Dataset Information

Atherosclerotic plaque component segmentation in combined carotid MRI and CTA data incorporating class label uncertainty.

ABSTRACT: 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 μCT 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 0.9±1.0% for calcification, 12.7±7.6% for fibrous and 12.1±8.1% 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.

SUBMITTER: van Engelen A

PROVIDER: S-EPMC3999092 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:IntroductionA reliable and automated method to segment and classify carotid artery atherosclerotic plaque components is needed to efficiently analyze multi-weighted magnetic resonance (MR) images to allow their integration into patient risk assessment for ischemic stroke. Certain plaque components such as lipid-rich necrotic core (LRNC) with hemorrhage suggest a greater likelihood of plaque rupture and stroke event. Assessment for presence and extent of LRNC could assist in directing treatment with impact upon patient outcomes.MethodsTo address the need to accurately determine the presence and extent of plaque components on carotid plaque MRI, we proposed a two-staged deep-learning-based approach that consists of a convolutional neural network (CNN), followed by a Bayesian neural network (BNN). The rationale for the two-stage network approach is to account for the class imbalance of vessel wall and background by providing an attention mask to the BNN. A unique feature of the network training was to use ground truth defined by both high-resolution ex vivo MRI data and histopathology. More specifically, standard resolution 1.5 T in vivo MR image sets with corresponding high resolution 3.0 T ex vivo MR image sets and histopathology image sets were used to define ground-truth segmentations. Of these, data from 7 patients was used for training and from the remaining two was used for testing the proposed method. Next, to evaluate the generalizability of the method, we tested the method with an additional standard resolution 3.0 T in vivo data set of 23 patients obtained from a different scanner.ResultsOur results show that the proposed method yielded accurate segmentation of carotid atherosclerotic plaque and outperforms not only manual segmentation by trained readers, who did not have access to the ex vivo or histopathology data, but also three state-of-the-art deep-learning-based segmentation methods. Further, the proposed approach outperformed a strategy where the ground truth was generated without access to the high resolution ex vivo MRI and histopathology. The accurate performance of this method was also observed in the additional 23-patient dataset from a different scanner.ConclusionIn conclusion, the proposed method provides a mechanism to perform accurate segmentation of the carotid atherosclerotic plaque in multi-weighted MRI. Further, our study shows the advantages of using high-resolution imaging and histology to define ground truth for training deep-learning-based segmentation methods.

Project description:Background and purposeCarotid intraplaque hemorrhage is associated with stroke, plaque thickness, stenosis, ulceration, and adventitial inflammation. Conflicting data exist on whether calcification is a marker of plaque instability, and no data exist on adventitial calcification. Our goal was to determine whether adventitial calcification and soft plaque (a rim sign) help predict carotid intraplaque hemorrhage.Materials and methodsThis was a retrospective cohort study of 96 patients who underwent carotid MRA and CTA within 1 month, from 2009 to 2016. We excluded occlusions (n = 4) and near occlusions (n = 0), leaving 188 carotid arteries. Intraplaque hemorrhage was detected by using MPRAGE. Calcification, adventitial pattern, stenosis, maximum plaque thickness (total, soft, and hard), ulceration, and intraluminal thrombus on CTA were recorded. Atherosclerosis risk factors and medications were recorded. We used mixed-effects multivariable Poisson regression, accounting for 2 vessels per patient. For the final model, backward elimination was used with a threshold of P < .10. Receiver operating characteristic analysis determined intraplaque hemorrhage by using the area under the curve.ResultsOur final model included the rim sign (prevalence ratio = 11.9, P < .001) and maximum soft-plaque thickness (prevalence ratio = 1.2, P = .06). This model had excellent intraplaque hemorrhage prediction (area under the curve = 0.94), outperforming the rim sign, maximum soft-plaque thickness, NASCET stenosis, and ulceration (area under the curve = 0.88, 0.86, 0.77, and 0.63, respectively; P < .001). Addition of the rim sign performed better than each marker alone, including maximum soft-plaque thickness (area under the curve = 0.94 versus 0.86, P < .001), NASCET stenosis (area under the curve = 0.90 versus 0.77, P < .001), and ulceration (area under the curve = 0.90 versus 0.63, P < .001).ConclusionsThe CTA rim sign of adventitial calcification with internal soft plaque is highly predictive of carotid intraplaque hemorrhage.

Dataset Information

Atherosclerotic plaque component segmentation in combined carotid MRI and CTA data incorporating class label uncertainty.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets