2023-2024: Computational Biomechanical Modelling of Thoracic Endovascular Aortic Repair

Thoracic aortic pathologies, such as aortic aneurysms and aortic dissections, are slow-progressing yet highly fatal cardiovascular diseases with a near 100% mortality rate upon rupture. Thoracic endovascular aortic repair (TEVAR) has emerged as an effective, minimally invasive treatment that reduces post-operative complications and optimizes patient outcomes. Yet, TEVAR is highly susceptible to the complex, patient-specific anatomical and biomechanical environments, which pose a wide variety of potential device-related risks (e.g. endoleaks, migration, collapse) to be addressed with discretion. As such, advancements computational fluid dynamics (CFD) enable the simulation of blood flow numerically, hence facilitating the qualitative and quantitative investigation of the haemodynamics and their impact on the device.

This project is still working in progress... however, you can click here to check out this light-weight tool box to fit any waveform from any raster plots and reconstruct into 21 Fourier terms!

Keynote - Computational Biomechanical Modelling of Thoracic Endovascular Aortic Repair.

2022-2023: Surrogate Modelling of Cardiovascular Fluid Dynamics with Physics-Informed Neural Networks

As universal function approximators, deep neural networks have the potential of being the surrogate solver of the Navier-Stokes (NS) equations. This was recently demonstrated via the Physics Informed Neural Network (PINN) on aneurysm flows by Sun et al. However, PINNs are specific to the geometry of the flow domain and require slow training for each new geometric scenario encountered. Here, we present an alternative approach, where a deep learning (DL) side network is cascaded to a PINN domain network for the pre-training of varied geometric cases, which has the potential to enhance network robustness and decrease training complexity.

2021-22: Fluid Mechanical Effects of Fetal Aortic Valvuloplasty for Cases of Aortic Stenosis and Evolving Hypoplastic Left Heart Syndrome

Fetal aortic stenosis (AS) with evolving hypoplastic left heart syndrome (feHLHS) causes high risks of progression to HLHS at birth. An in-utero catheter-based intervention, Fetal Aortic Valvuloplasty (FAV), has shown promise as an intervention strategy to circumvent the progression, but its impact on the heart's biomechanics is not well understood. We performed patient-specific computational fluid dynamic (CFD) simulations based on 4D fetal echocardiography to assess the changes in the fluid mechanical environment in the feHLHS left ventricle (LV) before and after FAV.

Past Projects

Archive of my past projects at Imperial College London.