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.

Model-based cap thickness and peak cap stress prediction for carotid MRI

A rupture-prone carotid plaque can potentially be identified by calculating the peak cap stress (PCS). For these calculations, plaque geometry from MRI is often used. Unfortunately, MRI is hampered by a low resolution, leading to an overestimation of cap thickness and an underestimation of PCS. We developed a model to reconstruct the cap based on plaque geometry to better predict cap thickness and PCS. We used histological stained plaques from 34 patients. These plaques were segmented and served as the ground truth. Sections of these plaques contained 93 necrotic cores with a cap thickness <0.62mm which were used to generate a geometry-based model. The histological data was used to simulate in vivo MRI images, which were manually delineated by three experienced MRI readers. Caps below the MRI resolution (n=31) were (digitally removed and) reconstructed according to the geometry-based model. Cap thickness and PCS were determined for the ground truth, readers, and reconstructed geometries. Cap thickness was 0.07mm for the ground truth, 0.23mm for the readers, and 0.12mm for the reconstructed geometries. The model predicts cap thickness significantly better than the readers. PCS was 464kPa for the ground truth, 262kPa for the readers and 384kPa for the reconstructed geometries. The model did not predict the PCS significantly better than the readers. The geometry-based model provided a significant improvement for cap thickness estimation and can potentially help in rupture-risk prediction, solely based on cap thickness. Estimation of PCS estimation did not improve, probably due to the complex shape of the plaques.

Carotid plaque elasticity estimation using ultrasound elastography, MRI, and inverse FEA - A numerical feasibility study

The material properties of atherosclerotic plaques govern the biomechanical environment, which is associated with rupture-risk. We investigated the feasibility of noninvasively estimating carotid plaque component material properties through simulating ultrasound (US) elastography and in vivo magnetic resonance imaging (MRI), and solving the inverse problem with finite element analysis. 2D plaque models were derived from endarterectomy specimens of nine patients. Nonlinear neo-Hookean models (tissue elasticity C1) were assigned to fibrous intima, wall (i.e., media/adventitia), and lipid-rich necrotic core. Finite element analysis was used to simulate clinical cross-sectional US strain imaging. Computer-simulated, single-slice in vivo MR images were segmented by two MR readers. We investigated multiple scenarios for plaque model elasticity, and consistently found clear separations between estimated tissue elasticity values. The intima C1 (160 kPa scenario) was estimated as 125.8 ± 19.4 kPa (reader 1) and 128.9 ± 24.8 kPa (reader 2). The lipid-rich necrotic core C1 (5 kPa) was estimated as 5.6 ± 2.0 kPa (reader 1) and 8.5 ± 4.5 kPa (reader 2). A scenario with a stiffer wall yielded similar results, while realistic US strain noise and rotating the models had little influence, thus demonstrating robustness of the procedure. The promising findings of this computer-simulation study stimulate applying the proposed methodology in a clinical setting.

Carotid Plaque Morphological Classification Compared With Biomechanical Cap Stress: Implications for a Magnetic Resonance Imaging-Based Assessment

BACKGROUND AND PURPOSE

Two approaches to target plaque vulnerability-a histopathologic classification scheme and a biomechanical analysis-were compared and the implications for noninvasive risk stratification of carotid plaques using magnetic resonance imaging were assessed.

METHODS

Seventy-five histological plaque cross sections were obtained from carotid endarterectomy specimens from 34 patients (>70% stenosis) and subjected to both a Virmani histopathologic classification (thin fibrous cap atheroma with <0.2-mm cap thickness, presumed vulnerable) and a peak cap stress computation (<140 kPa: presumed stable; >300 kPa: presumed vulnerable). To demonstrate the implications for noninvasive plaque assessment, numeric simulations of a typical carotid magnetic resonance imaging protocol were performed (0.62×0.62 mm(2) in-plane acquired voxel size) and used to obtain the magnetic resonance imaging-based peak cap stress.

RESULTS

Peak cap stress was generally associated with histological classification. However, only 16 of 25 plaque cross sections could be labeled as high-risk (peak cap stress>300 kPa and classified as a thin fibrous cap atheroma). Twenty-eight of 50 plaque cross sections could be labeled as low-risk (a peak cap stress<140 kPa and not a thin fibrous cap atheroma), leading to a κ=0.39. 31 plaques (41%) had a disagreement between both classifications. Because of the limited magnetic resonance imaging voxel size with regard to cap thickness, a noninvasive identification of only a group of low-risk, thick-cap plaques was reliable.

CONCLUSIONS

Instead of trying to target only vulnerable plaques, a more reliable noninvasive identification of a select group of stable plaques with a thick cap and low stress might be a more fruitful approach to start reducing surgical interventions on carotid plaques.

A computer-simulation study on the effects of MRI voxel dimensions on carotid plaque lipid-core and fibrous cap segmentation and stress modeling

Background

The benefits of a decreased slice thickness and/or in-plane voxel size in carotid MRI for atherosclerotic plaque component quantification accuracy and biomechanical peak cap stress analysis have not yet been investigated in detail because of practical limitations.

Methods

In order to provide a methodology that allows such an investigation in detail, numerical simulations of a T1-weighted, contrast-enhanced, 2D MRI sequence were employed. Both the slice thickness (2 mm, 1 mm, and 0.5 mm) and the in plane acquired voxel size (0.62x0.62 mm² and 0.31x0.31 mm²) were varied. This virtual MRI approach was applied to 8 histology-based 3D patient carotid atherosclerotic plaque models.

Results

A decreased slice thickness did not result in major improvements in lumen, vessel wall, and lipid-rich necrotic core size measurements. At 0.62x0.62 mm² in-plane, only a 0.5 mm slice thickness resulted in improved minimum fibrous cap thickness measurements (a 2–3 fold reduction in measurement error) and only marginally improved peak cap stress computations. Acquiring voxels of 0.31x0.31 mm² in-plane, however, led to either similar or significantly larger improvements in plaque component quantification and computed peak cap stress.

Conclusions

This study provides evidence that for currently-used 2D carotid MRI protocols, a decreased slice thickness might not be more beneficial for plaque measurement accuracy than a decreased in-plane voxel size. The MRI simulations performed indicate that not a reduced slice thickness (i.e. more isotropic imaging), but the acquisition of anisotropic voxels with a relatively smaller in-plane voxel size could improve carotid plaque quantification and computed peak cap stress accuracy.