News

ACR Data Science Institute Use Cases Advance Medical Imaging AI Development

A first-of-its-kind series of standardized AI use cases from the ACR Data Science Institute (ACR DSI) will accelerate medical imaging AI adoption by ensuring that algorithms can do the following:

• address relevant clinical questions;
• be implemented across multiple electronic workflow systems;
• enable ongoing quality assessment; and
• comply with legal, regulatory, and ethical requirements.

"The ACR DSI use cases present a pathway to help AI developers solve health care problems in a comprehensive way that turns concepts for AI solutions into safe and effective tools to help radiologists provide better care for our patients," says Bibb Allen Jr, MD, FACR, who serves as CMO of the ACR DSI. 

This continually updated, freely available use case series is the product of a previously missing and collaborative framework that enables efficient creation, implementation, and ongoing improvement of radiological AI tools. Specifically, the ACR-DSI Technology Oriented Use Cases in Health Care-AI (TOUCH-AI) framework does the following: 

• leverages multispecialty, multi-industry expert panels to define clinically relevant use cases for development of medical imaging, IR, and radiation oncology AI algorithms;
• establishes a methodology and provides tools and metrics for creating algorithm training, testing, and validation of data sets around these use cases;
• develops standardized pathways for implementing AI algorithms in clinical practice;
• creates opportunities to monitor the effectiveness of AI algorithms in clinical practice through the ACR National Radiology Data Registry, the ACR DSI algorithm monitoring service, Assess-AI, and others; and
• addresses regulatory, legal, and ethical issues regarding medical imaging, IR, and radiation oncology AI.

"The ACR DSI framework promotes standardization, interoperability, reportability, and patient safety in radiological artificial intelligence development that can help usher in a new era of advanced medicine," says Keith J. Dreyer, DO, PhD, FACR, chief science officer of the ACR DSI.

For more information, visit www.acrdsi.org.