Personalized treatment for cardiovascular diseases
Personalized treatment, which tailors healthcare decisions to each individual, has the potential to improve treatment efficacy. By considering patient-specific information, such as medical images, in our lab, we aim to create more efficient and effective methods for treating cardiovascular diseases. Our numerical simulations are a crucial part of this effort, providing insights into the best approach for each individual patient.
Objective
Develop personalized treatments for cardiovascular diseases based on patient-specific numerical models
Skillsets
-
Computational fluid dynamics and finite element modeling
-
Signal and image processing
-
Machine learning
Amirtahà Taebi
PI
Current members involved:
Hover the mouse over the figure to see details.
Deep Learning
We use deep learning in different steps of our numerical simulations, from image segmentation to prediction of the results.
Medical Imaging and Clinical Measurements
Our goal is to develop patient-specific solutions. Therefore, for each patient, we use medical images and clinical measurements to create numerical models that accurately represent the patient's health status.
Computational Domain
We use image processing and machine learning techniques to extract the geometry of interest from the medical images for every patient.
Mesh Generation
Boundary Conditions
The play an important role in obtaining accurate results. We use patient-specific clinical measurements, e.g., using echocardiography or magnetic resonance imaging, to determine the boundary conditions.
Simulation Results
We look into various hemodynamics parameters such as velocity profiles, wall shear stresses, and acoustic signatures.
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 ... Read more!
doi 10.3390/fluids7060197