Curriculum

The RSNA Imaging AI Certificate program is an interactive, educational program designed for radiologists by radiologists. The curriculum described on this page is for the program’s debut course—the Foundational Certificate. It’s the first step on the pathway to more advanced certificate courses and it includes six modules, with a new module released each month.

Develop your confidence and gain the experience you need to work with imaging AI products through a series of on-demand, cased-based videos and engaging, hands-on coursework.

Enrollment and pricing    FAQs

Course outcomes and learning objectives

Upon completion of the six-module curriculum, students will earn the Foundational Certificate, recognizing their understanding of AI-based tools for medical imaging and their ability to safely evaluate, deploy, monitor and use AI algorithms within their practice.

Certain portions of the program are eligible for CME credit. This activity has been approved for AMA PRA Category 1 Credits™.

Learning objectives:

  • Prepare radiologists, physicists, data scientists and clinical researchers to safely evaluate, implement, use and monitor performance of AI-based tools for medical imaging.
  • Deliver coordinated and comprehensive AI education that prepares radiologists to evaluate and use AI algorithms for clinical practice.
  • Demonstrate the steps and process of AI algorithm development.
  • Provide participants the ability to safely evaluate, deploy, monitor and use AI algorithms within their practice.

Program modules

Each of the six modules allows you to learn at your own pace through a series of short, pre-recorded videos and a variety of hands-on activities. New modules are released on the fourth Wednesday of every month through June 2022.

Module 1 — Introduction to AI in Radiology

In Module 1, you will review the history of ImageNet, machine learning definitions, origins of the field, early uses of AI in radiology, common workflow problems that can be solved using AI and insights from RSNA’s AI Challenges.

Module 2 — Data Curation

In Module 2, you will review key elements of data curation, focus on the importance of matching the data source with the intended use of the AI model, obtain an understanding of various methods for data de-identification and preprocessing steps, and apply your learning using hands-on exercises.

Module 3 — Data Annotation and Model Building

Building on concepts established in the previous two modules, in Module 3, you will review key elements of data annotation, examine machine learning models and understand key concepts for training and validating an AI model. You will be able to identify potential barriers of model building, determine the metrics used to measure performance, and apply your new skills via hands-on exercises.

Module 4 — Model Evaluation

Building on concepts established in the previous three modules, in Module 4, you will define the stages of AI model evaluation for medical imaging. This module will help you interpret the complex nature of AI evaluation in clinical practice and identify the tools necessary to help analyze AI systems. You will also have the opportunity to apply skills learned using hands-on exercises.

Module 5 — AI Ethics

Module 5 will be released Wednesday, May 25.

Module 6 — Clinical Implementation

Module 6 will be released Wednesday, June 22.

"...This was a very interactive and memorable way of truly understanding how to implement an AI project. I now have a more thorough understanding of what is required for a successful AI project."

—Enrollee, January 2022

Accreditation and Designation Statements

The Radiological Society of North America (RSNA) is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.

Physicians should claim only the credit commensurate with the extent of their participation in the activity.

Contact us

Questions? Contact us at customerservice@rsna.org.