Open-source AI platform successfully integrated and sustained two pediatric imaging pipelines for bone length and fetal MRI at a children's hospital.
Key Details
- 1AI pipelines managed over 500 clinical tasks in five months (360 bone-length, 161 fetal MRI).
- 2Success rates: 99.2% for AI processing, 98.8% for clinical delivery.
- 3Median turnaround: 12.9 seconds for bone-length, 15.6 minutes for fetal MRI.
- 4Platform built from open-source components, running on a single on-premises server.
- 5System integrated directly with hospital clinical workflows, without commercial software fees.
- 6Future plans include adding more pediatric imaging use-cases and sharing the open-source approach.
Why It Matters
Demonstrates real-world, sustainable integration of open-source AI into pediatric radiology clinical workflows, providing a cost-effective and transparent alternative to commercial platforms. This could enable broader adoption of imaging AI, especially in pediatric settings.
Source
AuntMinnie
Related News
•Radiology Business
Meta Funds Ohio State’s Radiology AI Innovation Projects
Meta will fund Ohio State researchers to explore AI-driven advancements in radiology, including chest X-ray reporting and disease prediction.
•AuntMinnie
ChatGPT-5 Performs Poorly at Detecting Distal Radius Fractures on X-rays
ChatGPT-5 missed about half of distal radius fractures on x-rays, showing limited diagnostic capability in a real-world scenario.
•AuntMinnie
AI Triage Tool Speeds Up ICH Head CT Turnaround in ED
AI-based triage for intracranial hemorrhage on head CT reduced emergency department report turnaround by 13 minutes.