As the global radiology community looks to come together at the RSNA annual meeting next week, AI is top of mind for many.  Every day I see exciting examples of AI being applied in radiology. Most recently, I’m inspired by Gleamer’s announcement that the combination of its BoneView AI and health professionals’ interpretations lowered the number of missed fractures by 29% and has received FDA and CE Mark clearance. 

‍

Yet, on the other hand, I recently met with a radiologist at one of the world’s top hospitals who told me his team is not using any AI in their radiology workflows. While we have much to be excited about, discussions like these remind me there is a lot of work still to be done to realize AI’s potential. 

‍

Partnering with deepc and Segmed to enable safe and inclusive AI at scale

‍

As AI becomes a more important and consistent part of radiology workflows, the data used to develop AI becomes more important as well. We know AI can perform differently as models move from development environments into diverse real world environments. Some sites - whether they’re collecting data from a similar machine or patient population - produce data similar to what was used to train the AI, and the AI performs well as a result. Other sites where this is not the case may see AI performance drop off. As a result, it’s critical to monitor model performance across sites, and to then use that insight to retrain underperforming models.   

‍

To make this model management and retraining easier, Centaur Labs is partnering with deepc, a leading radiology AI platform, and Segmed, a leading healthcare data provider. Through this partnership, deepc will identify when an AI model on its platform is performing sub-optimally, and will surface this information to the AI vendor. With this alert, they'll also offer on demand access to annotated data, provided by Centaur Labs and Segmed, that can be used to quickly retrain the model. As obtaining diverse, relevant data and labeling this data are two of the biggest bottlenecks in AI pipelines, providing the ability to identify model weaknesses and correct them quickly is a big step forward. This solution is under development. Read the press release here.

‍

Join us for a panel discussion about ensuring clinical AI safety at scale

‍

To kick off this partnership, Centaur Labs will participate in a panel discussion with clinical, AI and medical data leaders from Nuance Communications, deepc, Segmed and Gleamer about how to safely deploy, use and manage AI in radiology workflows. Join us on Wednesday November 30th at 3PM CT at deepc’s booth (#4565) for what promises to be an interesting discussion.

Connect with us at RSNA 2022

If you're developing AI or want to enrich your biomedical datasets, we want to meet you in Chicago!

• Schedule a meeting with us - Find a time convenient for you via the link or send us an email at contact@centaurlabs.com
• Join us for a panel discussion - Clinical, AI and medical data leaders from Centaur Labs, Nuance Communications, deepc, Segmed and Gleamer will discuss how to safely deploy, use and manage AI in radiology workflows. Join us on Wednesday November 30th at 3PM CT at deepc’s booth (#4565) for what promises to be an interesting discussion.

Learn more about how Centaur Labs annotates radiology images

‍

Centaur Labs, the leading scalable data annotation platform for the medical and life sciences industries, has extensive background annotating radiology imaging, for companies like Medtronic and leading academic provider institutions like Brigham and Women's Hospital and Memorial Sloan Kettering.

• Learn more about how Centaur Labs annotates medical images (CT, MR, X-ray, ultrasound, etc)
• Learn more about the research we’re publishing in the Annals of Emergency Medicine on annotating ultrasound - “A Novel Approach to Dataset Labeling for Deep Learning Model Development”
• Read about the work we’ve done with JIS Orthopedics to use AI to understand if patients with knee pain are candidates for TKA or UKA

‍

AI Resources at RSNA 2022

‍

RSNA is doing a lot of great work to support radiologists interested in leveraging AI in their practices, and developers using radiology data to build AI for radiologists. Below are a few resources we suggest checking out during and after the conference.

• Visit the AI Showcase Pavilion on the expo floor - connect with teams like deepc, Segmed, Gradient Health and Gleamer
• Attend the presentations in the AI Theater
• Visit the RSNAI Resource Center booth to learn more about all of RSNA’s AI programs
• Read and submit to the Radiology: Artificial Intelligence journal launched in 2019 and edited by Charles E. Kahn, Jr, MD, MS and listen to their podcast
• Register for the RSNA Imaging AI Certificate Program

‍

About Centaur Labs

Centaur Labs is the leading scalable data annotation platform for the medical and life sciences industries. The Centaur Labs platform has turned biomedical data annotation into a competitive sport - generating 2 million high quality annotations weekly from a proprietary network of tens of thousands of doctors, medical students, and other professionals, all of whom compete on the gamified platform to annotate data most accurately. Centaur Labs annotates a wide variety of data, including unstructured clinical notes, scientific papers, radiographic images, pathology slides, auscultation audio files, and more. We’re working with AI leaders at top-10 pharmaceutical companies, medical device companies like Medtronic, AI startups like Eko Health and leading academic provider institutions like Brigham and Women's Hospital and Memorial Sloan Kettering.

‍