Arna van Engelen

Three-Dimensional Carotid Ultrasound Plaque Texture Predicts Vascular Events

Background and Purpose— Carotid ultrasound atherosclerosis measurements, including those of the arterial wall and plaque, provide a way to monitor patients at risk of vascular events. Our objective was to examine carotid ultrasound plaque texture measurements and the change in carotid plaque texture during 1 year in patients at risk of events and to compare these with measurements of plaque volume and other risk factors as predictors of vascular events. Methods— We evaluated 298 patients with carotid atherosclerosis using 3-dimensional (3D) ultrasound at baseline and after 1 year and measured carotid plaque volume and 376 measures of plaque texture. Patients were followed up to 5 years (median [range], 3.12 [0.77–4.66]) for myocardial infarction, transient ischemic attack, and stroke. Sparse Cox regression was used to select the most predictive plaque texture measurements in independent training sets using a 10-fold cross-validation, repeated 5×, to ensure unbiased results. Results— Receiver operator curves and Kaplan–Meier analysis showed that changes in texture and total plaque volume combined provided the best predictor of vascular events. In multivariate Cox regression, changes in plaque texture (median hazard ratio, 1.4; P<0.001) and total plaque volume (median hazard ratio, 1.5 per 100 mm3; P<0.001) were both significant predictors, whereas the Framingham risk score was not. Conclusions— Changes in both plaque texture and volume are strongly predictive of vascular events. In high-risk patients, 3D ultrasound plaque measurements should be considered for vascular event risk prediction.

Atherosclerotic Plaque Component Segmentation in Combined Carotid MRI and CTA Data Incorporating Class Label Uncertainty

Atherosclerotic plaque composition can indicate plaque vulnerability. We segment atherosclerotic plaque components from the carotid artery on a combination of in vivo MRI and CT-angiography (CTA) data using supervised voxelwise classification. In contrast to previous studies the ground truth for training is directly obtained from 3D registration with histology for fibrous and lipid-rich necrotic tissue, and with CT for calcification. This registration does, however, not provide accurate voxelwise correspondence. We therefore evaluate three approaches that incorporate uncertainty in the ground truth used for training: I) soft labels are created by Gaussian blurring of the original binary histology segmentations to reduce weights at the boundaries between components, and are weighted by the estimated registration accuracy of the histology and in vivo imaging data (measured by overlap), II) samples are weighted by the local contour distance of the lumen and outer wall between histology and in vivo data, and III) 10% of each class is rejected by Gaussian outlier rejection. Classification was evaluated on the relative volumes (% of tissue type in the vessel wall) for calcified, fibrous and lipid-rich necrotic tissue, using linear discriminant (LDC) and support vector machine (SVM) classification. In addition, the combination of MRI and CTA data was compared to using only one imaging modality. Best results were obtained by LDC and outlier rejection: the volume error per vessel was 0.91.0% for calcification, 12.77.6% for fibrous and 12.18.1% for necrotic tissue, with Spearman rank correlation coefficients of 0.91 (calcification), 0.80 (fibrous) and 0.81 (necrotic). While segmentation using only MRI features yielded low accuracy for calcification, and segmentation using only CTA features yielded low accuracy for necrotic tissue, the combination of features from MRI and CTA gave good results for all studied components.

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.

Multi-Center MRI Carotid Plaque Component Segmentation Using Feature Normalization and Transfer Learning

Automated segmentation of plaque components in carotid artery magnetic resonance imaging (MRI) is important to enable large studies on plaque vulnerability, and for incorporating plaque composition as an imaging biomarker in clinical practice. Especially supervised classification techniques, which learn from labeled examples, have shown good performance. However, a disadvantage of supervised methods is their reduced performance on data different from the training data, for example on images acquired with different scanners. Reducing the amount of manual annotations required for each new dataset will facilitate widespread implementation of supervised methods. In this paper we segment carotid plaque components of clinical interest (fibrous tissue, lipid tissue, calcification and intraplaque hemorrhage) in a multi-center MRI study. We perform voxelwise tissue classification by traditional same-center training, and compare results with two approaches that use little or no annotated same-center data. These approaches additionally use an annotated set of different-center data. We evaluate 1) a nonlinear feature normalization approach, and 2) two transfer-learning algorithms that use same and different-center data with different weights. Results showed that the best results were obtained for a combination of feature normalization and transfer learning. While for the other approaches significant differences in voxelwise or mean volume errors were found compared with the reference same-center training, the proposed approach did not yield significant differences from that reference. We conclude that both extensive feature normalization and transfer learning can be valuable for the development of supervised methods that perform well on different types of datasets.

Multi-feature-based plaque characterization in ex vivo MRI trained by registration to 3D histology

We present a new method for automated characterization of atherosclerotic plaque composition in ex vivo MRI. It uses MRI intensities as well as four other types of features: smoothed, gradient magnitude and Laplacian images at several scales, and the distances to the lumen and outer vessel wall. The ground truth for fibrous, necrotic and calcified tissue was provided by histology and μCT in 12 carotid plaque specimens. Semi-automatic registration of a 3D stack of histological slices and μCT images to MRI allowed for 3D rotations and in-plane deformations of histology. By basing voxelwise classification on different combinations of features, we evaluated their relative importance. To establish whether training by 3D registration yields different results than training by 2D registration, we determined plaque composition using (1) a 2D slice-based registration approach for three manually selected MRI and histology slices per specimen, and (2) an approach that uses only the three corresponding MRI slices from the 3D-registered volumes. Voxelwise classification accuracy was best when all features were used (73.3 ± 6.3%) and was significantly better than when only original intensities and distance features were used (Friedman, p < 0.05). Although 2D registration or selection of three slices from the 3D set slightly decreased accuracy, these differences were non-significant.

Carotid artery wall segmentation by coupled surface graph cuts

We present a three-dimensional coupled surface graph cut algorithm for carotid wall segmentation from Magnetic Resonance Imaging (MRI). Using cost functions that highlight both inner and outer vessel wall borders, the method combines the search for both borders into a single graph cut optimization. Our approach requires little user interaction and can robustly segment the carotid artery bifurcation. Experiments on 32 carotid arteries from 16 patients show good agreement between manual segmentation performed by an expert and our method. The mean relative area of overlap is more than 85% for both lumen and outer vessel wall. In addition, differences in measured wall thickness with respect to the manual annotations were smaller than the in-plane pixel size.

Supervised in-vivo plaque characterization incorporating class label uncertainty

We segment atherosclerotic plaque components in in-vivo MRI and CT data using supervised voxelwise classification. The most reliable ground truth can be obtained from histology sections, however, it is not straightforward to use this for classifier training as the registration with in-vivo data often shows misalignments. Therefore, for training we incorporate uncertainty in the ground truth via ”soft” labels that indicate a probability for each class. Soft labels are created by Gaussian blurring of the original ”hard” segmentations, and weighted by the registration accuracy. Classification is evaluated on the relative volumes for fibrous, lipid-rich necrotic and calcified tissue. Using conventional hard labels, the differences between the ground truth and classification result per subject are -0.4±3.6% for calcification, +7.6±14.9% for fibrous and -7.2±14.5% for necrotic tissue. Using the new approach accuracy is improved: for calcification -0.6±1.6%, fibrous +3.6±16.8% and necrotic tissue -2.9±16.1%.

Plaque characterization in ex vivo MRI evaluated by dense 3D correspondence with histology

Automatic quantification of carotid artery plaque composition is important in the development of methods that distinguish vulnerable from stable plaques. MRI has shown to be capable of imaging different components noninvasively. We present a new plaque classification method which uses 3D registration of histology data with ex vivo MRI data, using non-rigid registration, both for training and evaluation. This is more objective than previously presented methods, as it eliminates selection bias that is introduced when 2D MRI slices are manually matched to histological slices before evaluation. Histological slices of human atherosclerotic plaques were manually segmented into necrotic core, fibrous tissue and calcification. Classification of these three components was voxelwise evaluated. As features the intensity, gradient magnitude and Laplacian in four MRI sequences after different degrees of Gaussian smoothing, and the distances to the lumen and the outer vessel wall, were used. Performance of linear and quadratic discriminant classifiers for different combinations of features was evaluated. Best accuracy (72.5 ± 7.7%) was reached with the linear classifier when all features were used. Although this was only a minor improvement to the accuracy of a classifier that only included the intensities and distance features (71.6 ± 7.9%), the difference was statistically significant (paired t-test, p<0.05). Good sensitivity and specificity for calcification was reached (83% and 95% respectively), however, differentiation between fibrous (sensitivity 85%, specificity 60%) and necrotic tissue (sensitivity 49%, specificity 89%) was more difficult.

Automated segmentation of atherosclerotic histology based on pattern classification

Background: Histology sections provide accurate information on atherosclerotic plaque composition, and are used in various applications. To our knowledge, no automated systems for plaque component segmentation in histology sections currently exist. Materials and Methods: We perform pixel-wise classification of fibrous, lipid, and necrotic tissue in Elastica Von Gieson-stained histology sections, using features based on color channel intensity and local image texture and structure. We compare an approach where we train on independent data to an approach where we train on one or two sections per specimen in order to segment the remaining sections. We evaluate the results on segmentation accuracy in histology, and we use the obtained histology segmentations to train plaque component classification methods in ex vivo Magnetic resonance imaging (MRI) and in vivo MRI and computed tomography (CT). Results: In leave-one-specimen-out experiments on 176 histology slices of 13 plaques, a pixel-wise accuracy of 75.7 ± 6.8% was obtained. This increased to 77.6 ± 6.5% when two manually annotated slices of the specimen to be segmented were used for training. Rank correlations of relative component volumes with manually annotated volumes were high in this situation (P = 0.82-0.98). Using the obtained histology segmentations to train plaque component classification methods in ex vivo MRI and in vivo MRI and CT resulted in similar image segmentations for training on the automated histology segmentations as for training on a fully manual ground truth. The size of the lipid-rich necrotic core was significantly smaller when training on fully automated histology segmentations than when manually annotated histology sections were used. This difference was reduced and not statistically significant when one or two slices per section were manually annotated for histology segmentation. Conclusions: Good histology segmentations can be obtained by automated segmentation, which show good correlations with ground truth volumes. In addition, these can be used to develop segmentation methods in other imaging modalities. Accuracy increases when one or two sections of the same specimen are used for training, which requires a limited amount of user interaction in practice.