A data-driven computational methodology towards a pre-hospital Acute Ischaemic Stroke screening tool using haemodynamics waveforms.

BACKGROUND AND OBJECTIVE: Acute Ischaemic Stroke (AIS), a significant global health concern, results from occlusions in cerebral arteries, causing irreversible brain damage. Different type of treatments exist depending on the size and location of the occlusion. Challenges persist in achieving faster diagnosis and treatment, which needs to happen in the first hours after the onset of symptoms to maximize the chances of patient recovery. The current diagnostic pipeline, i.e. "drip and ship", involves diagnostic via advanced imaging tools, only available in large clinical facilities, which poses important delays. This study investigates the feasibility of developing a machine learning model to diagnose and locate occluding blood clots from velocity waveforms, which can be easily be obtained with portable devices such as Doppler Ultrasound. The goal is to explore this approach as a cost-effective and time-efficient alternative to advanced imaging techniques typically available only in large hospitals. METHODS: Simulated haemodynamic data is used to conduct blood flow simulations representing healthy and different AIS scenarios using a population-based database. A Machine Learning classification model is trained to solve the inverse problem, this is, detect and locate a potentially occluding thrombus from measured waveforms. The classification process involves two steps. First, the region where the thrombus is located is classified into nine groups, including healthy, left or right large vessel occlusion, left or right anterior cerebral artery, and left or right posterior cerebral artery. In a second step, the bifurcation generation of the thrombus location is classified as small, medium, or large vessel occlusion. RESULTS: The proposed methodology is evaluated for data without noise, achieving a true prediction rate exceeding 95% for both classification steps mentioned above. The inclusion of up to 20% noise reduces the true prediction rate to 80% for region detection and 70% for bifurcation generation detection. CONCLUSIONS: This study demonstrates the potential effectiveness and efficiency of using haemodynamic data and machine learning to detect and locate occluding thrombi in AIS patients. Although the geometric and topological data used in this study are idealized, the results suggest that this approach could be applicable in real-world situations with appropriate adjustments. Source code is available in https://github.com/ahmetsenemse/Acute-Ischaemic-Stroke-screening-tool-.

Effect of foot stato-dynamic disorders on hemodynamics of the lower limb using strain-gauge plethysmography.

BACKGROUND: The plantar venous pump (PVP), composed of deep plantar veins, is the most distal contributor to venous return from the lower limbs. A pressing need still exists to assess how plantar muscle contraction and gait affect PVP function, how foot stato-dynamic disorders (FSDs) can contribute to venous insufficiency, and how venous return can be optimally stimulated. Our first objective is to compare the venous blood hemodynamics in lower limbs between healthy subjects with a FSD and healthy subjects without a FSD to understand the influence of foot morphology in the performance of the PVP. Our second objective is to evaluate whether PVP function varies with different plantar pressures. METHODS: A total of 52 healthy volunteers (26 feet with a normal arch as the control group and 26 feet with dysmorphism [13 flat feet and 13 hollow feet]) were included. Strain-gauge plethysmography was performed 8 cm above the medial malleolus at different conditions of PVP stimulation: (1) toe flexion, (2) intermittent pneumatic compression (IPC) with and without an insole, and (3) 3-km/h speed walking on a treadmill barefoot, with shoes, and with shoes and insoles. From the strain-gauge plethysmography, we measured the venous blood ejection fraction (EF). From the pressure sensor placed at the midfoot on the plantar arch during IPC, we obtained the maximal pressure (N/cm2). RESULTS: Toe flexion allowed for ejection of an average of 20% of the total venous volume in both groups. IPC and gait generated a mean EF superior to 100% of the available venous volume. The maximal pressure applied at the midfoot during IPC was lower than the pressure set. No significant differences in the EF or maximal pressure were observed between the two groups. The mean EF was not significantly affected for the pronator and supinator walkers compared with those with normal walking dynamics. Wearing shoes did not significantly affect the mean EF. However, wearing insoles during gait significantly increased the venous return in feet with plantar dysmorphism. CONCLUSIONS: To the best of our knowledge, this clinical study is the first to assess the PVP function in 52 healthy volunteers with and without FSDs. We found that wearing shoes did not significantly affect PVP efficiency but that wearing morphologically adapted insoles significantly improved the venous return in the dysmorphic feet. In our sample of healthy volunteers, the differences observed between the control group and feet with FSDs were not statistically significant.

Effect of dysmorphic plantar arch on venous hemodynamics of the lower limb.

BACKGROUND: The role of the plantar venous pump (PVP) on venous return is evident but the effects of the foot morphology have never been characterized properly. METHOD: 52 healthy volunteers-26 with normal plantar arch (control) and 26 with dysmorphic plantar arch (in two subgroups: 13 flat feet, 13 hollow feet)-were included. Using Doppler ultrasound, we measured the diameter and the peak systolic velocity in the large veins of the lower limb after PVP stimulation by manual compression and bodyweight transfer. RESULT: The mean peak systolic velocity of the studied veins varied from 12.2 cm/s to 41.7 cm/s in the control group and from 10.9 cm/s to 39.1 cm/s in the dysmorphic plantar group. The foot arch morphology did not affect significantly the venous blood flows, except in the great saphenous vein during manual compression. CONCLUSION: The plantar morphology did not induce a significant increase of venous blood velocity resulting from PVP stimulation.

Machine learning and reduced order modelling for the simulation of braided stent deployment.

Endoluminal reconstruction using flow diverters represents a novel paradigm for the minimally invasive treatment of intracranial aneurysms. The configuration assumed by these very dense braided stents once deployed within the parent vessel is not easily predictable and medical volumetric images alone may be insufficient to plan the treatment satisfactorily. Therefore, here we propose a fast and accurate machine learning and reduced order modelling framework, based on finite element simulations, to assist practitioners in the planning and interventional stages. It consists of a first classification step to determine a priori whether a simulation will be successful (good conformity between stent and vessel) or not from a clinical perspective, followed by a regression step that provides an approximated solution of the deployed stent configuration. The latter is achieved using a non-intrusive reduced order modelling scheme that combines the proper orthogonal decomposition algorithm and Gaussian process regression. The workflow was validated on an idealized intracranial artery with a saccular aneurysm and the effect of six geometrical and surgical parameters on the outcome of stent deployment was studied. We trained six machine learning models on a dataset of varying size and obtained classifiers with up to 95% accuracy in predicting the deployment outcome. The support vector machine model outperformed the others when considering a small dataset of 50 training cases, with an accuracy of 93% and a specificity of 97%. On the other hand, real-time predictions of the stent deployed configuration were achieved with an average validation error between predicted and high-fidelity results never greater than the spatial resolution of 3D rotational angiography, the imaging technique with the best spatial resolution (0.15 mm). Such accurate predictions can be reached even with a small database of 47 simulations: by increasing the training simulations to 147, the average prediction error is reduced to 0.07 mm. These results are promising as they demonstrate the ability of these techniques to achieve simulations within a few milliseconds while retaining the mechanical realism and predictability of the stent deployed configuration.

CRIMSON: An open-source software framework for cardiovascular integrated modelling and simulation.

In this work, we describe the CRIMSON (CardiovasculaR Integrated Modelling and SimulatiON) software environment. CRIMSON provides a powerful, customizable and user-friendly system for performing three-dimensional and reduced-order computational haemodynamics studies via a pipeline which involves: 1) segmenting vascular structures from medical images; 2) constructing analytic arterial and venous geometric models; 3) performing finite element mesh generation; 4) designing, and 5) applying boundary conditions; 6) running incompressible Navier-Stokes simulations of blood flow with fluid-structure interaction capabilities; and 7) post-processing and visualizing the results, including velocity, pressure and wall shear stress fields. A key aim of CRIMSON is to create a software environment that makes powerful computational haemodynamics tools accessible to a wide audience, including clinicians and students, both within our research laboratories and throughout the community. The overall philosophy is to leverage best-in-class open source standards for medical image processing, parallel flow computation, geometric solid modelling, data assimilation, and mesh generation. It is actively used by researchers in Europe, North and South America, Asia, and Australia. It has been applied to numerous clinical problems; we illustrate applications of CRIMSON to real-world problems using examples ranging from pre-operative surgical planning to medical device design optimization.

A nonlinear rotation-free shell formulation with prestressing for vascular biomechanics.

We implement a nonlinear rotation-free shell formulation capable of handling large deformations for applications in vascular biomechanics. The formulation employs a previously reported shell element that calculates both the membrane and bending behavior via displacement degrees of freedom for a triangular element. The thickness stretch is statically condensed to enforce vessel wall incompressibility via a plane stress condition. Consequently, the formulation allows incorporation of appropriate 3D constitutive material models. We also incorporate external tissue support conditions to model the effect of surrounding tissue. We present theoretical and variational details of the formulation and verify our implementation against axisymmetric results and literature data. We also adapt a previously reported prestress methodology to identify the unloaded configuration corresponding to the medically imaged in vivo vessel geometry. We verify the prestress methodology in an idealized bifurcation model and demonstrate the significance of including prestress. Lastly, we demonstrate the robustness of our formulation via its application to mouse-specific models of arterial mechanics using an experimentally informed four-fiber constitutive model.