Learning Hemodynamic Scalar Fields on Coronary Artery Meshes: A Benchmark of Geometric Deep Learning Models

Coronary artery disease, caused by the narrowing of coronary vessels due to atherosclerosis, is the leading cause of death worldwide. The diagnostic gold standard, fractional flow reserve (FFR), measures the trans-stenotic pressure ratio during maximal vasodilation but is invasive and costly. This has driven the development of virtual FFR (vFFR) using computational fluid dynamics (CFD) to simulate coronary flow. Geometric deep learning algorithms have shown promise for learning features on meshes, including cardiovascular research applications. This study empirically analyzes various backends for predicting vFFR fields in coronary arteries as CFD surrogates, comparing six backends for learning hemodynamics on meshes using CFD solutions as ground truth. The study has two parts: i) Using 1,500 synthetic left coronary artery bifurcations, models were trained to predict pressure-related fields for vFFR reconstruction, comparing different learning variables. ii) Using 427 patient-specific CFD simulations, experiments were repeated focusing on the best-performing learning variable from the synthetic dataset. Most backends performed well on the synthetic dataset, especially when predicting pressure drop over the manifold. Transformer-based backends outperformed others when predicting pressure and vFFR fields and were the only models achieving strong performance on patient-specific data, excelling in both average per-point error and vFFR accuracy in stenotic lesions. These results suggest geometric deep learning backends can effectively replace CFD for simple geometries, while transformer-based networks are superior for complex, heterogeneous datasets. Pressure drop was identified as the optimal network output for learning pressure-related fields.

Deep vectorised operators for pulsatile hemodynamics estimation in coronary arteries from a steady-state prior

Cardiovascular hemodynamic fields provide valuable medical decision markers for coronary artery disease. Computational fluid dynamics (CFD) is the gold standard for accurate, non-invasive evaluation of these quantities in vivo. In this work, we propose a time-efficient surrogate model, powered by machine learning, for the estimation of pulsatile hemodynamics based on steady-state priors. We introduce deep vectorised operators, a modelling framework for discretisation independent learning on infinite-dimensional function spaces. The underlying neural architecture is a neural field conditioned on hemodynamic boundary conditions. Importantly, we show how relaxing the requirement of point-wise action to permutation-equivariance leads to a family of models that can be parametrised by message passing and self-attention layers. We evaluate our approach on a dataset of 74 stenotic coronary arteries extracted from coronary computed tomography angiography (CCTA) with patient-specific pulsatile CFD simulations as ground truth. We show that our model produces accurate estimates of the pulsatile velocity and pressure while being agnostic to re-sampling of the source domain (discretisation independence). This shows that deep vectorised operators are a powerful modelling tool for cardiovascular hemodynamics estimation in coronary arteries and beyond.

Augmented Reality and Human-Robot Collaboration Framework for Percutaneous Nephrolithotomy

During Percutaneous Nephrolithotomy (PCNL) operations, the surgeon is required to define the incision point on the patient's back, align the needle to a pre-planned path, and perform puncture operations afterward. The procedure is currently performed manually using ultrasound or fluoroscopy imaging for needle orientation, which, however, implies limited accuracy and low reproducibility. This work incorporates Augmented Reality (AR) visualization with an optical see-through head-mounted display (OST-HMD) and Human-Robot Collaboration (HRC) framework to empower the surgeon's task completion performance. In detail, Eye-to-Hand calibration, system registration, and hologram model registration are performed to realize visual guidance. A Cartesian impedance controller is used to guide the operator during the needle puncture task execution. Experiments are conducted to verify the system performance compared with conventional manual puncture procedures and a 2D monitor-based visualisation interface. The results showed that the proposed framework achieves the lowest median and standard deviation error across all the experimental groups, respectively. Furthermore, the NASA-TLX user evaluation results indicate that the proposed framework requires the lowest workload score for task completion compared to other experimental setups. The proposed framework exhibits significant potential for clinical application in the PCNL task, as it enhances the surgeon's perception capability, facilitates collision-free needle insertion path planning, and minimises errors in task completion.

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

4D flow MRI is a non-invasive imaging method that can measure blood flow velocities over time. However, the velocity fields detected by this technique have limitations due to low resolution and measurement noise. Coordinate-based neural networks have been researched to improve accuracy, with SIRENs being suitable for super-resolution tasks. Our study investigates SIRENs for time-varying 3-directional velocity fields measured in the aorta by 4D flow MRI, achieving denoising and super-resolution. We trained our method on voxel coordinates and benchmarked our approach using synthetic measurements and a real 4D flow MRI scan. Our optimized SIREN architecture outperformed state-of-the-art techniques, producing denoised and super-resolved velocity fields from clinical data. Our approach is quick to execute and straightforward to implement for novel cases, achieving 4D super-resolution.

A Deep Learning-Based and Fully Automated Pipeline for Regurgitant Mitral Valve Anatomy Analysis from 3D Echocardiography

3D transesophageal echocardiography (3DTEE), is the recommended method for diagnosing mitral regurgitation (MR). 3DTEE provides a high-quality 3D image of the mitral valve (MV), allowing for precise segmentation and measurement of the regurgitant valve anatomy. However, manual TEE segmentations are time-consuming and prone to intra-operator variability, affecting the reliability of the measurements. To address this, we developed a fully automated pipeline using a 3D convolutional neural network (CNN) to segment MV substructures (annulus, anterior leaflet, and posterior leaflet) and quantify MV anatomy. The 3D CNN, based on a multi-decoder residual U-Net architecture, was trained and tested on a dataset comprising 100 3DTEE images with corresponding segmentations. Within the pipeline, a custom algorithm refines the CNN-based segmentations and extracts MV models, from which anatomical landmarks and features are quantified. The accuracy of the proposed method was assessed using Dice score and mean surface distance (MSD) against ground truth segmentations, and the extracted anatomical parameters were compared against a semiautomated commercial software TomTec Image Arena. The trained 3D CNN achieved an average Dice score of 0.79 and MSD of 0.47 mm for the combined segmentation of the annulus, anterior and posterior leaflet. The proposed CNN architecture outperformed a baseline residual U-Net architecture in MV substructure segmentation, and the refinement of the predicted annulus segmentation improved MSD by 8.36%. The annular and leaflet linear measurements differed by less than 7.94 mm and 3.67 mm, respectively, compared to the 3D measurements obtained with TomTec Image Arena. The proposed pipeline was faster than the commercial software, with a modeling time of 12.54 s and a quantification time of 54.42 s.

A CT-based deep learning system for automatic assessment of aortic root morphology for TAVI planning

Accurate planning of transcatheter aortic implantation (TAVI) is important to minimize complications, and it requires anatomic evaluation of the aortic root (AR), commonly done through 3D computed tomography (CT) image analysis. Currently, there is no standard automated solution for this process. Two convolutional neural networks (CNNs) with 3D U-Net architectures (model 1 and model 2) were trained on 310 CT scans for AR analysis. Model 1 performed AR segmentation and model 2 identified the aortic annulus and sinotubular junction (STJ) contours. Results were validated against manual measurements of 178 TAVI candidates. After training, the two models were integrated into a fully automated pipeline for geometric analysis of the AR. The trained CNNs effectively segmented the AR, annulus and STJ, resulting in mean Dice scores of 0.93 for the AR, and mean surface distances of 1.16 mm and 1.30 mm for the annulus and STJ, respectively. Automatic measurements were in good agreement with manual annotations, yielding annulus diameters that differed by 0.52 [-2.96, 4.00] mm (bias and 95% limits of agreement for manual minus algorithm). Evaluating the area-derived diameter, bias and limits of agreement were 0.07 [-0.25, 0.39] mm. STJ and sinuses diameters computed by the automatic method yielded differences of 0.16 [-2.03, 2.34] and 0.1 [-2.93, 3.13] mm, respectively. The proposed tool is a fully automatic solution to quantify morphological biomarkers for pre-TAVI planning. The method was validated against manual annotation from clinical experts and showed to be quick and effective in assessing AR anatomy, with potential for time and cost savings.

Data-driven generation of 4D velocity profiles in the aneurysmal ascending aorta

Numerical simulations of blood flow are a valuable tool to investigate the pathophysiology of ascending thoracic aortic aneurysms (ATAA). To accurately reproduce hemodynamics, computational fluid dynamics (CFD) models must employ realistic inflow boundary conditions (BCs). However, the limited availability of in vivo velocity measurements still makes researchers resort to idealized BCs. In this study we generated and thoroughly characterized a large dataset of synthetic 4D aortic velocity profiles suitable to be used as BCs for CFD simulations. 4D flow MRI scans of 30 subjects with ATAA were processed to extract cross-sectional planes along the ascending aorta, ensuring spatial alignment among all planes and interpolating all velocity fields to a reference configuration. Velocity profiles of the clinical cohort were extensively characterized by computing flow morphology descriptors of both spatial and temporal features. By exploiting principal component analysis (PCA), a statistical shape model (SSM) of 4D aortic velocity profiles was built and a dataset of 437 synthetic cases with realistic properties was generated. Comparison between clinical and synthetic datasets showed that the synthetic data presented similar characteristics as the clinical population in terms of key morphological parameters. The average velocity profile qualitatively resembled a parabolic-shaped profile, but was quantitatively characterized by more complex flow patterns which an idealized profile would not replicate. Statistically significant correlations were found between PCA principal modes of variation and flow descriptors. We built a data-driven generative model of 4D aortic velocity profiles, suitable to be used in computational studies of blood flow. The proposed software system also allows to map any of the generated velocity profiles to the inlet plane of any virtual subject given its coordinate set.