WSSNet: Aortic Wall Shear Stress Estimation Using Deep Learning on 4D Flow MRI

Rapid prediction of wall shear stress in stenosed coronary arteries based on deep learning

There is increasing evidence that coronary artery wall shear stress (WSS) measurement provides useful prognostic information that allows prediction of adverse cardiovascular events. Computational Fluid Dynamics (CFD) has been extensively used in research to measure vessel physiology and examine the role of the local haemodynamic forces on the evolution of atherosclerosis. Nonetheless, CFD modelling remains computationally expensive and time-consuming, making its direct use in clinical practice inconvenient. A number of studies have investigated the use of deep learning (DL) approaches for fast WSS prediction. However, in these reports, patient data were limited and most of them used synthetic data generation methods for developing the training set. In this paper, we implement 2 approaches for synthetic data generation and combine their output with real patient data in order to train a DL model with a U-net architecture for prediction of WSS in the coronary arteries. The model achieved 6.03% Normalised Mean Absolute Error (NMAE) with inference taking only 0.35 s; making this solution time-efficient and clinically relevant.

How to improve epidemiological trustworthiness concerning abdominal aortic aneurysms

BACKGROUND

Research on degenerative abdominal aortic aneurysms (AAA) is hampered by complex pathophysiology, sub-optimal pre-clinical models, and lack of effective medical therapies. In addition, trustworthiness of existing epidemiological data is impaired by elements of ambiguity, inaccuracy, and inconsistency. Our aim is to foster debate concerning the trustworthiness of AAA epidemiological data and to discuss potential solutions.

METHODS

We searched the literature from the last five decades for relevant epidemiological data concerning AAA development, rupture, and repair. We then discussed the main issues burdening existing AAA epidemiological figures and proposed suggestions potentially beneficial to AAA diagnosis, prognostication, and management.

RESULTS

Recent data suggest a heterogeneous scenario concerning AAA epidemiology with rates markedly varying by country and study cohorts. Overall, AAA prevalence seems to be decreasing worldwide while mortality is apparently increasing regardless of recent improvements in aortic-repair techniques. Prevalence and mortality are decreasing in high-income countries, whereas low-income countries show an increase in both. However, several pieces of information are missing or outdated, thus systematic renewal is necessary. Current AAA definition and surgical criteria do not consider inter-individual variability of baseline aortic size, further decreasing their reliability.

CONCLUSIONS

Switching from flat aortic-size thresholds to relative aortic indices would improve epidemiological trustworthiness regarding AAAs. Aortometry standardization focusing on simplicity, univocity, and accuracy is crucial. A patient-tailored approach integrating clinical data, multi-adjusted indices, and imaging parameters is desirable. Several novel imaging modalities boast promising profiles for investigating the aortic wall. New contrast agents, computational analyses, and artificial intelligence-powered software could provide further improvements.

Mesh neural networks for SE(3)-equivariant hemodynamics estimation on the artery wall

Computational fluid dynamics (CFD) is a valuable asset for patient-specific cardiovascular-disease diagnosis and prognosis, but its high computational demands hamper its adoption in practice. Machine-learning methods that estimate blood flow in individual patients could accelerate or replace CFD simulation to overcome these limitations. In this work, we consider the estimation of vector-valued quantities on the wall of three-dimensional geometric artery models. We employ group-equivariant graph convolution in an end-to-end SE(3)-equivariant neural network that operates directly on triangular surface meshes and makes efficient use of training data. We run experiments on a large dataset of synthetic coronary arteries and find that our method estimates directional wall shear stress (WSS) with an approximation error of 7.6% and normalised mean absolute error (NMAE) of 0.4% while up to two orders of magnitude faster than CFD. Furthermore, we show that our method is powerful enough to accurately predict transient, vector-valued WSS over the cardiac cycle while conditioned on a range of different inflow boundary conditions. These results demonstrate the potential of our proposed method as a plugin replacement for CFD in the personalised prediction of hemodynamic vector and scalar fields.

Four-dimensional flow cardiovascular magnetic resonance aortic cross-sectional pressure changes and their associations with flow patterns in health and ascending thoracic aortic aneurysm

BACKGROUND

Ascending thoracic aortic aneurysm (ATAA) is a silent and threatening dilation of the ascending aorta (AscAo). Maximal aortic diameter which is currently used for ATAA patients management and surgery planning has been shown to inadequately characterize risk of dissection in a large proportion of patients. Our aim was to propose a comprehensive quantitative evaluation of aortic morphology and pressure-flow-wall associations from four-dimensional (4D) flow cardiovascular magnetic resonance (CMR) data in healthy aging and in patients with ATAA.

METHODS

We studied 17 ATAA patients (64.7 ± 14.3 years, 5 females) along with 17 age- and sex-matched healthy controls (59.7 ± 13.3 years, 5 females) and 13 younger healthy subjects (33.5 ± 11.1 years, 4 females). All subjects underwent a CMR exam, including 4D flow and three-dimensional anatomical images of the aorta. This latter dataset was used for aortic morphology measurements, including AscAo maximal diameter (iDMAX) and volume, indexed to body surface area. 4D flow MRI data were used to estimate 1) cross-sectional local AscAo spatial (∆PS) and temporal (∆PT) pressure changes as well as the distance (∆DPS) and time duration (∆TPT) between local pressure peaks, 2) AscAo maximal wall shear stress (WSSMAX) at peak systole, and 3) AscAo flow vorticity amplitude (VMAX), duration (VFWHM), and eccentricity (VECC).

RESULTS

Consistency of flow and pressure indices was demonstrated through their significant associations with AscAo iDMAX (WSSMAX:r = -0.49, p < 0.001; VECC:r = -0.29, p = 0.045; VFWHM:r = 0.48, p < 0.001; ∆DPS:r = 0.37, p = 0.010; ∆TPT:r = -0.52, p < 0.001) and indexed volume (WSSMAX:r = -0.63, VECC:r = -0.51, VFWHM:r = 0.53, ∆DPS:r = 0.54, ∆TPT:r = -0.63, p < 0.001 for all). Intra-AscAo cross-sectional pressure difference, ∆PS, was significantly and positively associated with both VMAX (r = 0.55, p = 0.002) and WSSMAX (r = 0.59, p < 0.001) in the 30 healthy subjects (48.3 ± 18.0 years). Associations remained significant after adjustment for iDMAX, age, and systolic blood pressure. Superimposition of ATAA patients to normal aging trends between ∆PS and WSSMAX as well as VMAX allowed identifying patients with substantially high pressure differences concomitant with AscAo dilation.

CONCLUSION

Local variations in pressures within ascending aortic cross-sections derived from 4D flow MRI were associated with flow changes, as quantified by vorticity, and with stress exerted by blood on the aortic wall, as quantified by wall shear stress. Such flow-wall and pressure interactions might help for the identification of at-risk patients.

Deep learning based assessment of hemodynamics in the coarctation of the aorta: comparison of bidirectional recurrent and convolutional neural networks

The utilization of numerical methods, such as computational fluid dynamics (CFD), has been widely established for modeling patient-specific hemodynamics based on medical imaging data. Hemodynamics assessment plays a crucial role in treatment decisions for the coarctation of the aorta (CoA), a congenital heart disease, with the pressure drop (PD) being a crucial biomarker for CoA treatment decisions. However, implementing CFD methods in the clinical environment remains challenging due to their computational cost and the requirement for expert knowledge. This study proposes a deep learning approach to mitigate the computational need and produce fast results. Building upon a previous proof-of-concept study, we compared the effects of two different artificial neural network (ANN) architectures trained on data with different dimensionalities, both capable of predicting hemodynamic parameters in CoA patients: a one-dimensional bidirectional recurrent neural network (1D BRNN) and a three-dimensional convolutional neural network (3D CNN). The performance was evaluated by median point-wise root mean square error (RMSE) for pressures along the centerline in 18 test cases, which were not included in a training cohort. We found that the 3D CNN (median RMSE of 3.23 mmHg) outperforms the 1D BRNN (median RMSE of 4.25 mmHg). In contrast, the 1D BRNN is more precise in PD prediction, with a lower standard deviation of the error (±7.03 mmHg) compared to the 3D CNN (±8.91 mmHg). The differences between both ANNs are not statistically significant, suggesting that compressing the 3D aorta hemodynamics into a 1D centerline representation does not result in the loss of valuable information when training ANN models. Additionally, we evaluated the utility of the synthetic geometries of the aortas with CoA generated by using a statistical shape model (SSM), as well as the impact of aortic arch geometry (gothic arch shape) on the model's training. The results show that incorporating a synthetic cohort obtained through the SSM of the clinical cohort does not significantly increase the model's accuracy, indicating that the synthetic cohort generation might be oversimplified. Furthermore, our study reveals that selecting training cases based on aortic arch shape (gothic versus non-gothic) does not improve ANN performance for test cases sharing the same shape.

Four-Dimensional Flow MR Imaging: Technique and Advances

4D Flow MRI is an advanced imaging technique for comprehensive non-invasive assessment of the cardiovascular system. The capture of the blood velocity vector field throughout the cardiac cycle enables measures of flow, pulse wave velocity, kinetic energy, wall shear stress, and more. Advances in hardware, MRI data acquisition and reconstruction methodology allow for clinically feasible scan times. The availability of 4D Flow analysis packages allows for more widespread use in research and the clinic and will facilitate much needed multi-center, multi-vendor studies in order to establish consistency across scanner platforms and to enable larger scale studies to demonstrate clinical value.

Machine Learning and the Conundrum of Stroke Risk Prediction

Stroke is a leading cause of death worldwide. With escalating healthcare costs, early non-invasive stroke risk stratification is vital. The current paradigm of stroke risk assessment and mitigation is focused on clinical risk factors and comorbidities. Standard algorithms predict risk using regression-based statistical associations, which, while useful and easy to use, have moderate predictive accuracy. This review summarises recent efforts to deploy machine learning (ML) to predict stroke risk and enrich the understanding of the mechanisms underlying stroke. The surveyed body of literature includes studies comparing ML algorithms with conventional statistical models for predicting cardiovascular disease and, in particular, different stroke subtypes. Another avenue of research explored is ML as a means of enriching multiscale computational modelling, which holds great promise for revealing thrombogenesis mechanisms. Overall, ML offers a new approach to stroke risk stratification that accounts for subtle physiologic variants between patients, potentially leading to more reliable and personalised predictions than standard regression-based statistical associations.

Advances in machine learning applications for cardiovascular 4D flow MRI

Four-dimensional flow magnetic resonance imaging (MRI) has evolved as a non-invasive imaging technique to visualize and quantify blood flow in the heart and vessels. Hemodynamic parameters derived from 4D flow MRI, such as net flow and peak velocities, but also kinetic energy, turbulent kinetic energy, viscous energy loss, and wall shear stress have shown to be of diagnostic relevance for cardiovascular diseases. 4D flow MRI, however, has several limitations. Its long acquisition times and its limited spatio-temporal resolutions lead to inaccuracies in velocity measurements in small and low-flow vessels and near the vessel wall. Additionally, 4D flow MRI requires long post-processing times, since inaccuracies due to the measurement process need to be corrected for and parameter quantification requires 2D and 3D contour drawing. Several machine learning (ML) techniques have been proposed to overcome these limitations. Existing scan acceleration methods have been extended using ML for image reconstruction and ML based super-resolution methods have been used to assimilate high-resolution computational fluid dynamic simulations and 4D flow MRI, which leads to more realistic velocity results. ML efforts have also focused on the automation of other post-processing steps, by learning phase corrections and anti-aliasing. To automate contour drawing and 3D segmentation, networks such as the U-Net have been widely applied. This review summarizes the latest ML advances in 4D flow MRI with a focus on technical aspects and applications. It is divided into the current status of fast and accurate 4D flow MRI data generation, ML based post-processing tools for phase correction and vessel delineation and the statistical evaluation of blood flow.