Children's hospital uses open-source AI to model young hearts in seconds

Children's Hospital of Philadelphia says open-source AI turns routine scans into 3D heart models in seconds. Surgeons plan better, but device simulation is still being built and results are the hospital's own.

By Utopia Data & AI Team6 min read

A man in a white lab coat hands a small red 3D-printed heart model to a man in a dark suit and blue tie, while a younger man in a lab coat watches in a laboratory
Licensed photo. An FDA engineer shows then FDA Commissioner Scott Gottlieb a 3D-printed model of an individual patient's heart at the agency's device laboratories in Maryland, November 2017. It is not a CHOP model and involves no AI. Photo: Michael J. Ermarth/FDA/Wikimedia Commons, public domain[6][1]

In brief

  • NVIDIA reported on 15 September 2026 that Children's Hospital of Philadelphia builds patient-specific heart models from routine scans in seconds, using the open-source MONAI framework.[1][3]
  • The hospital says a model that took a researcher about four hours now takes seconds, and it expects about 200 modelled cases this year.[1]
  • In Malaysia, IJN performs 800 to 900 child and congenital heart operations a year, over half the national caseload, according to its surgeons.[4]

What the hospital reported

Every child born with a heart defect has a slightly different heart, yet surgeons often have to choose from off-the-shelf devices. Children's Hospital of Philadelphia, known as CHOP, says open-source AI now lets its team build an exact 3D model of a child's heart from existing scans in seconds, before anyone enters the operating room.[1]

The account comes from an NVIDIA blog post that quotes CHOP cardiologist Dr Matthew Jolley. The figures are the hospital's own and have not been independently audited. The tools behind them, MONAI and SlicerHeart, are free and openly licensed.[1][3][2]

A tall glass-fronted hospital building with a white steel lattice and coloured panels behind the glass, its roofline sign reading The Children's Hospital of Philadelphia, under a clear blue sky
Licensed photo. The main building of Children's Hospital of Philadelphia, March 2024. CHOP says it expects about 200 modelled heart cases this year. The photo shows no part of the modelling service. Photo: Ajay Suresh/Wikimedia Commons, CC BY 2.0[7][1]

From routine scans to 3D models

About 1% of live births involve a congenital heart defect, and no two are alike. CHOP's cardiac modelling service takes CT scans, MRI and 3D ultrasound that a child's care team already has, and produces anatomically precise heart models. The service runs on MONAI, an open-source medical imaging framework cofounded by NVIDIA.[1]

Jolley's lab first built SlicerHeart, a free extension to the 3D Slicer imaging software, to model small and complex child hearts. Each model once needed hours of work at a workstation. The team then trained segmentation networks with MONAI Label and NVIDIA's Auto3DSeg, starting once it had 10 or 20 image and model pairs.[1][2]

What changed for surgeons

CHOP says the AI output meets the quality a trained person would produce, in seconds instead of about four hours. For complex holes between the heart's lower chambers, known as ventricular septal defects, the hospital now models routinely before surgery. It expects about 200 modelled cases this year.[1]

The post describes one child who had two failed repair attempts because surgeons could not locate the defect. A 3D model made the anatomy clear and the next repair succeeded first time. More than 20 US children's hospitals now run cardiac modelling programmes, and Boston Children's Hospital uses modelling for roughly 500 operations a year.[1]

The pink and cream Institut Jantung Negara building with blue IJN logos and a hiring banner, seen from a footbridge above rows of parked motorcycles on Jalan Tun Razak
Licensed photo. Institut Jantung Negara on Jalan Tun Razak, Kuala Lumpur, January 2025. IJN performs 800 to 900 child and congenital heart operations a year. It is not linked to CHOP's work. Photo: Wiki Farazi/Wikimedia Commons, CC0[8][4]

Device simulation is still being built

The next goal is to predict what a device will do inside a particular heart. CHOP is working with NVIDIA and the open-source community on biomechanics tools for Newton, an open physics engine built on NVIDIA's Warp framework. The aim is to cut device simulations that can take four hours, or a whole night, to near real time.[1]

That work is early. CHOP has begun using Warp and Newton features for closure devices that seal holes in children's hearts and hopes to extend them to replacement valves. A link to 3D digital twins and virtual reality is still in development. Jolley says the patient group is too small and varied for normal commercial investment, which is why open source matters.[1]

What it could mean for Malaysian heart care

Surgeons at the National Heart Institute, IJN, wrote in 2024 that Malaysia has about 500,000 births a year and roughly 5,000 babies with congenital heart disease. Ministry of Health data put the number needing surgery at 2,000 to 3,000 a year. IJN performs 800 to 900 of these operations, and eight government hospitals add 250 to 470.[4]

The same paper says elective cases at IJN wait at least a year, and that interventional cardiologists close some holes with devices to free operating theatre time. Faster planning tools could help in principle, but no Malaysian hospital is named in CHOP's work, and local use would need clinical validation.[4][5]

Why Malaysia should care

About 5,000 Malaysian babies are born with heart defects each year, and IJN's elective surgery waitlist runs at least a year. The tools CHOP uses are free, but no Malaysian hospital is named in this work.

Cardiac teams

Free tools for surgical planning.[2][3]

Practical move: Trial models on past cases.

Hospital managers

Planning time may shrink.[1]

Practical move: Measure theatre time before and after.

Parents

Plans can fit a child's heart.[1]

Practical move: Ask surgeons about 3D planning.

What Malaysians can do now

  1. Cardiac and imaging teams can test MONAI and SlicerHeart on anonymised past cases before any clinical use.
  2. Hospitals considering the tools should record planning time and repair outcomes, so any benefit is measured locally rather than assumed.
  3. Parents facing surgery for a child can ask whether 3D imaging or modelling is part of the plan.

What we still do not know

What we still do not know

  • Whether peer-reviewed studies show better outcomes.
  • How accurate device simulations prove in live patients.
  • Whether any Malaysian centre plans to adopt the tools.

Sources

  1. Heart of the Matter: How a Major Children's Hospital Uses Open Source NVIDIA AI for Cardiac CareNVIDIA, 15 September 2026
  2. SlicerHeart: 3D Slicer extension for cardiac analysisSlicerHeart project on GitHub
  3. MONAI - Medical Open Network for AIProject MONAI
  4. Surgery for CHD in Malaysia: setting standards for lower and middle-income countriesIndian Journal of Thoracic and Cardiovascular Surgery (via PubMed Central), 23 August 2024
  5. No 1 Paediatric Heart Hospital In MalaysiaInstitut Jantung Negara, 14 December 2023
  6. File:Commissioner Gottlieb Tours CDRH Labs - 9055 (25313517668).jpgWikimedia Commons, 28 November 2017
  7. File:Children's Hospital of Philadelphia (CHOP) (53590379823).jpgWikimedia Commons, 1 March 2024
  8. File:IJN, Kuala Lumpur 20250121 122252.jpgWikimedia Commons, 21 January 2025

All three images come from Wikimedia Commons, with licence, author and capture date read live from the Commons API on 28 September 2026: one US government public-domain photograph, one Creative Commons photograph and one CC0 photograph. None shows CHOP's modelling service, its software or any patient, and each caption states what the image actually shows. No image was generated, composited or retouched; source-preserving framing was the only change made.

Last fact check: 28 September 2026. Factual correction? devteam.utopia@gmail.com.

More AI News

Back to AI NewsAll 201 stories