Enhancement of cerebrovascular 4D flow MRI velocity fields using machine learning and computational fluid dynamics simulation data

Super-Resolving and Denoising 4D flow MRI of Neurofluids Using Physics-Guided Neural Networks

PURPOSE

To obtain high-resolution velocity fields of cerebrospinal fluid (CSF) and cerebral blood flow by applying a physics-guided neural network (div-mDCSRN-Flow) to 4D flow MRI.

METHODS

The div-mDCSRN-Flow network was developed to improve spatial resolution and denoise 4D flow MRI. The network was trained with patches of paired high-resolution and low-resolution synthetic 4D flow MRI data derived from computational fluid dynamic simulations of CSF flow within the cerebral ventricles of five healthy cases and five Alzheimer's disease cases. The loss function combined mean squared error with a binary cross-entropy term for segmentation and a divergence-based regularization term for the conservation of mass. Performance was assessed using synthetic 4D flow MRI in one healthy and one Alzheimer' disease cases, an in vitro study of healthy cerebral ventricles, and in vivo 4D flow imaging of CSF as well as flow in arterial and venous blood vessels. Comparison was performed to trilinear interpolation, divergence-free radial basis functions, divergence-free wavelets, 4DFlowNet, and our network without divergence constraints.

RESULTS

The proposed network div-mDCSRN-Flow outperformed other methods in reconstructing high-resolution velocity fields from synthetic 4D flow MRI in healthy and AD cases. The div-mDCSRN-Flow network reduced error by 22.5% relative to linear interpolation for in vitro core voxels and by 49.5% in edge voxels.

CONCLUSION

The results demonstrate generalizability of our 4D flow MRI super-resolution and denoising approach due to network training using flow patches and physics-based constraints. The mDCSRN-Flow network can facilitate MRI studies involving CSF flow measurements in cerebral ventricles and association of MRI-based flow metrics with cerebrovascular health.

A comparison of machine learning methods for recovering noisy and missing 4D flow MRI data

Experimental blood flow measurement techniques are invaluable for a better understanding of cardiovascular disease formation, progression, and treatment. One of the emerging methods is time-resolved three-dimensional phase-contrast magnetic resonance imaging (4D flow MRI), which enables noninvasive time-dependent velocity measurements within large vessels. However, several limitations hinder the usability of 4D flow MRI and other experimental methods for quantitative hemodynamics analysis. These mainly include measurement noise, corrupt or missing data, low spatiotemporal resolution, and other artifacts. Traditional filtering is routinely applied for denoising experimental blood flow data without any detailed discussion on why it is preferred over other methods. In this study, filtering is compared to different singular value decomposition (SVD)-based machine learning and autoencoder-type deep learning methods for denoising and filling in missing data (imputation). An artificially corrupted and voxelized computational fluid dynamics (CFD) simulation as well as in vitro 4D flow MRI data are used to test the methods. SVD-based algorithms achieve excellent results for the idealized case but severely struggle when applied to in vitro data. The autoencoders are shown to be versatile and applicable to all investigated cases. For denoising, the in vitro 4D flow MRI data, the denoising autoencoder (DAE), and the Noise2Noise (N2N) autoencoder produced better reconstructions than filtering both qualitatively and quantitatively. Deep learning methods such as N2N can result in noise-free velocity fields even though they did not use clean data during training. This work presents one of the first comprehensive assessments and comparisons of various classical and modern machine-learning methods for enhancing corrupt cardiovascular flow data in diseased arteries for both synthetic and experimental test cases.

Optimizing encoding strategies for 4D Flow MRI of mean and turbulent flow

For 4D Flow MRI of mean and turbulent flow a compromise between spatiotemporal undersampling and velocity encodings needs to be found. Assuming a fixed scan time budget, the impact of trading off spatiotemporal undersampling versus velocity encodings on quantification of velocity and turbulence for aortic 4D Flow MRI was investigated. For this purpose, patient-specific mean and turbulent aortic flow data were generated using computational fluid dynamics which were embedded into the patient-specific background image data to generate synthetic MRI data with corresponding ground truth flow. Cardiac and respiratory motion were included. Using the synthetic MRI data as input, 4D Flow MRI was subsequently simulated with undersampling along pseudo-spiral Golden angle Cartesian trajectories for various velocity encoding schemes. Data were reconstructed using a locally low rank approach to obtain mean and turbulent flow fields to be compared to ground truth. Results show that, for a 15-min scan, velocity magnitudes can be reconstructed with good accuracy relatively independent of the velocity encoding scheme ( S S I M U = 0.938 ± 0.003 ) , good accuracy ( S S I M U ≥ 0.933 ) and with peak velocity errors limited to 10%. Turbulence maps on the other hand suffer from both lower reconstruction quality ( S S I M TKE ≥ 0.323 ) and larger sensitivity to undersampling, motion and velocity encoding strengths ( S S I M TKE = 0.570 ± 0.110 ) when compared to velocity maps. The best compromise to measure unwrapped velocity maps and turbulent kinetic energy given a fixed 15-min scan budget was found to be a 7-point multi- V enc acquisition with a low V enc tuned for best sensitivity to the range of expected intra-voxel standard deviations and a high V enc larger than the expected peak velocity.

Unraveling diurnal and technical variability in cerebral hemodynamics from neurovascular 4D-Flow MRI

Neurovascular 4D-Flow MRI enables non-invasive evaluation of cerebral hemodynamics including measures of cerebral blood flow (CBF), vessel pulsatility index (PI), and cerebral pulse wave velocity (PWV). 4D-Flow measures have been linked to various neurovascular disorders including small vessel disease and Alzheimer's disease; however, physiological and technical sources of variability are not well established. Here, we characterized sources of diurnal physiological and technical variability in cerebral hemodynamics using 4D-Flow in a retrospective study of cognitively unimpaired older adults (N = 750) and a prospective study of younger adults (N = 10). Younger participants underwent repeated MRI sessions at 7am, 4 pm, and 10 pm. In the older cohort, having an MRI earlier on the day was significantly associated with higher CBF and lower PI. In prospective experiments, time of day significantly explained variability in CBF and PI; however, not in PWV. Test-retest experiments showed high CBF intra-session repeatability (repeatability coefficient (RPC) =7.2%), compared to lower diurnal repeatability (RPC = 40%). PI and PWV displayed similar intra-session and diurnal variability (PI intra-session RPC = 22%, RPC = 24% 7am vs 4 pm; PWV intra-session RPC = 17%, RPC = 21% 7am vs 4 pm). Overall, CBF measures showed low technical variability, supporting diurnal variability is from physiology. PI and PWV showed higher technical variability but less diurnal variability.

Imaging of Intracranial Aneurysms: A Review of Standard and Advanced Imaging Techniques

The treatment of intracranial aneurysms is dictated by its risk of rupture in the future. Several clinical and radiological risk factors for aneurysm rupture have been described and incorporated into prediction models. Despite the recent technological advancements in aneurysm imaging, linear length and visible irregularity with a bleb are the only radiological measure used in clinical prediction models. The purpose of this article is to summarize both the standard imaging techniques, including their limitations, and the advanced techniques being used experimentally to image aneurysms. It is expected that as our understanding of advanced techniques improves, and their ability to predict clinical events is demonstrated, they become an increasingly routine part of aneurysm assessment. It is important that neurovascular specialists understand the spectrum of imaging techniques available.

Hemodynamic factors of spontaneous vertebral artery dissecting aneurysms assessed with numerical and deep learning algorithms: Role of blood pressure and asymmetry

BACKGROUND AND OBJECTIVES

The pathophysiology of spontaneous vertebral artery dissecting aneurysms (SVADA) is poorly understood. Our goal is to investigate the hemodynamic factors contributing to their formation using computational fluid dynamics (CFD) and deep learning algorithms.

METHODS

We have developed software that can use patient imagery as input to recreate the vertebrobasilar arterial system, both with and without SVADA, which we used in a series of three patients. To obtain the kinematic blood flow data before and after the aneurysm forms, we utilized numerical methods to solve the complex Navier-Stokes partial differential equations. This was accomplished through the application of a finite volume solver (OpenFoam/Helyx OS). Additionally, we trained a neural ordinary differential equation (NODE) to learn and replicate the dynamical streamlines obtained from the computational fluid dynamics (CFD) simulations.

RESULTS

In all three cases, we observed that the equilibrium of blood pressure distributions across the VAs, at a specific vertical level, accurately predicted the future SVADA location. In the two cases where there was a dominant VA, the dissection occurred on the dominant artery where blood pressure was lower compared to the contralateral side. The SVADA sac was characterized by reduced wall shear stress (WSS) and decreased velocity magnitude related to increased turbulence. The presence of a high WSS gradient at the boundary of the SVADA may explain its extension. Streamlines generated by CFD were learned with a neural ordinary differential equation (NODE) capable of capturing the system's dynamics to output meaningful predictions of the flow vector field upon aneurysm formation.

CONCLUSION

In our series, asymmetry in the vertebrobasilar blood pressure distributions at and proximal to the site of the future SVADA accurately predicted its location in all patients. Deep learning algorithms can be trained to model blood flow patterns within biological systems, offering an alternative to the computationally intensive CFD. This technology has the potential to find practical applications in clinical settings.

Implicit neural representations for unsupervised super-resolution and denoising of 4D flow MRI

BACKGROUND AND OBJECTIVE

4D flow magnetic resonance imaging provides time-resolved blood flow velocity measurements, but suffers from limitations in spatio-temporal resolution and noise. In this study, we investigated the use of sinusoidal representation networks (SIRENs) to improve denoising and super-resolution of velocity fields measured by 4D flow MRI in the thoracic aorta.

METHODS

Efficient training of SIRENs in 4D was achieved by sampling voxel coordinates and enforcing the no-slip condition at the vessel wall. A set of synthetic measurements were generated from computational fluid dynamics simulations, reproducing different noise levels. The influence of SIREN architecture was systematically investigated, and the performance of our method was compared to existing approaches for 4D flow denoising and super-resolution.

RESULTS

Compared to existing techniques, a SIREN with 300 neurons per layer and 20 layers achieved lower errors (up to 50% lower vector normalized root mean square error, 42% lower magnitude normalized root mean square error, and 15% lower direction error) in velocity and wall shear stress fields. Applied to real 4D flow velocity measurements in a patient-specific aortic aneurysm, our method produced denoised and super-resolved velocity fields while maintaining accurate macroscopic flow measurements.

CONCLUSIONS

This study demonstrates the feasibility of using SIRENs for complex blood flow velocity representation from clinical 4D flow, with quick execution and straightforward implementation.

Current Understanding of the Anatomy, Physiology, and Magnetic Resonance Imaging of Neurofluids: Update From the 2022 "ISMRM Imaging Neurofluids Study group" Workshop in Rome

Neurofluids is a term introduced to define all fluids in the brain and spine such as blood, cerebrospinal fluid, and interstitial fluid. Neuroscientists in the past millennium have steadily identified the several different fluid environments in the brain and spine that interact in a synchronized harmonious manner to assure a healthy microenvironment required for optimal neuroglial function. Neuroanatomists and biochemists have provided an incredible wealth of evidence revealing the anatomy of perivascular spaces, meninges and glia and their role in drainage of neuronal waste products. Human studies have been limited due to the restricted availability of noninvasive imaging modalities that can provide a high spatiotemporal depiction of the brain neurofluids. Therefore, animal studies have been key in advancing our knowledge of the temporal and spatial dynamics of fluids, for example, by injecting tracers with different molecular weights. Such studies have sparked interest to identify possible disruptions to neurofluids dynamics in human diseases such as small vessel disease, cerebral amyloid angiopathy, and dementia. However, key differences between rodent and human physiology should be considered when extrapolating these findings to understand the human brain. An increasing armamentarium of noninvasive MRI techniques is being built to identify markers of altered drainage pathways. During the three-day workshop organized by the International Society of Magnetic Resonance in Medicine that was held in Rome in September 2022, several of these concepts were discussed by a distinguished international faculty to lay the basis of what is known and where we still lack evidence. We envision that in the next decade, MRI will allow imaging of the physiology of neurofluid dynamics and drainage pathways in the human brain to identify true pathological processes underlying disease and to discover new avenues for early diagnoses and treatments including drug delivery. Evidence level: 1 Technical Efficacy: Stage 3.

Accelerated simulation methodologies for computational vascular flow modelling

Vascular flow modelling can improve our understanding of vascular pathologies and aid in developing safe and effective medical devices. Vascular flow models typically involve solving the nonlinear Navier-Stokes equations in complex anatomies and using physiological boundary conditions, often presenting a multi-physics and multi-scale computational problem to be solved. This leads to highly complex and expensive models that require excessive computational time. This review explores accelerated simulation methodologies, specifically focusing on computational vascular flow modelling. We review reduced order modelling (ROM) techniques like zero-/one-dimensional and modal decomposition-based ROMs and machine learning (ML) methods including ML-augmented ROMs, ML-based ROMs and physics-informed ML models. We discuss the applicability of each method to vascular flow acceleration and the effectiveness of the method in addressing domain-specific challenges. When available, we provide statistics on accuracy and speed-up factors for various applications related to vascular flow simulation acceleration. Our findings indicate that each type of model has strengths and limitations depending on the context. To accelerate real-world vascular flow problems, we propose future research on developing multi-scale acceleration methods capable of handling the significant geometric variability inherent to such problems.

Metastatic Lymph Node Detection on Ultrasound Images Using YOLOv7 in Patients with Head and Neck Squamous Cell Carcinoma

Ultrasonography is the preferred modality for detailed evaluation of enlarged lymph nodes (LNs) identified on computed tomography and/or magnetic resonance imaging, owing to its high spatial resolution. However, the diagnostic performance of ultrasonography depends on the examiner's expertise. To support the ultrasonographic diagnosis, we developed YOLOv7-based deep learning models for metastatic LN detection on ultrasonography and compared their detection performance with that of highly experienced radiologists and less experienced residents. We enrolled 462 B- and D-mode ultrasound images of 261 metastatic and 279 non-metastatic histopathologically confirmed LNs from 126 patients with head and neck squamous cell carcinoma. The YOLOv7-based B- and D-mode models were optimized using B- and D-mode training and validation images and their detection performance for metastatic LNs was evaluated using B- and D-mode testing images, respectively. The D-mode model's performance was comparable to that of radiologists and superior to that of residents' reading of D-mode images, whereas the B-mode model's performance was higher than that of residents but lower than that of radiologists on B-mode images. Thus, YOLOv7-based B- and D-mode models can assist less experienced residents in ultrasonographic diagnoses. The D-mode model could raise the diagnostic performance of residents to the same level as experienced radiologists.

Dynamic adaptive moving mesh finite-volume method for the blood flow and coagulation modeling

In this work, we develop numerical methods for the solution of blood flow and coagulation on dynamic adaptive moving meshes. We consider the blood flow as a flow of incompressible Newtonian fluid governed by the Navier-Stokes equations. The blood coagulation is introduced through the additional Darcy term, with a permeability coefficient dependent on reactions. To this end, we introduce moving mesh collocated finite-volume methods for the Navier-Stokes equations, advection-diffusion equations, and a method for the stiff cascade of reactions. A monolithic nonlinear system is solved to advance the solution in time. The finite volume method for the Navier-Stokes equations features collocated arrangement of pressure and velocity unknowns and a coupled momentum and mass flux. The method is conservative and inf-sup stable despite the saddle point nature of the system. It is verified on a series of analytical problems and applied to the blood flow problem in the deforming domain of the right ventricle, reconstructed from a time series of computed tomography scans. At last, we demonstrate the ability to model the coagulation process in deforming microfluidic capillaries.

The Potential of Deep Learning to Advance Clinical Applications of Computational Biomechanics

When combined with patient information provided by advanced imaging techniques, computational biomechanics can provide detailed patient-specific information about stresses and strains acting on tissues that can be useful in diagnosing and assessing treatments for diseases and injuries. This approach is most advanced in cardiovascular applications but can be applied to other tissues. The challenges for advancing computational biomechanics for real-time patient diagnostics and treatment include errors and missing information in the patient data, the large computational requirements for the numerical solutions to multiscale biomechanical equations, and the uncertainty over boundary conditions and constitutive relations. This review summarizes current efforts to use deep learning to address these challenges and integrate large data sets and computational methods to enable real-time clinical information. Examples are drawn from cardiovascular fluid mechanics, soft-tissue mechanics, and bone biomechanics. The application of deep-learning convolutional neural networks can reduce the time taken to complete image segmentation, and meshing and solution of finite element models, as well as improving the accuracy of inlet and outlet conditions. Such advances are likely to facilitate the adoption of these models to aid in the assessment of the severity of cardiovascular disease and the development of new surgical treatments.

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.

Deep learning phase error correction for cerebrovascular 4D flow MRI

Background phase errors in 4D Flow MRI may negatively impact blood flow quantification. In this study, we assessed their impact on cerebrovascular flow volume measurements, evaluated the benefit of manual image-based correction, and assessed the potential of a convolutional neural network (CNN), a form of deep learning, to directly infer the correction vector field. With IRB waiver of informed consent, we retrospectively identified 96 MRI exams from 48 patients who underwent cerebrovascular 4D Flow MRI from October 2015 to 2020. Flow measurements of the anterior, posterior, and venous circulation were performed to assess inflow-outflow error and the benefit of manual image-based phase error correction. A CNN was then trained to directly infer the phase-error correction field, without segmentation, from 4D Flow volumes to automate correction, reserving from 23 exams for testing. Statistical analyses included Spearman correlation, Bland-Altman, Wilcoxon-signed rank (WSR) and F-tests. Prior to correction, there was strong correlation between inflow and outflow (ρ = 0.833-0.947) measurements with the largest discrepancy in the venous circulation. Manual phase error correction improved inflow-outflow correlation (ρ = 0.945-0.981) and decreased variance (p < 0.001, F-test). Fully automated CNN correction was non-inferior to manual correction with no significant differences in correlation (ρ = 0.971 vs ρ = 0.982) or bias (p = 0.82, Wilcoxon-Signed Rank test) of inflow and outflow measurements. Residual background phase error can impair inflow-outflow consistency of cerebrovascular flow volume measurements. A CNN can be used to directly infer the phase-error vector field to fully automate phase error correction.

Super-resolution 4D flow MRI to quantify aortic regurgitation using computational fluid dynamics and deep learning

Changes in cardiovascular hemodynamics are closely related to the development of aortic regurgitation (AR), a type of valvular heart disease. Metrics derived from blood flows are used to indicate AR onset and evaluate its severity. These metrics can be non-invasively obtained using four-dimensional (4D) flow magnetic resonance imaging (MRI), where accuracy is primarily dependent on spatial resolution. However, insufficient resolution often results from limitations in 4D flow MRI and complex aortic regurgitation hemodynamics. To address this, computational fluid dynamics simulations were transformed into synthetic 4D flow MRI data and used to train a variety of neural networks. These networks generated super-resolution, full-field phase images with an upsample factor of 4. Results showed decreased velocity error, high structural similarity scores, and improved learning capabilities from previous work. Further validation was performed on two sets of in vivo 4D flow MRI data and demonstrated success in de-noising flow images. This approach presents an opportunity to comprehensively analyse AR hemodynamics in a non-invasive manner.

Cerebrovascular super-resolution 4D Flow MRI - Sequential combination of resolution enhancement by deep learning and physics-informed image processing to non-invasively quantify intracranial velocity, flow, and relative pressure

The development of cerebrovascular disease is tightly coupled to regional changes in intracranial flow and relative pressure. Image-based assessment using phase contrast magnetic resonance imaging has particular promise for non-invasive full-field mapping of cerebrovascular hemodynamics. However, estimations are complicated by the narrow and tortuous intracranial vasculature, with accurate image-based quantification directly dependent on sufficient spatial resolution. Further, extended scan times are required for high-resolution acquisitions, and most clinical acquisitions are performed at comparably low resolution (>1 mm) where biases have been observed with regard to the quantification of both flow and relative pressure. The aim of our study was to develop an approach for quantitative intracranial super-resolution 4D Flow MRI, with effective resolution enhancement achieved by a dedicated deep residual network, and with accurate quantification of functional relative pressures achieved by subsequent physics-informed image processing. To achieve this, our two-step approach was trained and validated in a patient-specific in-silico cohort, showing good accuracy in estimating velocity (relative error: 15.0 ± 0.1%, mean absolute error (MAE): 0.07 ± 0.06 m/s, and cosine similarity: 0.99 ± 0.06 at peak velocity) and flow (relative error: 6.6 ± 4.7%, root mean square error (RMSE): 0.56 mL/s at peak flow), and with the coupled physics-informed image analysis allowing for maintained recovery of functional relative pressure throughout the circle of Willis (relative error: 11.0 ± 7.3%, RMSE: 0.3 ± 0.2 mmHg). Furthermore, the quantitative super-resolution approach is applied to an in-vivo volunteer cohort, effectively generating intracranial flow images at <0.5 mm resolution and showing reduced low-resolution bias in relative pressure estimation. Our work thus presents a promising two-step approach to non-invasively quantify cerebrovascular hemodynamics, being applicable to dedicated clinical cohorts in the future.

Influence of hydrodynamic and functional nonlinearities of blood flow in the cerebral vasculature on cerebral perfusion and autoregulation pressure reserve

Ensuring the transport of oxygenated blood to the brain is one of the priorities of the human body. In the literature, there are many models of cerebral circulation with different levels of complexity used to assess pathological conditions, support clinical decisions, and learn about the relationships governing cerebral circulation. This paper presents a zero-dimensional cerebral circulation model that considers hydrodynamic nonlinearities and autoregulation mechanisms. The model has been verified using a computational fluid dynamics (CFD) model of the Circle of Willis (CoW) and its supplying and outgoing branches. Despite the considerable simplicity, the presented model captured the dominant features of cerebral circulation and provides good agreement with the CFD model. The errors in relation to the CFD model did not exceed 2.6% and 9.9% for the symmetrical and highly asymmetrical CoW configurations, respectively. The practical application of the model was demonstrated for predicting the autoregulation pressure reserve for different diameters of natural anastomoses: Posterior and Anterior Communicating Arteries. The advantages and limitations of the model were discussed.

Accelerated 4D-flow MRI with 3-point encoding enabled by machine learning

PURPOSE

To investigate the acceleration of 4D-flow MRI using a convolutional neural network (CNN) that produces three directional velocities from three flow encodings, without requiring a fourth reference scan measuring background phase.

METHODS

A fully 3D CNN using a U-net architecture was trained in a block-wise fashion to take complex images from three flow encodings and to produce three real-valued images for each velocity component. Using neurovascular 4D-flow scans (n = 144), the CNN was trained to predict velocities computed from four flow encodings by standard reconstruction including correction for residual background phase offsets. Methods to optimize loss functions were investigated, including magnitude, complex difference, and uniform velocity weightings. Subsequently, 3-point encoding was evaluated using cross validation of pixelwise correlation, flow measurements in major arteries, and in experiments with data at differing acceleration rates than the training data.

RESULTS

The CNN-produced 3-point velocities showed excellent agreements with the 4-point velocities, both qualitatively in velocity images, in flow rate measures, and quantitatively in regression analysis (slope = 0.96, R²  = 0.992). Optimizing the training to focus on vessel velocities rather than the global velocity error and improved the correlation of velocity within vessels themselves. The lowest error was observed when the loss function used uniform velocity weighting, in which the magnitude-weighted inverse of the velocity frequency uniformly distributed weighting across all velocity ranges. When applied to highly accelerated data, the 3-point network maintained a high correlation with ground truth data and demonstrated a denoising effect.

CONCLUSION

The 4D-flow MRI can be accelerated using machine learning requiring only three flow encodings to produce three-directional velocity maps with small errors.

Recent developments in modeling, imaging, and monitoring of cardiovascular diseases using machine learning

Cardiovascular diseases are the leading cause of mortality, morbidity, and hospitalization around the world. Recent technological advances have facilitated analyzing, visualizing, and monitoring cardiovascular diseases using emerging computational fluid dynamics, blood flow imaging, and wearable sensing technologies. Yet, computational cost, limited spatiotemporal resolution, and obstacles for thorough data analysis have hindered the utility of such techniques to curb cardiovascular diseases. We herein discuss how leveraging machine learning techniques, and in particular deep learning methods, could overcome these limitations and offer promise for translation. We discuss the remarkable capacity of recently developed machine learning techniques to accelerate flow modeling, enhance the resolution while reduce the noise and scanning time of current blood flow imaging techniques, and accurate detection of cardiovascular diseases using a plethora of data collected by wearable sensors.

Physics-informed compressed sensing for PC-MRI: an inverse Navier-Stokes problem

We formulate a physics-informed compressed sensing (PICS) method for the reconstruction of velocity fields from noisy and sparse phase-contrast magnetic resonance signals. The method solves an inverse Navier-Stokes boundary value problem, which permits us to jointly reconstruct and segment the velocity field, and at the same time infer hidden quantities such as the hydrodynamic pressure and the wall shear stress. Using a Bayesian framework, we regularize the problem by introducing a priori information about the unknown parameters in the form of Gaussian random fields. This prior information is updated using the Navier-Stokes problem, an energy-based segmentation functional, and by requiring that the reconstruction is consistent with the k-space signals. We create an algorithm that solves this inverse problem, and test it for noisy and sparse k-space signals of the flow through a converging nozzle. We find that the method is capable of reconstructing and segmenting the velocity fields from sparsely-sampled (15% k-space coverage), low (~10) signal-to-noise ratio (SNR) signals, and that the reconstructed velocity field compares well with that derived from fully-sampled (100% k-space coverage) high (>40) SNR signals of the same flow.

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.

Long-term recovery behavior of brain tissue in hydrocephalus patients after shunting

The unpredictable complexities in hydrocephalus shunt outcomes may be related to the recovery behavior of brain tissue after shunting. The simulated cerebrospinal fluid (CSF) velocity and intracranial pressure (ICP) over 15 months after shunting were validated by experimental data. The mean strain and creep of the brain had notable changes after shunting and their trends were monotonic. The highest stiffness of the hydrocephalic brain was in the first consolidation phase (between pre-shunting to 1 month after shunting). The viscous component overcame and damped the input load in the third consolidation phase (after the fifteenth month) and changes in brain volume were stopped. The long-intracranial elastance (long-IE) changed oscillatory after shunting and there was not a linear relationship between long-IE and ICP. We showed the long-term effect of the viscous component on brain recovery behavior of hydrocephalic brain. The results shed light on the brain recovery mechanism after shunting and the mechanisms for shunt failure.

Abdominal applications of quantitative 4D flow MRI

4D flow MRI is a quantitative MRI technique that allows the comprehensive assessment of time-resolved hemodynamics and vascular anatomy over a 3-dimensional imaging volume. It effectively combines several advantages of invasive and non-invasive imaging modalities like ultrasound, angiography, and computed tomography in a single MRI acquisition and provides an unprecedented characterization of velocity fields acquired non-invasively in vivo. Functional and morphological imaging of the abdominal vasculature is especially challenging due to its complex and variable anatomy with a wide range of vessel calibers and flow velocities and the need for large volumetric coverage. Despite these challenges, 4D flow MRI is a promising diagnostic and prognostic tool as many pathologies in the abdomen are associated with changes of either hemodynamics or morphology of arteries, veins, or the portal venous system. In this review article, we will discuss technical aspects of the implementation of abdominal 4D flow MRI ranging from patient preparation and acquisition protocol over post-processing and quality control to final data analysis. In recent years, the range of applications for 4D flow in the abdomen has increased profoundly. Therefore, we will review potential clinical applications and address their clinical importance, relevant quantitative and qualitative parameters, and unmet challenges.

SRflow: Deep learning based super-resolution of 4D-flow MRI data

Exploiting 4D-flow magnetic resonance imaging (MRI) data to quantify hemodynamics requires an adequate spatio-temporal vector field resolution at a low noise level. To address this challenge, we provide a learned solution to super-resolve in vivo 4D-flow MRI data at a post-processing level. We propose a deep convolutional neural network (CNN) that learns the inter-scale relationship of the velocity vector map and leverages an efficient residual learning scheme to make it computationally feasible. A novel, direction-sensitive, and robust loss function is crucial to learning vector-field data. We present a detailed comparative study between the proposed super-resolution and the conventional cubic B-spline based vector-field super-resolution. Our method improves the peak-velocity to noise ratio of the flow field by 10 and 30% for in vivo cardiovascular and cerebrovascular data, respectively, for 4 × super-resolution over the state-of-the-art cubic B-spline. Significantly, our method offers 10x faster inference over the cubic B-spline. The proposed approach for super-resolution of 4D-flow data would potentially improve the subsequent calculation of hemodynamic quantities.

A New Definition for Intracranial Compliance to Evaluate Adult Hydrocephalus After Shunting

The clinical application of intracranial compliance (ICC), ∆V/∆P, as one of the most critical indexes for hydrocephalus evaluation was demonstrated previously. We suggest a new definition for the concept of ICC (long-term ICC) where there is a longer amount of elapsed time (up to 18 months after shunting) between the measurement of two values (V1 and V2 or P1 and P2). The head images of 15 adult patients with communicating hydrocephalus were provided with nine sets of imaging in nine stages: prior to shunting, and 1, 2, 3, 6, 9, 12, 15, and 18 months after shunting. In addition to measuring CSF volume (CSFV) in each stage, intracranial pressure (ICP) was also calculated using fluid–structure interaction simulation for the noninvasive calculation of ICC. Despite small increases in the brain volume (16.9%), there were considerable decreases in the ICP (70.4%) and CSFV (80.0%) of hydrocephalus patients after 18 months of shunting. The changes in CSFV, brain volume, and ICP values reached a stable condition 12, 15, and 6 months after shunting, respectively. The results showed that the brain tissue needs approximately two months to adapt itself to the fast and significant ICP reduction due to shunting. This may be related to the effect of the “viscous” component of brain tissue. The ICC trend between pre-shunting and the first month of shunting was descending for all patients with a “mean value” of 14.75 ± 0.6 ml/cm H2O. ICC changes in the other stages were oscillatory (nonuniform). Our noninvasive long-term ICC calculations showed a nonmonotonic trend in the CSFV–ICP graph, the lack of a linear relationship between ICC and ICP, and an oscillatory increase in ICC values during shunt treatment. The oscillatory changes in long-term ICC may reflect the clinical variations in hydrocephalus patients after shunting.

Deep Learning for Computational Hemodynamics: A Brief Review of Recent Advances

Computational fluid dynamics (CFD) modeling of blood flow plays an important role in better understanding various medical conditions, designing more effective drug delivery systems, and developing novel diagnostic methods and treatments. However, despite significant advances in computational technology and resources, the expensive computational cost of these simulations still hinders their transformation from a research interest to a clinical tool. This bottleneck is even more severe for image-based, patient-specific CFD simulations with realistic boundary conditions and complex computational domains, which make such simulations excessively expensive. To address this issue, deep learning approaches have been recently explored to accelerate computational hemodynamics simulations. In this study, we review recent efforts to integrate deep learning with CFD and discuss the applications of this approach in solving hemodynamics problems, such as blood flow behavior in aorta and cerebral arteries. We also discuss potential future directions in the field. In this review, we suggest that incorporating physiologic understandings and underlying fluid mechanics laws in deep learning models will soon lead to a paradigm shift in the development novel non-invasive computational medical decisions.

Medical Image-Based Computational Fluid Dynamics and Fluid-Structure Interaction Analysis in Vascular Diseases

Hemodynamic factors, induced by pulsatile blood flow, play a crucial role in vascular health and diseases, such as the initiation and progression of atherosclerosis. Computational fluid dynamics, finite element analysis, and fluid-structure interaction simulations have been widely used to quantify detailed hemodynamic forces based on vascular images commonly obtained from computed tomography angiography, magnetic resonance imaging, ultrasound, and optical coherence tomography. In this review, we focus on methods for obtaining accurate hemodynamic factors that regulate the structure and function of vascular endothelial and smooth muscle cells. We describe the multiple steps and recent advances in a typical patient-specific simulation pipeline, including medical imaging, image processing, spatial discretization to generate computational mesh, setting up boundary conditions and solver parameters, visualization and extraction of hemodynamic factors, and statistical analysis. These steps have not been standardized and thus have unavoidable uncertainties that should be thoroughly evaluated. We also discuss the recent development of combining patient-specific models with machine-learning methods to obtain hemodynamic factors faster and cheaper than conventional methods. These critical advances widen the use of biomechanical simulation tools in the research and potential personalized care of vascular diseases.

Application of moving particle semi-implicit (MPS) method on retro-oil fluid using three-dimensional vitreous cavity models from magnetic resonance imaging

Silicone oil (SO) is a safe and widely used intraocular tamponade agent for treating complicated vitreoretinal diseases, such as retinal detachments (RRDs) with inferior proliferative vitreoretinopathy (PVR). However, as the human vitreous cavity is irregularly shaped, it is difficult to predict the area of the inferior retina covered with SO and the retro-oil fluid currents in each patient. Here, we performed fluid simulation analysis using the moving particle semi-implicit method on the oil cover rates and absolute velocity gradient of retro-oil fluid to the retina using vitreous cavity models derived from magnetic resonance imaging of patients to determine the appropriate amount of SO and postoperative position to achieve a sufficient tamponade effect on the inferior retina. In all seven vitreous cavity models tested, the inferior quadrant of the retina was completely covered by SO in more positions and the absolute velocity gradient of the retro-oil fluid in contact with the retinal wall caused by eye and head movements was lower when the vitreous cavity was filled with 95% SO and 5% retro-oil fluid versus 80% SO and 20% retro-oil fluid. Taken together, these findings have clinical implications for the treatment of complicated RRDs with inferior PVR requiring SO tamponade.