Projects Available

Master’s Project: Geometric Deep Learning for Predicting Calcified Coronary Artery Response to Angioplasty

Project Description: Cardiologists face significant challenges in treating patients with highly calcified coronary arteries. Calcified tissue within the arterial wall is highly non-compliant which can severely restrict the expansion of drug eluting stents. To mitigate such complications, cardiologists pre-emptively employ several interventional strategies such as using several stents, adjusting stent deployment parameters, or employing vessel preparation techniques such as atherectomy or lithotripsy.

However, predicting the mechanical interaction between device and coronary anatomy is difficult and requires the use of costly numerical simulations.  This project aims to develop a deep learning tool to rapidly predict the response of calcified coronary arteries to angioplasty, assisting cardiologists in making setting interventional strategies. Our lab has recently developed a virtual angioplasty platform that can numerically model stent expansion under various morphological and mechanical conditions. This project will leverage graph neural networks (geometric deep learning) as a surrogate model to process 3D meshes of multi-material calcified coronary arteries and predict clinical metrics of stent expansion as predicted by numerical models under varying material and deployment parameters.

Responsibilities: The selected master’s student will work closely with a PhD student and will be responsible for:

  • Processing and analyzing 3D meshes of calcified coronary arteries.
  • Developing a geometric deep learning surrogate model to predict stent expansion response in calcified coronary arteries.
  • Validating the model using clinical data and imaging modalities.
  • Collaborating with cardiologists to refine the model and ensure its applicability in clinical settings.


  • Experience in deep learning libraries, such as PyTorch.
  • Knowledge of computational mechanics.
  • Experience in computational geometry.

Good to haves:

  • Knowledge of cardiology.
  • Experience in scientific machine learning
  • Experience with geometric deep learning libraries (such as Pytorch Geometric).
  • Experience with soft tissue biomechanics simulations

Prospective candidates should candidate

Master’s Project: Deep Learning-Based Co-Registration of Coronary Computed Tomography and Intravascular Images

Project Description: Coronary Computed Tomography Angiography (CCTA) is a 3-dimensional imaging modality that offers crucial information on the presence, extent, and severity of obstructive coronary artery disease (CAD). Patients undergoing CCTA typically receive a contrast dye injection, enabling visualization of coronary anatomy. Although CCTA is widely used, it primarily focuses on luminal assessment, with limited capabilities for evaluating soft tissue intraplaque components and distinctive blooming artifacts in the presence of intraplaque calcium deposits.

Multiple studies have quantified CCTA’s effectiveness in assessing CAD-related diagnostic metrics, such as luminal area, calcium morphology, and plaque burden. Most of these studies validate CCTA’s performance by co-registering image slices with invasive intravascular imaging modalities like Optical Coherence Tomography (OCT), which offers higher fidelity visualization of the lumen and surrounding diseased tissue. We have recently developed a semi-automatic pipeline that aligns intravascular image frames along the artery to their equivalent frames in CCTA images. This project aims to integrate deep-learning modules into the pipeline to automatically align OCT and CCTA images. The resulting module will serve as a foundation for further research projects examining the relationship between calcium micromorphology, arterial biomechanics, clinical intervention success rates, and major cardiovascular events.

Responsibilities: The selected master’s student will be responsible for:

  • Developing a co-registered dataset of CT-OCT images to train machine learning algorithms.
  • Adapting and improving a previously developed spatial transformation module for optimization-based alignment of CT and OCT image pairs.
  • Leveraging recent advances in deep learning and image registration to automatically align CT-OCT image pairs.


  • Experience in PyTorch.
  • Experience working with imaging data.
  • Knowledge of machine learning for computer vision.

Good to have:

  • Knowledge of computer-aided design.
  • Knowledge of medical image registration.
  • Knowledge of self-supervised learning
  • Knowledge of denoising diffusion models
  • Knowledge of cardiac imaging.

Prospective candidates should candidate