FIGURE 6 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Comparison of velocity fields between CFD results and DL prediction. (A). Carotid stenotic artery model; (B). Carotid artery model without stenosis (cavity changed model).
Source publication
Hemodynamic prediction of carotid artery stenosis (CAS) is of great clinical significance in the diagnosis, prevention, and treatment prognosis of ischemic strokes. While computational fluid dynamics (CFD) is recognized as a useful tool, it shows a crucial issue that the high computational costs are usually required for real-time simulations of com...
Context in source publication
Context 1
... then randomly selected a preoperative model and a postoperative (cavity changed) model from the testing sets as samples to intuitively illustrate the predicted hemodynamic results in terms of pressure and velocity distributions of the maximum inflow rate (t = 0.21 s in Figure 1B) as illustrated in Figures 5, 6. It is observed that both the pressure fields ( Figure 5) and velocity fields ( Figure 6) associated with the CAS model and the normal carotid artery model (i.e., the cavity changed model) display excellent consistency between the CFD-based and DLpredicted results. ...
Citations
... Noninvasive measurements of pulse wave signals can now be easily implemented using various low-cost home electronic devices, providing helpful information for the low-cost and patient-friendly diagnosis of CVDs and relevant complications [26]. Recently, machine learning (ML) and deep learning (DL) methodologies have been employed for the analysis of pulse wave signals, demonstrating high potential and feasibility in terms of pulse wave pattern classification and cardiac function prediction [22,[27][28][29][30]. Wang et al. successfully classified 407 datasets of pulse waveforms into five patterns by developing a Bayesian network based on six pulse-waveform parameters of depth, width, length, frequency, rhythm, and intensity, achieving classification with a success rate of 84% [31]. ...
Background
Left ventricular enlargement (LVE) is a common manifestation of cardiac remodeling that is closely associated with cardiac dysfunction, heart failure (HF), and arrhythmias. This study aimed to propose a machine learning (ML)-based strategy to identify LVE in HF patients by means of pulse wave signals.
Method
We constructed two high-quality pulse wave datasets comprising a non-LVE group and an LVE group based on the 264 HF patients. Fourier series calculations were employed to determine if significant frequency differences existed between the two datasets, thereby ensuring their validity. Then, the ML-based identification was undertaken by means of classification and regression models: a weighted random forest model was employed for binary classification of the datasets, and a densely connected convolutional network was utilized to directly estimate the left ventricular diastolic diameter index (LVDdI) through regression. Finally, the accuracy of the two models was validated by comparing their results with clinical measurements, using accuracy and the area under the receiver operating characteristic curve (AUC-ROC) to assess their capability for identifying LVE patients.
Results
The classification model exhibited superior performance with an accuracy of 0.91 and an AUC-ROC of 0.93. The regression model achieved an accuracy of 0.88 and an AUC-ROC of 0.89, indicating that both models can quickly and accurately identify LVE in HF patients.
Conclusion
The proposed ML methods are verified to achieve effective classification and regression with good performance for identifying LVE in HF patients based on pulse wave signals. This study thus demonstrates the feasibility and potential of the ML-based strategy for clinical practice while offering an effective and robust tool for diagnosing and intervening ventricular remodeling.
... 4 Furthermore, a deep learning (DL) method for predicting carotid artery stenosis (CAS) demonstrated a significant reduction in computational cost while maintaining high accuracy, with DL-based predictions closely matching CFD simulations for preoperative and postoperative datasets. 5 Numerical simulations comparing non-Newtonian and Newtonian models indicated that severe stenosis (90%) could lead to critical lesions and thrombus formation, with blood shear stresses increasing up to 8.4 times. 6 In addition, even mild stenosis at the pre-bifurcation region was found to significantly increase maximum velocities in the internal carotid artery (ICA) and external carotid artery (ECA), particularly during diastole, while post-bifurcation stenosis influenced the ICA velocity profile throughout the cardiac cycle. ...
This paper presents a comprehensive model of hemodynamic pulsatile flow within the carotid artery, examining both normal conditions and those affected by stenosis. The primary focus lies in visualizing shear stress along the inner walls, aiming to elucidate how stenosis alters blood flow characteristics and subsequently impacts plaque deposition. Utilizing advanced computational fluid dynamics simulations, temporal variations in flow patterns, velocity profiles, and pressure gradients resulting from stenosis are captured, thereby elucidating the mechanical forces exerted on arterial walls. Moreover, this study analyzes the influence of hemodynamic parameters, such as Reynolds number, Womersley number, and arterial geometry, on flow disruption and stagnation points. Such insights are critical in understanding the mechanisms underlying plaque formation and progression. Critical thresholds of shear stress and flow patterns contributing to endothelial dysfunction and atherosclerotic lesion initiation are identified by comparing hemodynamic environments in healthy vs stenotic arteries. The results demonstrate significant differences in hemodynamic characteristics between stenosed and normal arteries, particularly near systolic peaks. Stenosed arteries exhibit notably higher velocities at arterial bifurcations during systole than normal arteries, indicative of altered flow dynamics. In addition, stenosis disrupts flow patterns, leading to vortex formation at locations beyond systolic peaks. Overall, findings from this research advance our understanding of cardiovascular disease pathogenesis and provide valuable insights into the hemodynamic effects of arterial stenosis.
... Stents comprise a growing industry, and along with the strong prospects for implantable medical devices overall, the stent market is recognized as an especially promising industry because of the full-fledged demographic shift toward the ageing of society and the development of information and communication technologies (Kan et al., 2021;Wang et al., 2023;Guerra and Ciurana, 2018;Guerra and Ciurana, 2019;Lee et al., 2023). ...
Purpose
The development of new advanced materials, such as photopolymerizable resins for use in stereolithography (SLA) and Ti6Al4V manufacture via selective laser melting (SLM) processes, have gained significant attention in recent years. Their accuracy, multi-material capability and application in novel fields, such as implantology, biomedical, aviation and energy industries, underscore the growing importance of these materials. The purpose of this study is oriented toward the application of new advanced materials in stent manufacturing realized by 3D printing technologies.
Design/methodology/approach
The methodology for designing personalized medical devices, implies computed tomography (CT) or magnetic resonance (MR) techniques. By realizing segmentation, reverse engineering and deriving a 3D model of a blood vessel, a subsequent stent design is achieved. The tessellation process and 3D printing methods can then be used to produce these parts. In this context, the SLA technology, in close correlation with the new types of developed resins, has brought significant evolution, as demonstrated through the analyses that are realized in the research presented in this study. This study undertakes a comprehensive approach, establishing experimentally the characteristics of two new types of photopolymerizable resins (both undoped and doped with micro-ceramic powders), remarking their great accuracy for 3D modeling in die-casting techniques, especially in the production process of customized stents.
Findings
A series of analyses were conducted, including scanning electron microscopy, energy-dispersive X-ray spectroscopy, mapping and roughness tests. Additionally, the structural integrity and molecular bonding of these resins were assessed by Fourier-transform infrared spectroscopy–attenuated total reflectance analysis. The research also explored the possibilities of using metallic alloys for producing the stents, comparing the direct manufacturing methods of stents’ struts by SLM technology using Ti6Al4V with stent models made from photopolymerizable resins using SLA. Furthermore, computer-aided engineering (CAE) simulations for two different stent struts were carried out, providing insights into the potential of using these materials and methods for realizing the production of stents.
Originality/value
This study covers advancements in materials and additive manufacturing methods but also approaches the use of CAE analysis, introducing in this way novel elements to the domain of customized stent manufacturing. The emerging applications of these resins, along with metallic alloys and 3D printing technologies, have brought significant contributions to the biomedical domain, as emphasized in this study. This study concludes by highlighting the current challenges and future research directions in the use of photopolymerizable resins and biocompatible metallic alloys, while also emphasizing the integration of artificial intelligence in the design process of customized stents by taking into consideration the 3D printing technologies that are used for producing these stents.
... Nowadays, the popularity of using machine learning algorithms has increased in the medical area as in every research area. The studies have been conducted in the detection of carotid artery diseases by machine learning techniques in the literature [12][13][14][15]. Machine learning techniques can be utilized to predict blood flow velocity in the carotid artery, considering various factors such as the geometry of the artery, blood viscosity, arterial walls mechanical properties such as elasticity modulus, Poisson ratio, and density. ...
Computational fluid dynamics (CFD) shows promise in aiding clinical methods in the early detection of atherosclerosis when combined with currently popular machine learning algorithms. In this study, fluid-structure interaction (FSI) analysis of the carotid artery was performed by creating three-dimensional patient-specific pre-operation carotid artery models of four different patients which have vessel stenosis or aneurysms. As a result of numerical simulations, the average flow velocity and average pressure of the patients at 80 specific cross-sections were obtained. The simulation results of three patients’ pre-operation were used for learning in the machine learning algorithm. The training data consists of 80% of the numerical values, while the remaining 20% is used for testing. Then, the algorithm was asked to predict the flow velocity values at different cross-sections of the artery. The values obtained as a result of learning were compared with those obtained from numerical simulation. We found the results promising in terms of guiding the clinical decisions.
... Increasing the size and concentration of the nanoparticles in the blood could be another method to improve the blood flow in a stenosed artery. 75 Artificial intelligence (AI) based strategies, such as deep learning (DL) based machine learning, can be used to predict hemodynamics pre-and post-operative hemodynamics of coronary artery stenosis, similar to what was done by Wang et al. 76 for predicting hemodynamics of carotid artery stenosis before and after surgical treatments, owing to its capability of achieving high accuracy while reducing the computational costs. ...
The estimation of pressure drop across stenotic arteries can provide valuable information about the hemodynamic features. Nevertheless, the temporal behavior of pressure in stenotic arteries is not well reported for realistic pulsatile flows. This research investigates the pressure drop across a left coronary artery model for different degrees of stenotic severity and heart rates. The zones prone to further atherogenic degeneration are identified using time-averaged wall shear stress (TAWSS) and oscillatory shear index (OSI). A unique attempt has been made to quantify the effect of stenosis severity and elevated heart rate on coronary perfusion pressure (CPP) and endocardial viability ratio (EVR), which is an indicator of myocardial oxygen supply-demand balance. We have predicted reductions in both CPP and EVR as stenosis severity increases. The aforementioned metrics exhibit a notable drop when confronted with moderate stenosis at an increased heart rate, implying that the hemodynamic consequences of moderate stenosis during an elevated heart rate may be comparable to those of severe stenosis during a state of rest. The current computational investigation has the potential to reduce the need for in vivo hemodynamic assessments of stenosis. In addition, the wall shear stress-based mechanical parameters, such as TAWSS and OSI, can indicate the atherogenic and thrombogenic regions in the stenosed vessels.
... As illustrated in Fig. 1, the parameters, i.e., LVDd, LVDs, and LAD, directly evaluate the morphological condition of the heart chamber and the heartbeat functions at systole and diastole; the LVEF quantifies the ratio of blood supply from the heart; and the SpO 2 determines the patient's blood oxygen level at the end of the blood supply as well as the supply efficiency. It has been broadly recognized that the ML methodology has powerful and feasible capabilities in robust feature extraction [33,[35][36][37][38][39]. ...
Pulse wave, as a message carrier in the cardiovascular system (CVS), enables inferring CVS conditions while diagnosing cardiovascular diseases (CVDs). Heart failure (HF) is a major CVD, typically requiring expensive and time-consuming treatments for health monitoring and disease deterioration; it would be an effective and patient-friendly tool to facilitate rapid and precise non-invasive evaluation of the heart’s blood-supply capability by means of powerful feature-abstraction capability of machine learning (ML) based on pulse wave, which remains untouched yet. Here we present an ML-based methodology, which is verified to accurately evaluate the blood-supply capability of patients with HF based on clinical data of 237 patients, enabling fast prediction of five representative cardiovascular function parameters comprising left ventricular ejection fraction (LVEF), left ventricular end-diastolic diameter (LVDd), left ventricular end-systolic diameter (LVDs), left atrial dimension (LAD), and peripheral oxygen saturation (SpO2). Two ML networks were employed and optimized based on high-quality pulse wave datasets, and they were validated consistently through statistical analysis based on the summary independent-samples t-test (p > 0.05), the Bland–Altman analysis with clinical measurements, and the error-function analysis. It is proven that evaluation of the SpO2, LAD, and LVDd performance can be achieved with the maximum error < 15%. While our findings thus demonstrate the potential of pulse wave-based, non-invasive evaluation of the blood-supply capability of patients with HF, they also set the stage for further refinements in health monitoring and deterioration prevention applications.
... A growing interest is emerging in computational fluid dynamics (CFD) to simulate blood flow inside the carotid arteries [149,150]. Indeed, the hemodynamic environment affects development as much as progression and plaque complications [77][78][79]. ...
Carotid artery stenosis is a major cause of morbidity and mortality. The journey to understanding carotid disease has developed over time and radiology has a pivotal role in diagnosis, risk stratification and therapeutic management. This paper reviews the history of diagnostic imaging in carotid disease, its evolution towards its current applications in the clinical and research fields, and the potential of new technologies to aid clinicians in identifying the disease and tailoring medical and surgical treatment.
... The presented model fills the gap, allowing for an instant preliminary hemolysis risk assessment based on non-invasive imaging methods and blood flow velocity. In addition, it can be implemented in software commonly used in hospitals, and artificial intelligence [61,[89][90][91] can be responsible for identifying narrowing areas and their geometric parameters [92,93]. ...
Atherosclerosis affects human health in many ways, leading to disability or premature death due to ischemic heart disease, stroke, or limb ischemia. Poststenotic blood flow disruption may also play an essential role in artery wall impairment linked with hemolysis related to shear stress. The maximum shear stress in the atherosclerotic plaque area is the main parameter determining hemolysis risk. In our work, a 3D internal carotid artery model was built from CT scans performed on patients qualified for percutaneous angioplasty due to its symptomatic stenosis. The obtained stenosis geometries were used to conduct a series of computer simulations to identify critical parameters corresponding to the increase in shear stress in the arteries. Stenosis shape parameters responsible for the increase in shear stress were determined. The effect of changes in the carotid artery size, length, and degree of narrowing on the change in maximum shear stress was demonstrated. Then, a correlation for the quick initial diagnosis of atherosclerotic stenoses regarding the risk of hemolysis was developed. The developed relationship for rapid hemolysis risk assessment uses information from typical non-invasive tests for treated patients. Practical guidelines have been developed regarding which stenosis shape parameters pose a risk of hemolysis, which may be adapted in medical practice.
... With the support of advanced network algorithms and powerful GPU servers, deep learning algorithms extract low-level features of datasets to travel more abstract high-level features or attribute features, so as to further perform classification and regression tasks, and it has shown more efficient performance than traditional methods in various fields. Numerous studies have explored the use of deep learning for flow fields or hemodynamics prediction, including hemodynamic parameters or clinical metrics (e.g., FFRct [21,22], local blood flow velocity, vessel cross-sectional area and blood pressure [23]), two-dimensional planar bypass flow [24,25] and even three-dimensional flow velocity and pressure fields within individualized models of patients [26][27][28]. However, these studies still suffer from shortcomings. ...
... Pi and P i represented the flow velocity or pressure value at a certain point calculated by CFD and deep learning, respectively. The authors' previous work demonstrated that MRE was the stable evaluation indicator that had clear physical meaning and was easy to understand [26,29,31]. And it was used and supported by a large number of studies as well [50][51][52]. ...
Hemodynamic parameters are of great significance in the clinical diagnosis and treatment of cardiovascular diseases. However, noninvasive, real-time and accurate acquisition of hemodynamics remains a challenge for current invasive detection and simulation algorithms. Here, we integrate computational fluid dynamics with our customized analysis framework based on a multi-attribute point cloud dataset and physics-informed neural networks (PINNs)-aided deep learning modules. This combination is implemented by our workflow that generates flow field datasets within two types of patient personalized models - aorta with fine coronary branches and abdominal aorta. Deep learning modules with or without an antecedent hierarchical structure model the flow field development and complete the mapping from spatial and temporal dimensions to 4D hemodynamics. 88,000 cases on 4 randomized partitions in 16 controlled trials reveal the hemodynamic landscape of spatio-temporal anisotropy within two types of personalized models, which demonstrates the effectiveness of PINN in predicting the space-time behavior of flow fields and gives the optimal deep learning framework for different blood vessels in terms of balancing the training cost and accuracy dimensions. The proposed framework shows intentional performance in computational cost, accuracy and visualization compared to currently prevalent methods, and has the potential for generalization to model flow fields and corresponding clinical metrics within vessels at different locations. We expect our framework to push the 4D hemodynamic predictions to the real-time level, and in statistically significant fashion, applicable to morphologically variable vessels.
