WASHINGTON, DC, May 6: The American College of Radiology® Council approved the groundbreaking ACR-SIIM (Society for Imaging Informatics in Medicine) Practice Parameter for Imaging Artificial Intelligence (AI) at ACR 2026, the College’s annual meeting in Washington, DC. The ACR Data Science Institute® (DSI) also published in the Journal of the American College of Radiology® (JACR) a landmark article detailing the technical framework for Assess-AI, the world’s first AI quality registry and data service, which helps practices monitor and improve AI performance and patient care. These seminal efforts are critical to fueling the safe, effective, and transparent use of imaging AI in clinical care worldwide.
“This first-of-its-kind ACR-SIIM Practice Parameter outlines steps that imaging facilities can follow to help implement, use, and continually update AI to successfully deploy these rapidly evolving technologies in clinical care — everything from selection, to monitoring, to continuous quality improvement,” said Tessa Cook, MD, PhD, FSIIM, FACR, chair of the practice parameter writing committee and incoming chair of the ACR Commission on Informatics.
“This leading-edge practice parameter is a vital step toward the safe, effective, and transparent acceleration of radiology AI adoption to help radiologists and allied professionals provide the highest-quality patient care,” said Elias Kikano, MD, SIIM lead representative.
The trailblazing practice parameter applies to physicians, technologists, medical physicists, informatics and IT teams, data scientists, and administrators who deploy AI or use AI results in imaging workflows. It explains how practices can choose AI tools, evaluate them before deployment, watch performance over time, and protect patient privacy. Practices who implement AI responsibly can earn the ACR Recognized Center for Healthcare-AI (ARCH-AI) designation from the first international AI facility quality assurance program and join the learning community of sites supporting each other in this journey. Both ARCH-AI and the new practice parameter guide sites in the following areas:
Set up an AI governance group with clinical, technical, and compliance leaders. Keep an inventory of all AI tools in use, including versions and intended use. Run local acceptance testing before deployment and track results. Monitor real-world model performance for drift and safety issues and define stop rules. Follow HIPAA privacy and security requirements, including strong access controls and logging. The JACR article outlines and examines the design, infrastructure, and functionality of the innovative Assess-AI service:
Assess‑AI supports post‑deployment AI governance by measuring concordance between clinical AI outputs and radiology report‑derived surrogate labels. The service integrates de‑identified data via ACR Connect with centralized analytics and benchmarking. LLM‑based prompting enables surrogate label extraction from de-identified radiology reports. Facilities can investigate discordant cases locally using ACR Forensics, completing a closed‑loop quality improvement workflow.
“Assess-AI provides facilities with interactive analytics that show how AI tools perform across their practices over time, enabling them to take control and manage performance, product selection and risk. Site data can be compared to aggregated national performance benchmarks from other sites using AI for identical use cases,” said Christoph Wald, MD, PhD, MBA, FACR, vice chair of the ACR Board of Chancellors and chair of the ACR Commission on Informatics. “This innovative data solution can also help AI model developers to improve future model versions in collaboration with customers and ultimately help imaging physicians improve patient care.”
Assess-AI is the newest ACR National Radiology Data Registry®. It currently supports multiple imaging AI use cases, including intracranial hemorrhage, pulmonary embolism, pneumothorax, large vessel occlusion, bone age, cervical spine fracture, breast density, pneumoperitoneum, tube malposition, pleural effusion, brain mass effect and obstructive hydrocephalus.
“Assess-AI monitors AI results and collects an array of contextual information, including anonymized patient demographics, exam metadata, and output from radiology reports,” said Bernardo Bizzo, MD, PhD, associate chief science officer, ACR Data Science Institute (DSI). “This is a step forward as most legacy radiology systems were never built to help sites ensure clinical AI tools perform as expected.”
Assess-AI is the latest AI-related resource offered by ACR. ACR’s portfolio of AI products includes AI Central – a tool that helps facilities make informed AI solution purchasing decisions to care for their patients.
“We look forward to expanding ACR and DSI facilitated offerings that provide tangible, real-world approaches to address AI challenges that radiologists increasingly face and ensuring that AI delivers on its tremendous promise to improve patient care,” said Woojin Kim, MD, chief medical officer, ACR DSI.
ACR, SIIM and allied stakeholders, working with leadership at the U.S. Food and Drug Administration and Congress, serve a central role in the future of radiology AI.
“Responsible use of AI in healthcare, particularly when dealing with critical patient data like medical imaging, is an ongoing process rather than a single event. It demands a dedicated team consistently applying processes supported by methods and technology,” said SIIM Board Chair Nabile Safdar, MD, “This practice parameter is based on the principles of AI science, interoperability standards, expert involvement, and methodological precision. This collaborative effort between SIIM and the ACR transforms these foundations into practical guidance that any imaging practice can implement to improve patient care now.”
