Children's Hospital of Philadelphia uses Nvidia AI for cardiac modeling

MONAI: MONAI is an open source medical imaging framework cofounded by NVIDIA that supports AI development for segmentation, labeling and analysis of scans. In this news, CHOP builds its pediatric heart modeling workflows on MONAI Label and NVIDIA's Auto3DSeg to train networks that match human-quality output from CT, MRI and ultrasound data. The framework enables the rapid, automated creation of patient-specific models that integrate with simulation tools for device planning. NVIDIA: NVIDIA develops AI hardware, software platforms and open source tools that power medical imaging and simulation at scale. In this news, the company cofounded MONAI and supports Newton and Warp frameworks that CHOP integrates for GPU-accelerated heart modeling and device simulation, connecting these with 3D Slicer and Omniverse for clinical workflows. Its collaboration provides children's hospitals access to industrial-grade infrastructure for rare-condition care. Dr. Matthew Jolley: Dr. Matthew Jolley is a cardiologist and researcher at Children's Hospital of Philadelphia who leads efforts in pediatric cardiac modeling and simulation. In this news, he directs the work applying machine learning and physics engines to create individualized heart models, helping surgeons select and fit devices for unique congenital anatomies before procedures. Jolley has advanced open source extensions like SlicerHeart to make these capabilities available across institutions. Children's Hospital of Philadelphia: Children's Hospital of Philadelphia, also known as CHOP, is a leading pediatric academic medical center focused on research and care for children with complex conditions. In this news, CHOP's cardiac modeling service uses open source AI to generate precise 3D heart models from existing scans, shifting cardiac planning from hours of manual work to seconds for routine clinical use. The hospital's team, through its IDEA Lab, is extending these tools beyond cardiac care while collaborating on national open source infrastructure. AI Integration in Care: Machine learning segmentation combined with digital twin technologies is moving from research into standard clinical workflows at children's hospitals for planning interventions in congenital heart conditions. Open Source Collaboration: Researchers at multiple children's hospitals contribute tools and extensions to shared open source platforms, enabling coordinated progress on pediatric modeling without barriers between institutions. Pediatric Device Planning: Open source physics simulation frameworks allow clinicians to test how devices will interact with a child's specific heart tissue in near real time, supporting same-day decisions for complex repairs.