PHILADELPHIA, September 19 — The shift is happening in pediatric cardiology, and it’s happening fast. Children’s Hospital of Philadelphia is now using open source artificial intelligence tools to build anatomically precise 3D models of children’s hearts in seconds — a workflow that once took a skilled researcher four hours at a workstation. The stakes are not abstract.
About 1% of all live births involve a congenital heart defect, and no two are alike. A child born with a hole between the lower chambers of their heart, or a leaking valve in the single pumping chamber keeping them alive, needs care fitted to their exact anatomy.
Historically, the devices surgeons reached for were almost never designed with that specific child in mind. “You’ve got a one-of-a-kind kid and an off-the-shelf device,” said Dr. Matthew Jolley, a cardiologist and researcher at CHOP. “Our job is to find what fits — and modeling lets us do that before anyone goes into the cath lab or operating room.”
From four hours to seconds
CHOP’s cardiac modeling service runs on MONAI, an open source medical imaging framework cofounded by NVIDIA. It takes the images a child’s care team already has — CT scans, MRI, 3D ultrasound — and produces anatomically precise heart models in just seconds. That speed is what moves modeling out of the research lab and into routine clinical use.
Jolley joined CHOP in 2015, when 3D echocardiography was just coming online. Tools existed for modeling adult valves, but almost nothing was built for the complex, small anatomies he was treating.
His lab worked with the open source community to build SlicerHeart, an extension of 3D Slicer open source software for visualizing, segmenting and analyzing 3D medical images, and began developing workflows to model pediatric hearts and valves from multiple imaging modalities. Machine learning changed the economics of that work. Using MONAI Label and NVIDIA’s Auto3DSeg implementation, Jolley’s team trained segmentation networks on pairs of prior images and models.
The output meets the same quality standard a trained human would produce — in seconds rather than hours. “Machine learning has become just bread and butter,” Jolley said.
“As soon as we’ve made 10 or 20 image-model pairs, we train a model and start applying it.”
The clinical proof
For complex ventricular septal defects — holes between the heart’s lower chambers — CHOP now models routinely before surgery. One early case made the value clear. A child had already undergone two failed repair attempts, with surgeons unable to locate the defect with traditional methods.
The 3D model clarified the anatomy. The repair succeeded on the first try.
For cases like these, Jolley said, cardiac modeling has moved from research to standard of care. The approach is spreading well beyond Philadelphia. More than 20 children’s hospitals across the U.S. now run cardiac modeling programs.
At Boston Children’s Hospital, modeling supports more than half of all cardiac surgeries — roughly 500 cases a year.
Next: simulating the device inside the heart
Visualization alone isn’t the end goal. Jolley’s team wants to know not just what a child’s heart looks like, but what will happen when a device is deployed inside it — before any procedure begins. That’s where Newton comes in.
Newton is an open source physics engine built on the NVIDIA Warp Python framework that runs physics simulations on GPUs. CHOP is working with NVIDIA and the open source community to build biomechanics-focused simulation frameworks with Warp that can be brought into Newton, originally intended for simulation-based AI robot training.
Once integrated with 3D Slicer and SlicerHeart, those frameworks can help doctors understand tissue material properties that determine how a device will deploy in a given heart. And the ambition doesn’t stop at the heart. Where this work began in cardiac care, CHOP is now aiming to apply the same tools across multiple disciplines through the IDEA Lab, part of the hospital’s Morgan Center for Research and Innovation.
Watch this space. The trend underneath is bigger than one hospital: open source imaging frameworks plus GPU-accelerated physics are turning one-of-a-kind anatomy into something you can model, test and repair on a screen before anyone touches a scalpel.
