study to obtain more accurate 3D vessel models for improved computational fluid dynamics simulations and the development of models of atherosclerotic plaque progression.

Using a distance map and an active contour model to segment the carotid artery boundary from the lumen contour in proton density weighted magnetic resonance images

Segmentation methods have assumed an important role in image-based diagnosis of several cardiovascular diseases. Particularly, the segmentation of the boundary of the carotid artery is demanded in the detection and characterization of atherosclerosis and assessment of the disease progression. In this article, a fully automatic approach for the segmentation of the carotid artery boundary in Proton Density Weighted Magnetic Resonance Images is presented. The approach relies on the expansion of the lumen contour based on a distance map built using the gray-weighted distance relative to the center of the identified lumen region in the image under analysis. Then, a Snake model with a modified weighted external energy based on the combination of a balloon force along with a Gradient Vector Flow-based external energy is applied to the expanded contour towards the correct boundary of the carotid artery. The average values of the Dice coefficient, Polyline distance, mean contour distance and centroid distance found in the segmentation of 139 carotid arteries were 0.83 ± 0.11, 2.70 ± 1.69 pixels, 2.79 ± 1.89 pixels and 3.44 ± 2.82 pixels, respectively. The segmentation results of the proposed approach were also compared against the ones obtained by related approaches found in the literature, which confirmed the outstanding performance of the new approach. Additionally, the proposed weighted external energy for the Snake model was shown to be also robust to carotid arteries with large thickness and weak boundary image edges.

Cooperative carotid artery centerline extraction in MRI

Centerline extraction of the carotid artery in MRI is important to analyze the artery geometry and to provide input for further processing such as registration and segmentation. The centerline of the artery bifurcation is often extracted by means of two independent minimum cost paths ranging from the common to the internal and the external carotid artery. Often the cost is not well defined at the artery bifurcation, leading to centerline errors. To solve this problem, we developed a method to cooperatively extract both centerlines, where in the cost to extract each centerline, we integrate a constraint region derived from the estimated position of the neighbor centerline. This method avoids that both centerlines follow the same cheapest path after the bifurcation, which is a common error when the paths are extracted independently. We show that this method results in less error compared to extracting them independently: 10 failed centerlines Vs. 3 failures in a data set of 161 arteries with manual annotations. Additionally, we show that the new method improves the non-cooperative approach in 28 cases (p < 0.0001) in a data set of 3,904 arteries.

Automated Registration of Freehand B-Mode Ultrasound and Magnetic Resonance Imaging of the Carotid Arteries Based on Geometric Features

An automated method for registering B-mode ultrasound (US) and magnetic resonance imaging (MRI) of the carotid arteries is proposed. The registration uses geometric features, namely, lumen centerlines and lumen segmentations, which are extracted fully automatically from the images after manual annotation of three seed points in US and MRI. The registration procedure starts with alignment of the lumen centerlines using a point-based registration algorithm. The resulting rigid transformation is used to initialize a rigid and subsequent non-rigid registration procedure that jointly aligns centerlines and segmentations by minimizing a weighted sum of the Euclidean distance between centerlines and the dissimilarity between segmentations. The method was evaluated in 28 carotid arteries from eight patients and six healthy volunteers. First, the automated US lumen segmentation method was validated and optimized in a cross-validation experiment. Next, the effect of the weighting parameter of the proposed registration dissimilarity metric and the control point spacing in the non-rigid registration was evaluated. Finally, the proposed registration method was evaluated in comparison to an existing intensity-and-point-based method, a registration using only the centerlines and a registration using manual US lumen segmentations. Registration accuracy was measured in terms of the mean surface distance between manual US segmentations and the registered MRI segmentations. The average mean surface distance was 0.78 ± 0.34 mm for all subjects, 0.65 ± 0.09 mm for healthy volunteers and 0.87 ± 0.42 mm for patients. The results for the complete set were significantly better (Wilcoxon test, p < 0.01) than the results for the intensity-and-point-based method and the centerline-based registration method. We conclude that the proposed method can robustly and accurately register US and MR images of the carotid artery, allowing multimodal analysis of the carotid plaque to improve plaque assessment.

Determinants of carotid atherosclerotic plaque burden in a stroke-free population

BACKGROUND AND AIMS

In a large stroke-free population, we sought to identify cardiovascular risk factors and carotid plaque components associated with carotid plaque burden, lumen volume and stenosis.

METHODS

The carotid arteries of 1562 stroke-free participants from The Rotterdam Study were imaged on a 1.5-Tesla MRI scanner. Inner and outer wall of the carotid arteries were automatically segmented and lumen volume (mm³), wall volume (outer wall-inner wall) and plaque burden (wall volume/outer wall volume) (%) were quantified. Plaque components were visually determined and luminal stenosis was assessed. We analyzed associations of cardiovascular risk factors and carotid plaque components with plaque burden and lumen volumes using regression analysis.

RESULTS

We investigated 2821 carotid plaques and found that women had larger plaque burden (50.7 ± 7.8% vs. 49.2 ± 7.7%, p < 0.0001) and smaller lumen volumes (933 ± 286 mm³vs. 1078 ± 334 mm³, p < 0.0001) than men. In women, age, HDL-cholesterol and systolic blood pressure, and in men, total cholesterol, non-HDL cholesterol and statin use were independently associated with higher plaque burden and lumen volume. Furthermore, smoking and diabetes were associated with lumen volume in men (respectively p = 0.04 and p = 0.002). Intraplaque hemorrhage (IPH) and lipid were related to a larger plaque burden (OR 1.30 [1.05-1.60] and OR 1.28[1.06-1.55]). Finally, within the highest quartile of plaque burden, IPH was strongly associated with luminal stenosis independent of age, sex, plaque burden and composition (Beta = 15.2; [11.8-18.6]).

CONCLUSIONS

Several cardiovascular risk factors and plaque components, in particular IPH, are associated with higher plaque burden. Carotid IPH is strongly associated with an increased luminal stenosis.

Carotid Artery Wall Segmentation in Multispectral MRI by Coupled Optimal Surface Graph Cuts

We present a new three-dimensional coupled optimal surface graph-cut algorithm to segment the wall of the carotid artery bifurcation from Magnetic Resonance (MR) images. The method combines the search for both inner and outer borders into a single graph cut and uses cost functions that integrate information from multiple sequences. Our approach requires manual localization of only three seed points indicating the start and end points of the segmentation in the internal, external, and common carotid artery. We performed a quantitative validation using images of 57 carotid arteries. Dice overlap of 0.86 ± 0.06 for the complete vessel and 0.89 ± 0.05 for the lumen compared to manual annotation were obtained. Reproducibility tests were performed in 60 scans acquired with an interval of 15 ± 9 days, showing good agreement between baseline and follow-up segmentations with intraclass correlations of 0.96 and 0.74 for the lumen and complete vessel volumes respectively.

Multiple Sparse Representations Classification

Sparse representations classification (SRC) is a powerful technique for pixelwise classification of images and it is increasingly being used for a wide variety of image analysis tasks. The method uses sparse representation and learned redundant dictionaries to classify image pixels. In this empirical study we propose to further leverage the redundancy of the learned dictionaries to achieve a more accurate classifier. In conventional SRC, each image pixel is associated with a small patch surrounding it. Using these patches, a dictionary is trained for each class in a supervised fashion. Commonly, redundant/overcomplete dictionaries are trained and image patches are sparsely represented by a linear combination of only a few of the dictionary elements. Given a set of trained dictionaries, a new patch is sparse coded using each of them, and subsequently assigned to the class whose dictionary yields the minimum residual energy. We propose a generalization of this scheme. The method, which we call multiple sparse representations classification (mSRC), is based on the observation that an overcomplete, class specific dictionary is capable of generating multiple accurate and independent estimates of a patch belonging to the class. So instead of finding a single sparse representation of a patch for each dictionary, we find multiple, and the corresponding residual energies provides an enhanced statistic which is used to improve classification. We demonstrate the efficacy of mSRC for three example applications: pixelwise classification of texture images, lumen segmentation in carotid artery magnetic resonance imaging (MRI), and bifurcation point detection in carotid artery MRI. We compare our method with conventional SRC, K-nearest neighbor, and support vector machine classifiers. The results show that mSRC outperforms SRC and the other reference methods. In addition, we present an extensive evaluation of the effect of the main mSRC parameters: patch size, dictionary size, and sparsity level.