AJR Live Banner

About AJR Live Webinars

AJR Live webinars are interactive, online educational sessions featuring expert discussions on high-impact articles and key topics from the American Journal of Roentgenology. Join renowned speakers and moderators to explore evolving practices, engage in debates, and ask questions in real-time.

Registration for all AJR Live webinars is completely free. Secure your spot today to participate in the conversation and earn CME credit. Access to both the live broadcast and the on-demand recording is included.

Get Notified: Don't want to miss the next one? Sign up for email alerts when new topics are announced.

AJR Live Webinar

Artificial Intelligence for CT and MRI Protocoling

Speakers: Scott Adams, MD, PhD and Ethan Sacoransky, MD
Moderator: Stella Kang, MD

CT and MRI have shown substantial increases in utilization across health care settings. Before a CT or MRI examination is performed, a radiologist (or other designated practitioner) protocols the examination. This task entails reviewing the imaging requisition and potentially additional information sources (e.g., the EMR), ensuring imaging appropriateness, selecting from a set of prespecified configurations of acquisition parameters, potentially prescribing modifications to these parameters, and considering safety issues (e.g., relating to renal insufficiency or contrast media allergies). Protocol selection includes determination of whether to use various forms of contrast media and, for studies using IV contrast media, the timing of the contrast-enhanced phases. This process directly influences examinations’ diagnostic yield. Protocoling remains resource-intensive and time-consuming. This study evaluated the performance of traditional ML models, BERT models, and LLMs for automated CT and MRI protocoling.

  • Time: Tuesday August 11, 2026 at 12:00–1:00 pm, Eastern Time
Register Now
Registration includes access to the live session and on-demand recording.

Learning Objectives

  1. Evaluate performance of traditional machine learning (ML) models, bidirectional encoder representations from transformers (BERT) models, and large language models (LLMs) for automated CT and MRI protocoling.
  2. Discuss findings and the ongoing exploration of LLMs for protocoling.
Disclosure of Commercial Interest
  • Stella Kang has nothing to disclose.
  • Scott Adams has nothing to disclose.
  • Ethan Sacoransky has nothing to disclose.
  • Andrew Rosenkrantz has nothing to disclose.
  • Samantha Schulz has nothing to disclose.
Accreditation Statement

The American Roentgen Ray Society (ARRS) is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education activities for physicians.

The ARRS designates this live activity for a maximum of 1.00 AMA PRA Category 1 Credit(s)™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.