AI-powered personalized heart and blood-flow modeling from medical images

SCH: Efficient Image-based Hemodynamic Modeling via Physics-integrated Bayesian Deep Learning

NIH-funded research Cornell University · NIH-11376133

Using AI to turn heart and vessel scans into fast, personalized blood-flow maps to help people with heart or vascular conditions get clearer treatment information.

Quick facts

Grant typeR01 grant
Study typeNIH-funded research
Funding institutionCornell University NIH-funded
Lab location1 site (Ithaca, United States)
Project IDNIH-11376133 on NIH RePORTER

What this research studies

This project builds AI tools that automatically convert your CT, MRI, or ultrasound images into 3-D models of your heart and blood vessels and then runs fast computer simulations of blood flow and wall stress. The team combines physics-based knowledge with deep learning so the results are both rapid and grounded in real blood-flow principles. They will add Bayesian methods to show how certain each prediction is and create visual tools so doctors and patients can explore many simulated scenarios. The approach aims to reduce the manual work, time, and computational cost of current image-based modeling.

Who could benefit from this research

Good fit: Ideal candidates are people with heart or blood-vessel conditions who have recent CT, MRI, or ultrasound images and are willing to share those images for analysis.

Not a fit: People without cardiovascular problems or without usable medical imaging are unlikely to benefit directly from this work.

Why it matters

Potential benefit: If successful, this could give patients quicker, more reliable personalized blood-flow information to guide diagnosis and treatment choices.

How similar studies have performed: Related AI methods have shown promise for speeding up blood-flow modeling, but the specific blend of physics-integrated, mesh-aware deep learning with Bayesian uncertainty quantification is relatively new.

Where this research is happening

Ithaca, United States

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.