Automated segmentation of carotid lumen-intima boundary (LIB) and media-adventitia boundary (MAB) by deep convolutional neural networks (CNN) from three-dimensional ultrasound (3DUS) images has made ...assessment and monitoring of carotid atherosclerosis more efficient than manual segmentation. However, training of CNN still requires manual segmentation of LIB and MAB. Therefore, there is a need to improve the efficiency of manual segmentation and develop strategies to improve segmentation accuracy by the CNN for serial monitoring of carotid atherosclerosis. One strategy to reduce segmentation time is to increase the interslice distance (ISD) between segmented axial slices of a 3DUS image while maintaining the segmentation reliability. We, for the first time, investigated the effect of ISD on the reproducibility of MAB and LIB segmentations. The intra-observer reproducibility of LIB and MAB segmentations at ISDs of 1 mm and 2 mm was not statistically significantly different, whereas the reproducibility at ISD = 3 mm was statistically lower. Therefore, we conclude that segmentation with an ISD of 2 mm provides sufficient reliability for CNN training. We further proposed training the CNN by the baseline images of the entire cohort of patients for automatic segmentation of the follow-up images acquired for the same cohort. We validated that segmentation with this time-based partitioning approach is more accurate than that produced by patient-based partitioning, especially at the carotid bifurcation. This study forms the basis for an efficient, reproducible, and accurate 3DUS workflow for serial monitoring of carotid atherosclerosis useful in risk stratification of cardiovascular events and in evaluating the efficacy of new treatments.
Segmentation of the carotid section encompassing the common carotid artery (CCA), the bifurcation and the internal carotid artery (ICA) from three-dimensional ultrasound (3DUS) is required to measure ...the vessel wall volume (VWV) and localized vessel-wall-plus-plaque thickness (VWT), shown to be sensitive to treatment effect. We proposed an approach to combine a centerline extraction network (CHG-Net) and a dual-stream centerline-guided network (DSCG-Net) to segment the lumen-intima (LIB) and media-adventitia boundaries (MAB) from 3DUS images. Correct arterial location is essential for successful segmentation of the carotid section encompassing the bifurcation. We addressed this challenge by using the arterial centerline to enhance the localization accuracy of the segmentation network. The CHG-Net was developed to generate a heatmap indicating high probability regions for the centerline location, which was then integrated with the 3DUS image by the DSCG-Net to generate the MAB and LIB. The DSCG-Net includes a scale-based and a spatial attention mechanism to fuse multi-level features extracted by the encoder, and a centerline heatmap reconstruction side-branch connected to the end of the encoder to increase the generalization ability of the network. Experiments involving 224 3DUS volumes produce a Dice similarity coefficient (DSC) of 95.8±1.9% and 92.3±5.4% for CCA MAB and LIB, respectively, and 93.2±4.4% and 89.0±10.0% for ICA MAB and LIB, respectively. Our approach outperformed four state-of-the-art 3D CNN models, even after their performances were boosted by centerline guidance. The efficiency afforded by the framework would allow it to be incorporated into the clinical workflow for improved quantification of plaque change.
Quantitative measurements of carotid plaque burden progression or regression are important in monitoring patients and in evaluation of new treatment options. 3D ultrasound (US) has been used to ...monitor the progression or regression of carotid artery plaques. This paper reports on the development and application of a method used to analyze changes in carotid plaque morphology from 3D US. The technique used is evaluated using manual segmentations of the arterial wall and lumen from 3D US images acquired in two imaging sessions. To reduce the effect of segmentation variability, segmentation was performed five times each for the wall and lumen. The mean wall and lumen surfaces, computed from this set of five segmentations, were matched on a point-by-point basis, and the distance between each pair of corresponding points served as an estimate of the combined thickness of the plaque, intima, and media (vessel-wall-plus-plaque thickness or VWT). The VWT maps associated with the first and the second US images were compared and the differences of VWT were obtained at each vertex. The 3D VWT and VWT-Change maps may provide important information for evaluating the location of plaque progression in relation to the localized disturbances of flow pattern, such as oscillatory shear, and regression in response to medical treatments.
Both optical tweezers and acoustic tweezers have been demonstrated for trapping small particles in diverse biomedical applications. Compared to the optical tweezers, acoustic tweezers have deeper ...penetration, lower intensity, and are more useful in light opaque media. These advantages enable the potential utility of acoustic tweezers in biological science. Since the first demonstration of acoustic tweezers, various applications have required the trapping of not only one, but more particles simultaneously in both the axial and lateral direction. In this research, a method is proposed to create multiple trapping patterns, to prove the feasibility of trapping micro-particles. It has potential ability to electronically control the location and movement of the particles in real-time. A multiple-focus acoustic field can be generated by controlling the excitation of the transducer elements. The pressure and intensity of the field are obtained by modeling phased array transducer. Moreover, scattering force and gradient force at various positions are also evaluated to analyze their relative components to the effect of the acoustic tweezers. Besides, the axial and lateral radiation force and the trapping trajectory are computed based on ray acoustic approach. The results obtained demonstrate that the acoustic tweezers are capable of multiple trapping in both the axial and lateral directions.
Purpose
Vessel wall volume (VWV) and localized vessel‐wall‐plus‐plaque thickness (VWT) measured from three‐dimensional (3D) ultrasound (US) carotid images are sensitive to anti‐atherosclerotic ...effects of medical/dietary treatments. VWV and VWT measurements require the lumen‐intima (LIB) and media‐adventitia boundaries (MAB) at the common and internal carotid arteries (CCA and ICA). However, most existing segmentation techniques were capable of segmenting the CCA only. An approach capable of segmenting the MAB and LIB from the CCA and ICA was required to accelerate VWV and VWT quantification.
Methods
Segmentation for CCA and ICA was performed independently using the proposed two‐channel U‐Net, which was driven by a novel loss function known as the adaptive triple Dice loss (ADTL) function. The training set was augmented by interpolating manual segmentation along the longitudinal direction, thereby taking continuity of the artery into account. A test‐time augmentation (TTA) approach was applied, in which segmentation was performed three times based on the input axial images and its flipped versions; the final segmentation was generated by pixel‐wise majority voting.
Results
Experiments involving 224 3DUS volumes produce a Dice similarity coefficient (DSC) of 95.1% ± 4.1% and 91.6% ± 6.6% for the MAB and LIB, in the CCA, respectively, and 94.2% ± 3.3% and 89.0% ± 8.1% for the MAB and LIB, in the ICA, respectively. TTA and ATDL independently contributed to a statistically significant improvement to all boundaries except the LIB in ICA.
Conclusions
The proposed two‐channel U‐Net with ADTL and TTA can segment the CCA and ICA accurately and efficiently from the 3DUS volume. Our approach has the potential to accelerate the transition of 3DUS measurements of carotid atherosclerosis to clinical research.
Purpose:
The previously described 2D standardized vessel-wall-plus-plaque thickness (VWT) maps constructed from 3D ultrasound vessel wall measurements using an arc-length (AL) scaling approach ...adjusted the geometric variability of carotid arteries and has allowed for the comparisons of VWT distributions in longitudinal and cross-sectional studies. However, this mapping technique did not optimize point correspondence of the carotid arteries investigated. The potential misalignment may lead to errors in point-wise VWT comparisons. In this paper, we developed and validated an algorithm based on steepest description length (DL) descent to optimize the point correspondence implied by the 2D VWT maps.
Methods:
The previously described AL approach was applied to obtain initial 2D maps for a group of carotid arteries. The 2D maps were reparameterized based on an iterative steepest DL descent approach, which consists of the following two steps. First, landmarks established by resampling the 2D maps were aligned using the Procrustes algorithm. Then, the gradient of the DL with respect to horizontal and vertical reparameterizations of each landmark on the 2D maps was computed, and the 2D maps were subsequently deformed in the direction of the steepest descent of DL. These two steps were repeated until convergence. The quality of the correspondence was evaluated in a phantom study and an in vivo study involving ten carotid arteries enrolled in a 3D ultrasound interscan variability study. The correspondence quality was evaluated in terms of the compactness and generalization ability of the statistical shape model built based on the established point correspondence in both studies. In the in vivo study, the effect of the proposed algorithm on interscan variability of VWT measurements was evaluated by comparing the percentage of landmarks with statistically significant VWT-change before and after point correspondence optimization.
Results:
The statistical shape model constructed with optimized correspondence was more compact and had a better generalization ability than that constructed using the AL approach in both the phantom and in vivo studies. A statistical test on the group-average VWT-Change at each point of the 2D carotid template showed that the group-average VWT-change was significantly different from 0 in 18% of landmarks when the AL approach was used, and this percentage was reduced to 11% after correspondence optimization.
Conclusions:
The optimized correspondence resulted in a more compact and generalizable statistical shape model, and the algorithm was shown to reduce interscan variability of point-wise VWT measurements obtained using the previously described arc-length scaling parameterization approach.
While three-dimensional (3D) late gadolinium-enhanced (LGE) magnetic resonance (MR) imaging provides good conspicuity of small myocardial lesions with short acquisition time, it poses a challenge for ...image analysis as a large number of axial images are required to be segmented. We developed a fully automatic convolutional neural network (CNN) called cascaded triplanar autoencoder M-Net (CTAEM-Net) to segment myocardial scar from 3D LGE MRI. Two sub-networks were cascaded to segment the left ventricle (LV) myocardium and then the scar within the pre-segmented LV myocardium. Each sub-network contains three autoencoder M-Nets (AEM-Nets) segmenting the axial, sagittal and coronal slices of the 3D LGE MR image, with the final segmentation determined by voting. The AEM-Net integrates three features: (1) multi-scale inputs, (2) deep supervision and (3) multi-tasking. The multi-scale inputs allow consideration of the global and local features in segmentation. Deep supervision provides direct supervision to deeper layers and facilitates CNN convergence. Multi-task learning reduces segmentation overfitting by acquiring additional information from autoencoder reconstruction, a task closely related to segmentation. The framework provides an accuracy of 86.43% and 90.18% for LV myocardium and scar segmentation, respectively, which are the highest among existing methods to our knowledge. The time required for CTAEM-Net to segment LV myocardium and the scar was 49.72 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 9.69s and 120.25 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 23.18s per MR volume, respectively. The accuracy and efficiency afforded by CTAEM-Net will make possible future large population studies. The generalizability of the framework was also demonstrated by its competitive performance in two publicly available datasets of different imaging modalities.
The large amount of data available in the modern big data era opens new opportunities to expand our knowledge by integrating information from heterogeneous sources. Multiview learning has recently ...achieved tremendous success in deriving complementary information from multiple data modalities. This article proposes a framework called multiview latent space projection (MVLSP) to integrate features extracted from multiple sources in a discriminative way to facilitate binary and multiclass classifications. Our approach is associated with three innovations. First, most existing multiview learning algorithms promote pairwise consistency between two views and do not have a natural extension to applications with more than two views. MVLSP finds optimum mappings from a common latent space to match the feature space in each of the views. As the matching is performed on a view-by-view basis, the framework can be readily extended to multiview applications. Second, feature selection in the common latent space can be readily achieved by adding a class view, which matches the latent space representations of training samples with their corresponding labels. Then, high-order view correlations are extracted by considering feature-label correlations. Third, a technique is proposed to optimize the integration of different latent patterns based on their correlations. The experimental results on the prostate image dataset demonstrate the effectiveness of the proposed method.
We developed a new method to measure the voxel-based vessel-wall-plus-plaque volume (VWV). In addition to quantifying local thickness change as in the previously introduced vessel-wall-plus-plaque ...thickness (VWT) metric, voxel-based VWV further considers the circumferential change associated with vascular remodeling. Three-dimensional ultrasound images were acquired at baseline and 1 y afterward. The vessel wall region was divided into small voxels with the voxel-based VWV change (ΔVVol%) computed by taking the percentage volume difference between corresponding voxels in the baseline and follow-up images. A 3-D carotid atlas was developed to allow visualization of the local thickness and circumferential change patterns in the pomegranate versus the placebo groups. A new patient-based biomarker was obtained by computing the mean ΔVVol% over the entire 3-D map for each patient (ΔVVol%¯). ΔVVol%¯ detected a significant difference between patients randomized to pomegranate juice/extract and placebo groups (p = 0.0002). The number of patients required by ΔVVol%¯ to establish statistical significance was approximately a third of that required by the local VWT biomarker. The increased sensitivity afforded by the proposed biomarker improves the cost-effectiveness of clinical studies evaluating new anti-atherosclerotic treatments.
PDF
