A team of researchers from the University of California, San Francisco's Department of Radiology and Biomedical Imaging and Center for Intelligent Imaging (ci2) developed a primer for the use of artificial intelligence (AI) in radiology.
The researchers, Ali Tejani, MD, Andreas Rauschecker, MD, PhD, Marc Kohli, MD, and John Mongan, MD, PhD, present their findings in "AI for Radiology: A Primer Part I. From Idea to Algorithm," published in RSNA: Radiology.
This primer is the first in a series providing a foundation in AI literacy for radiologists. Understanding the foundational workings of AI algorithms is critical for making informed decisions when using AI as a tool, enabling recognition of when AI may fail or be prone to bias.
In part I of the primer, the ci2 researchers explain common steps of AI development, identify clinical scenarios for AI solutions and determine performance metrics.
The series of articles will examine paradigms for delivering to end users and their interactions with AI results, explain barriers to AI integration from the perspectives of various imaging workflow stakeholders, and detail post-deployment considerations for AI monitoring and regulation after model procurement and deployment in practice.
"Investing in AI literacy enables wider implementation by empowering radiologists to identify practical limitations that may be overlooked, ensuring safe and effective integration in practice," the authors write.
Visit the UCSF ci2 blog to read more about research and news.
