Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Copyright © 2025. All rights reserved by Centaur Labs.
Blog
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.
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 suboptimally 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.
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.
Centaur Labs, the leading scalable data annotation platform for the medical and life sciences industries, has extensive experience annotating radiology imaging for companies like Medtronic and leading academic provider institutions like Brigham and Women's Hospital and Memorial Sloan Kettering. 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.
Worked with Volastra Therapeutics to annotate cancer cell images, supporting AI models in quantifying chromosomal instability and advancing cancer research.
A Centaur Labs study found that disease prevalence and expert feedback significantly influence diagnostic accuracy in dermatology, highlighting the need for contextual data and ongoing guidance to reduce errors and improve clinical decision-making.
Learn more about how Centaur Labs is working with the Brigham and Women's Hospital team to develop multiple AI applications for point of care ultrasound.