In recent years, deep learning has shown impressive performance in medical imaging analysis. However, for a model to be useful in the real world, it needs to be valid and trustworthy. The uncertainty quantification (UQ) methods determine the calibrated level of a model’s confidence in its predictions. Moreover, UQ can demonstrate biases caused by overconfidence or lack of confidence in the model’s predictions. By enabling UQ in medical deep learning models, users can be alerted when a model does not have enough information to make a decision. Consequently, a medical expert could reevaluate the uncertain cases, which would eventually lead to gaining more trust in the model.

Objectives

  • Discuss the relationship between output, probability, and uncertainty of predictive models
  • Identify the various types of uncertainty that affect model predictions and underline its pivotal role in the outcomes of predictive models
  • Define the broad categories of UQ techniques and gain insights into use cases of UQ
  • Identify the challenges involved in performing UQ and explore potential solutions

Watch for Free without credit on YouTube!

Additional Resources

CE Credit

SIIM has approved this activity for 1.0 hours of SIIM IIP Credits towards certification and re-certification by the American Board of Imaging Informatics (ABII).

To receive credit, registrants must view the entire webinar and then complete the post-webinar survey. Webinar credits will only be awarded one time per webinar view, regardless of if the learner watches the content live or on-demand.

Note: In order to receive credits for any events/learning you attend you must select your eligible credit types found in the CE & Certification section of your MySIIM Account profile.

To access the webinar, once you are registered navigate to My Learning in your My SIIM Account profile.    

Not a member?  Join SIIM Today and Save! 

DATE

Nov 2, 2023

Credit Amount

1.0

Credit Type

IIP

Non-Member Cost

$30

Member Cost

$0

Delivery Type

  • On-Demand

Audience Type

  • Clinician
  • Developer
  • Imaging IT
  • Researcher/Scientist
  • Vendor

Richard J. Bruce, MD

Associate Professor of Radiology, Vice chair of Informatics

University of Wisconsin Madison

Bradley J. Erickson, MD, PhD, CIIP, FSIIM

Professor of Radiology & Director of AI Lab

Mayo Clinic, Rochester

Shahriar Faghani, MD

Postdoctoral Research Fellow

Mayo Clinic, Rochester

Mana Moassefi, MD

Postdoctoral Research Fellow

Mayo Clinic, Rochester Moderator

Webinar

POCUS Has Arrived: Does Your System’s Workflow Need to Catch Up?

Nov 19, 2024

Point-of-care ultrasound (POCUS) is transforming clinical workflows, allowing clinicians to make quick, informed decisions at the bedside. But as POCUS…

Webinar

Women in Imaging Informatics – Spotlight on Imaging Informatics Leader Dr. Katherine Andriole

Nov 7, 2024

Join us as we kick off a series of webinars spotlighting women in imaging informatics with Dr. Katherine Andriole, a…

Webinar

The Value of Clean Data – Tips and Tricks

Oct 23, 2024

This presentation will highlight the critical role of high-quality medical imaging metadata in optimizing AI algorithms. It will emphasize the…