Unsupervised deep learning-based displacement estimation for vascular elasticity imaging applications.

Objective. Arterial wall stiffness can provide valuable information on the proper function of the cardiovascular system. Ultrasound elasticity imaging techniques have shown great promise as a low-cost and non-invasive tool to enable localized maps of arterial wall stiffness. Such techniques rely upon motion detection algorithms that provide arterial wall displacement estimation.Approach. In this study, we propose an unsupervised deep learning-based approach, originally proposed for image registration, in order to enable improved quality arterial wall displacement estimation at high temporal and spatial resolutions. The performance of the proposed network was assessed through phantom experiments, where various models were trained by using ultrasound RF signals, or B-mode images, as well as different loss functions.Main results. Using the mean square error (MSE) for the training process provided the highest signal-to-noise ratio when training on the B-modes images (30.36 ± 1.14 dB) and highest contrast-to-noise ratio when training on the RF signals (32.84 ± 1.89 dB). In addition, training the model on RF signals demonstrated the capability of providing accurate localized pulse wave velocity (PWV) maps, with a mean relative error (MREPWV) of 3.32 ± 1.80% and anR2 of 0.97 ± 0.03. Finally, the developed model was tested in human common carotid arteriesin vivo, providing accurate tracking of the distension pulse wave propagation, with an MREPWV= 3.86 ± 2.69% andR2 = 0.95 ± 0.03.Significance. In conclusion, a novel displacement estimation approach was presented, showing promise in improving vascular elasticity imaging techniques.

Pulse wave and vector flow Imaging for atherosclerotic disease progression in hypercholesterolemic swine.

Non-invasive monitoring of atherosclerosis remains challenging. Pulse Wave Imaging (PWI) is a non-invasive technique to measure the local stiffness at diastolic and end-systolic pressures and quantify the hemodynamics. The objective of this study is twofold, namely (1) to investigate the capability of (adaptive) PWI to assess progressive change in local stiffness and homogeneity of the carotid in a high-cholesterol swine model and (2) to assess the ability of PWI to monitor the change in hemodynamics and a corresponding change in stiffness. Nine (n=9) hypercholesterolemic swine were included in this study and followed for up to 9 months. A ligation in the left carotid was used to cause a hemodynamic disturbance. The carotids with detectable hemodynamic disturbance showed a reduction in wall shear stress immediately after ligation (2.12 ± 0.49 to 0.98 ± 0.47 Pa for 40-90% ligation (Group B) and 1.82 ± 0.25 to 0.49 ± 0.46 Pa for >90% ligation (Group C)). Histology revealed subsequent lesion formation after 8-9 months, and the type of lesion formation was dependent on the type of the induced ligation, with more complex plaques observed in the carotids with a more significant ligation (C: >90%). The compliance progression appears differed for groups B and C, with an increase in compliance to 2.09 ± 2.90×10-10 m2 Pa-1 for group C whereas the compliance of group B remained low at 8 months (0.95 ± 0.94×10-10 m2 Pa-1). In summary, PWI appeared capable of monitoring a change in wall shear stress and separating two distinct progression pathways resulting in distinct compliances.

Pulse wave imaging of a stenotic artery model with plaque constituents of different stiffnesses: Experimental demonstration in phantoms and fluid-structure interaction simulation.

Vulnerable plaques associated with softer components may rupture, releasing thrombotic emboli to smaller vessels in the brain, thus causing an ischemic stroke. Pulse Wave Imaging (PWI) is an ultrasound-based method that allows for pulse wave visualization while the regional pulse wave velocity (PWV) is mapped along the arterial wall to infer the underlying wall compliance. One potential application of PWI is the non-invasive estimation of plaque's mechanical properties for investigating its vulnerability. In this study, the accuracy of PWV estimation in stenotic vessels was investigated by computational simulation and PWI in validation phantoms to evaluate this modality for assessing future stroke risk. Polyvinyl alcohol (PVA) phantoms with plaque constituents of different stiffnesses were designed and constructed to emulate stenotic arteries in the experiment, and the novel fabrication process was described. Finite-element fluid-structure interaction simulations were performed in a stenotic phantom model that matched the geometry and parameters of the experiment in phantoms. The peak distension acceleration of the phantom wall was tracked to estimate PWV. PWVs of 2.57 ms-1, 3.41 ms-1, and 4.48 ms-1 were respectively obtained in the soft, intermediate, and stiff plaque material in phantoms during the experiment using PWI. PWVs of 2.10 ms-1, 3.33 ms-1, and 4.02 ms-1 were respectively found in the soft, intermediate, and stiff plaque material in the computational simulation. These results demonstrate that PWI can effectively distinguish the mechanical properties of plaque in phantoms as compared to computational simulation.

Adaptive Wall Shear Stress Imaging in Phantoms, Simulations and In Vivo.

WSS measurement is challenging since it requires sensitive flow measurements at a distance close to the wall. The aim of this study is to develop an ultrasound imaging technique which combines vector flow imaging with an unsupervised data clustering approach that automatically detects the region close to the wall with optimally linear flow profile, to provide direct and robust WSS estimation. The proposed technique was evaluated in phantoms, mimicking normal and atherosclerotic vessels, and spatially registered Fluid Structure Interaction (FSI) simulations. A relative error of 6.7% and 19.8% was obtained for peak systolic (WSSPS) and end diastolic (WSSED) WSS in the straight phantom, while in the stenotic phantom, a good similarity was found between measured and simulated WSS distribution, with a correlation coefficient, R, of 0.89 and 0.85 for WSSPS and WSSED, respectively. Moreover, the feasibility of the technique to detect pre-clinical atherosclerosis was tested in an atherosclerotic swine model. Six swines were fed atherogenic diet, while their left carotid artery was ligated in order to disturb flow patterns. Ligated arterial segments that were exposed to low WSSPS and WSS characterized by high frequency oscillations at baseline, developed either moderately or highly stenotic plaques (p < 0.05). Finally, feasibility of the technique was demonstrated in normal and atherosclerotic human subjects. Atherosclerotic carotid arteries with low stenosis had lower WSSPS as compared to control subjects (p < 0.01), while in one subject with high stenosis, elevated WSS was found on an arterial segment, which coincided with plaque rupture site, as determined through histological examination.

Deep learning-based automated pipeline for blood vessel detection and distribution analysis in multiplexed prostate cancer images.

Introduction: Prostate cancer is a highly heterogeneous disease, presenting varying levels of aggressiveness and response to treatment. Angiogenesis is one of the hallmarks of cancer, providing oxygen and nutrient supply to tumors. Micro vessel density has previously been correlated with higher Gleason score and poor prognosis. Manual segmentation of blood vessels (BVs) In microscopy images is challenging, time consuming and may be prone to inter-rater variabilities. In this study, an automated pipeline is presented for BV detection and distribution analysis in multiplexed prostate cancer images. Methods: A deep learning model was trained to segment BVs by combining CD31, CD34 and collagen IV images. In addition, the trained model was used to analyze the size and distribution patterns of BVs in relation to disease progression in a cohort of prostate cancer patients (N = 215). Results: The model was capable of accurately detecting and segmenting BVs, as compared to ground truth annotations provided by two reviewers. The precision (P), recall (R) and dice similarity coefficient (DSC) were equal to 0.93 (SD 0.04), 0.97 (SD 0.02) and 0.71 (SD 0.07) with respect to reviewer 1, and 0.95 (SD 0.05), 0.94 (SD 0.07) and 0.70 (SD 0.08) with respect to reviewer 2, respectively. BV count was significantly associated with 5-year recurrence (adjusted p = 0.0042), while both count and area of blood vessel were significantly associated with Gleason grade (adjusted p = 0.032 and 0.003 respectively). Discussion: The proposed methodology is anticipated to streamline and standardize BV analysis, offering additional insights into the biology of prostate cancer, with broad applicability to other cancers.

Modeling Pulse Wave Propagation Through a Stenotic Artery With Fluid Structure Interaction: A Validation Study Using Ultrasound Pulse Wave Imaging.

Pulse wave imaging (PWI) is an ultrasound-based method that allows spatiotemporal mapping of the arterial pulse wave propagation, from which the local pulse wave velocity (PWV) can be derived. Recent reports indicate that PWI can help the assessment of atherosclerotic plaque composition and mechanical properties. However, the effect of the atherosclerotic plaque's geometry and mechanics on the arterial wall distension and local PWV remains unclear. In this study, we investigated the accuracy of a finite element (FE) fluid-structure interaction (FSI) approach to predict the velocity of a pulse wave propagating through a stenotic artery with an asymmetrical plaque, as quantified with PWI method. Experiments were designed to compare FE-FSI modeling of the pulse wave propagation through a stenotic artery against PWI obtained with manufactured phantom arteries made of polyvinyl alcohol (PVA) material. FSI-generated spatiotemporal maps were used to estimate PWV at the plaque region and compared it to the experimental results. Velocity of the pulse wave propagation and magnitude of the wall distension were correctly predicted with the FE analysis. In addition, findings indicate that a plaque with a high degree of stenosis (>70%) attenuates the propagation of the pulse pressure wave. Results of this study support the validity of the FE-FSI methods to investigate the effect of arterial wall structural and mechanical properties on the pulse wave propagation. This modeling method can help to guide the optimization of PWI to characterize plaque properties and substantiate clinical findings.

Adaptive Pulse Wave Imaging: Automated Spatial Vessel Wall Inhomogeneity Detection in Phantoms and in-Vivo.

Imaging arterial mechanical properties may improve vascular disease diagnosis. Pulse wave velocity (PWV) is a marker of arterial stiffness linked to cardio-vascular mortality. Pulse wave imaging (PWI) is a technique for imaging the pulse wave propagation at high spatial and temporal resolution. In this paper, we introduce adaptive PWI, a technique for the automated partition of heterogeneous arteries into individual segments characterized by most homogeneous pulse wave propagation, allowing for more robust PWV estimation. This technique was validated in a silicone phantom with a soft-stiff interface. The mean detection error of the interface was 4.67 ± 0.73 mm and 3.64 ± 0.14 mm in the stiff-to-soft and soft-to-stiff pulse wave transmission direction, respectively. This technique was tested in monitoring the progression of atherosclerosis in mouse aortas in vivo ( n = 11 ). The PWV was found to already increase at the early stage of 10 weeks of high-fat diet (3.17 ± 0.67 m/sec compared to baseline 2.55 ± 0.47 m/sec, ) and further increase after 20 weeks of high-fat diet (3.76±1.20 m/sec). The number of detected segments of the imaged aortas monotonically increased with the duration of high-fat diet indicating an increase in arterial wall property inhomogeneity. The performance of adaptive PWI was also tested in aneurysmal mouse aortas in vivo. Aneurysmal boundaries were detected with a mean error of 0.68±0.44 mm. Finally, initial feasibility was shown in the carotid arteries of healthy and atherosclerotic human subjects in vivo ( n = 3 each). Consequently, adaptive PWI was successful in detecting stiffness inhomogeneity at its early onset and monitoring atherosclerosis progression in vivo.

Arterial wall mechanical inhomogeneity detection and atherosclerotic plaque characterization using high frame rate pulse wave imaging in carotid artery disease patients in vivo.

Pulse wave imaging (PWI) is a non-invasive, ultrasound-based technique, which provides information on arterial wall stiffness by estimating the pulse wave velocity (PWV) along an imaged arterial wall segment. The aims of the present study were to: (1) utilize the PWI information to automatically and optimally divide the artery into the segments with most homogeneous properties and (2) assess the feasibility of this method to provide arterial wall mechanical characterization in normal and atherosclerotic carotid arteries in vivo. A silicone phantom consisting of a soft and stiff segment along its longitudinal axis was scanned at the stiffness transition, and the PWV in each segment was estimated through static testing. The proposed algorithm detected the stiffness interface with an average error of 0.98 ± 0.49 mm and 1.04 ± 0.27 mm in the soft-to-stiff and stiff-to-soft pulse wave transmission direction, respectively. Mean PWVs estimated in the case of the soft-to-stiff pulse wave transmission direction were 2.47 [Formula: see text] 0.04 m s-1 and 3.43 [Formula: see text] 0.08 m s-1 for the soft and stiff phantom segments, respectively, while in the case of stiff-to-soft transmission direction PWVs were 2.60 [Formula: see text] 0.18 m s-1 and 3.72 [Formula: see text] 0.08 m s-1 for the soft and stiff phantom segments, respectively, which were in good agreement with the PWVs obtained through static testing (soft segment: 2.41 m s-1, stiff segment: 3.52 m s-1). Furthermore, the carotid arteries of N = 9 young subjects (22-32 y.o.) and N = 9 elderly subjects (60-73 y.o.) with no prior history of carotid artery disease were scanned, in vivo, as well as the atherosclerotic carotid arteries of N = 12 (59-85 y.o.) carotid artery disease patients. One-way ANOVA with Holm-Sidak correction showed that the number of most homogeneous segments in which the artery was divided was significantly higher in the case of carotid artery disease patients compared to young (3.25 [Formula: see text] 0.86 segments versus 1.00 [Formula: see text] 0.00 segments, p -value < 0.0001) and elderly non-atherosclerotic subjects (3.25 [Formula: see text] 0.86 segments versus 1.44 [Formula: see text] 0.51 segments p -value < 0.0001), indicating increased wall inhomogeneity in atherosclerotic arteries. The compliance provided by the proposed algorithm was significantly higher in non-calcified/high-lipid plaques as compared with calcified plaques (3.35 [Formula: see text] 2.45 *[Formula: see text] versus 0.22 [Formula: see text] 0.18 * [Formula: see text], p -value < 0.01) and the compliance estimated in elderly subjects (3.35 [Formula: see text] 2.45 * [Formula: see text] versus 0.79 [Formula: see text] 0.30 * [Formula: see text], p -value < 0.01). Moreover, lower compliance was estimated in cases where vulnerable plaque characteristics were present (i.e. necrotic lipid core, thrombus), compared to stable plaque components (calcification), as evaluated through plaque histological examination. The proposed algorithm was thus capable of evaluating arterial wall inhomogeneity and characterize wall mechanical properties, showing promise in vascular disease diagnosis and monitoring.