ACR 2019 Attendees to Get a Taste of AI

Am. College of Radiology-AMCLC

Dr. Allen

This post was contributed by ACR Data Science Institute Chief Medical Officer Bibb Allen, MD, FACR, and Chief Science Officer Keith Dreyer, DO, PhD, FACR.

 The American College of Radiology (ACR) Data Science Institute (DSI) is developing a framework for radiologists in all practice settings to use artificial intelligence (AI) tools to help improve performance and efficiency.

As a first step toward allowing local radiologists to take part in AI development, the ACR DSI will allow attendees at the May ACR 2019 annual meeting to use ACR DSI data and cloud-based computing to gain experience annotating cases and see how AI algorithms can improve with additional training.

  • Attendees can assess breast density using ACR cases and annotated cases which will then be used to train an algorithm to perform the same function. The more members who take part in contributing cases, the more accurate the algorithm will become.

    ACR_325

    Dr. Dreyer

  • In order to specifically target trainees, over the summer, radiology residents will be invited to participate in a 60-day “Resident Breast Density Challenge” where they will use ACR DSI-hosted data and computing to train and develop an ACR DSI Breast Density Algorithm.

The ACR DSI is enabling radiologists to shape the future of radiology technology and patient care.

We hope that you will take advantage of the opportunities this process will bring in 2019. 

Please share your thoughts in the comments section below and join the discussion on Engage (login required).

 

Leave a Comment

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s