The American College of Radiology (ACR) Data Science Institute® (DSI) has launched ACR AI-LAB, a free software platform to help local radiologists participate in the creation, validation, and use of artificial intelligence (AI). Specifically, ACR personnel say, the ACR DSI is committed to unlocking the potential of AI and helping radiology advance this technology throughout health care.
As part of that strategy, ACR AI-LAB will provide radiologists with tools to develop AI algorithms at their own facilities, using their own data, to meet their own clinical needs. All of this will be done securely behind their own institutional firewalls, according to the ACR. By combining ACR’s member network, its institutional connectivity to facilities and an industry community working to advance AI in healthcare, radiologists will be able to engage in all phases of the radiology AI development process, the ACR says.
Through a freely available, open, vendor-neutral framework, radiologists will be able to learn about AI, contribute AI datasets, share AI algorithms, evaluate AI models, develop AI models, and even combine these models though transfer learning and model ensembles to address their local clinical needs. The ACR AI-LAB™ platform will also support any future FDA initiatives that use real world data for local adaptive learning for algorithm improvement and monitoring of continuously learning algorithms, according to ACR personnel.
“By enabling radiologists to actively participate in all aspects of AI development, we can expect to see high impact healthcare solutions grow rapidly,” says Bibb Allen Jr., MD, FACR, ACR DSI chief medical officer. “This new initiative fills existing gaps and permits direct participation throughout the AI development life-cycle.”
Keith Dreyer, DO, PhD, FACR, ACR DSI chief science officer, also spoke out about ACR AI-LAB, commenting: “Acquiring the necessary large amounts of patient data for algorithm training has been a huge problem for developers up to this point. Consequently, AI has been slow to develop and has not spread widely to improve patient care. Enabling radiologists to develop AI on-premises, at their own institutions, will unlock massively larger data stores available for the development of AI. This will rapidly expand the AI solutions available to us all.”
The initial version of ACR AI-LAB will be shown at the 2019 ACR Annual Meeting in Washington, D.C., from May 18-22.