Refresher Courses are sessions captured at past RSNA Annual Meetings focusing on themes of health care reform, payment models, research and innovation, patient-centered radiology, and advances in the different imaging modalities. Refresher Courses are targeted to diagnostic, interventional and oncologic radiologists and are designed to improve knowledge and competence in responding to the challenges and advancements in the field of radiology.

For ongoing education and resources, please visit RSNA’s Online Learning Center.

Content Areas (Codes):
The following Content Areas will be printed on the certificate for this course:

• Artificial Intelligence
• Informatics

Learning Objectives:

• Explain familiar fundamentals of AI experiment design and nomenclatures used and their importance for generalizability and future algorithm certification and deployment.
• Discuss the rationale and importance of separation of datasets into training, validation, and test sets for generalizability.
• Explain and become familiar with different internal cross validation techniques.
• Explain and become familiar with different sources of bias and the importance of robust design for mitigating bias and enhancing generalizability.
• Illustrate different examples illustrating impact of proportions, dataset size, and data variety for algorithm generalizability.
• Develop a basic understanding of data harmonization strategies for improving generalizability.
• Describe advanced approaches such as scan pre-screening for identification of outlier for improving generalizability.
• Summarize the importance of validation for future certification and deployment.
• Discuss the potential importance of well structured or auditable platforms and approaches for pre-certification.
• Develop a basic understanding of potential deployment strategies and challenges for AI algorithms, contrasting with traditional CAD.
• Review the challenges and principles of validation techniques in AI.
• Describe the main validation techniques for machine learning.
• Describe the main validation techniques for deep learning.
• Evaluate strategies for setting up validation studies in machine/deep learning.
• Identify what open source libraries and toolkits can be used for validating AI methods in radiology.
• Describe key attributes of experimental design to facilitate publication of results.
• Review US regulatory process for the certification of algorithms and how they influence experimental design.
• Describe systems necessary for the design and deployment of AI/machine learning models.

This enduring material is estimated to take 45 minutes to complete.

Start Date: 5/19/2021
End Date for CME Eligibility/Online Expiration Date: 5/18/2024

This educational activity was originally presented at the RSNA 2020 Annual Meeting and Scientific Assembly.

Faculty:

• Samuel Kadoury, PhD
• Reza Forghani, MD, PhD
• Curtis P. Langlotz, MD, PhD

Disclosure Statements:
The ACCME requires that the RSNA, as an accredited provider of CME, disclose the relevant financial relationships of the planners, faculty, and any other individuals in a position to control content of this activity. If there is a relevant financial relationship that has been disclosed please find it below:

• Matthew S. Davenport, MD: Royalties, Wolters Kluwer NV.
• Alexander R. Guimaraes, MD, PhD: Speakers Bureau, Siemens AG; Consultant, Takeda Pharmaceutical Company Limited, Merck & Co, Inc, Agfa-Gevaert Group, PAREXEL International Corporation.
• Ajay Gupta, MD: Support, Siemens AG, General Electric Company.
• Christopher P. Hess, MD, PhD: Research, Siemens AG; Consultant, General Electric Company.
• Vincent B. Ho, MD, MBA: Research collaboration, General Electric Company.
• Maxine S. Jochelson, MD: Speaker, General Electric Company; Consultant, Bayer AG.
• Jeffrey S. Klein, MD: Editor with royalties, Wolters Kluwer NV.
• Petra J. Lewis, MBBS: Committee Member, CairnSurgical.
• Katherine E. Maturen, MD: Royalties, Reed Elsevier, Wolters Kluwer NV.
• Matthew A. Mauro, MD: Board Member, Boston Scientific Corporation; Investor, Medtronic plc, Bayer AG.
• Christine O. Menias, MD: Royalties, Reed Elsevier.
• Charles E. Ray Jr, MD, PhD: Consultant, Medtronic plc; Editor with royalties, Thieme Medical Publishers, Inc.
• Evis Sala, MD, PhD: Co-founder, Cambridge AI Health; Speakers Bureau, GlaxoSmithKline plc.
• Jorge A. Soto, MD: Royalties, Reed Elsevier.
• Bachir Taouli, MD: Research Grant, Bayer AG, Takeda Pharmaceutical Company Limited, Regeneron Pharmaceuticals, Inc; Consultant, Alexion Pharmaceuticals, Inc, Bayer AG.
• Ioannis Vlahos, MRCP, FRCR: Director, Grayscale Ltd; Co-owner, Grayscale Ltd.
• Abbey Winant, MD: Spouse, Research Grant, Bristol-Myers Squibb Company, Novartis AG; Spouse, Research Consultant, Tango Therapeutics.
• Judy Yee, MD: Research Grant, EchoPixel, Inc, Koninklijke Philips NV, General Electric Company.
• Margarita L. Zuley, MD: Investigator, Hologic, Inc.
• Reza Forghani, MD, PhD: Researcher, General Electric Company; Institutional research collaboration, General Electric Company; Consultant, General Electric Company; Speaker, General Electric Company; Founder, 4intelligent Inc; Stockholder, 4intelligent Inc, Real-Time Medical, Inc.
• Samuel Kadoury, PhD: Research grants, Elekta Ltd.
• Curtis P. Langlotz, MD, PhD: Advisory Board, whiterabbit.ai, Galileo CDS Inc, Nines.ai; Stockholder, whiterabbit.ai, Galileo CDS Inc, Nines.ai, Bunker Hill Inc; Board of Directors, Bunker Hill Inc; Research Grant, General Electric Company, Siemens AG, Koninklijke Philips NV, Alphabet Inc.

All other individuals in control of content have indicated that there are no relevant financial relationships with any commercial interests to be disclosed.

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.

This enduring material can be applied towards the ABR MOC Part 2 requirement (CME).

To earn CME credit, participants must watch the full-length of the recording and complete the course evaluation.

The RSNA designates this enduring material for a maximum of 0.75 AMA PRA Category 1 Credit(s)™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.

Price:
Non-member Rate: $50.00
Member Rate: $0.00

Refund / Exchange Policy:
RSNA will not issue any refunds or exchanges for online only versions of educational products or activities purchased online. Please review the entire product or activity description prior to purchase.

RSNA Disclaimer:
The opinions or views expressed in this activity are those of the presenters and do not necessarily reflect the opinions, recommendations or endorsement of the RSNA. Participants should critically appraise the information presented and are encouraged to consult appropriate resources for information surrounding any product or device mentioned. Information presented, as well as publications, technologies, products and/or services discussed, are intended to inform the learner about the knowledge, techniques, and experiences of RSNA faculty who are willing to share such information with colleagues. The RSNA disclaims any and all liability for damages to any individual user for all claims which may result from the use of said information, publications, technologies, products and/or services, and events.