- ACR Offers Free Healthcare Artificial Intelligence Platform
- Healthcare Artificial Intelligence Group Forms to Set Standards
The seven institutions will use the ACR AI-LAB to demonstrate the process of creating healthcare AI models from image data without the use of a programming language. Using an AI model developed at one institution, each organization will be able to evaluate and optimize the model for their own investigational needs.
“We know algorithms can underperform when deployed at sites where they weren’t trained. Now, radiologists in the pilot program will have access to AI algorithms developed outside their institutions in order evaluate a model’s performance using their own data and, as necessary, retrain the algorithm using their local data to enhance its performance,” said Bibb Allen Jr., MD, chief medical officer at the ACR Data Science Institute.
NVIDIA, Nuance Contributing Tech to the Healthcare AI Pilot
NVIDIA will provide the pilot with its Clara AI software toolkits so the institutions can perform the annotation creation, transfer learning, and pipeline integration for the healthcare AI model.
“AI technology is entering the next phase where software writes software and less computer science expertise is required,” said Abdul Hamid Halabi, director of healthcare at NVIDIA. “Radiologists have always been technology trailblazers. Working with the ACR AI-LAB to bring NVIDIA’s AI computing capability to the edge — where radiologists and their data reside — we are demonstrating that investigational AI tools can be made available to any imaging institution.”
In addition, Nuance will provide the last-mile technology to integrate AI for the participating radiologists.
“We’re proud to be partnering with local Boston and industry-wide leaders in healthcare to expedite the development of critical innovations for radiologists across the country. With the Nuance AI Marketplace, we can expand the footprint of these valuable AI solutions produced by the ACR AI-LAB initiative so others can benefit at scale,” said Karen Holzberger, vice president and general manager for healthcare diagnostics at Nuance.
ACR said that sharing local healthcare AI models from image data between institutions for fine tuning, while patient information remains securely on site at the originating institution, has not previously been done in radiology at this scale. This is due to the variability in how medical images are created, including the equipment, software, and protocols used.
Sites Will Use ACR AI-LAB to Assess AI Developed Elsewhere
The pilot sites will use ACR AI-LAB to evaluate AI developed elsewhere, modifying the algorithms to improve performance based on testing and evaluating them on local patient data. Creating the local AI models will not require ACR AI-LAB users to have programming skills. ACR AI-LAB will enable users to adjust and change AI models without having to make line-by-line changes to the underlying code.
Once the pilot is complete, the consortium is anticipated to progressively expand to more institutions and vendors interested in participating.
The investigational algorithms resulting from this project will undergo further evaluation and refinement by sites should they pursue commercialization, including obtaining appropriate regulatory clearance or approvals, according to ACR.
“ACR AI-LAB has kicked off a very exciting era of AI democratization, making it possible for healthcare institutions and industry to build customized AI models for investigative purposes without coding and without moving image data off premises. Soon all institutions interested in participating in the AI democratization revolution will have the opportunity to get involved,” said Keith Dreyer, PhD, chief science officer at ACR DSI.