Assessing AI for Imaging in Healthcare

Events /Assessing AI for Imaging in Healthcare


Algorithms can change the radiology game—but they’re not one size fits all. Join Dr. Anouk Stein and Haley Wight for a compelling look into the validation of algorithms in relation to clinical artificial intelligence, presented by NTT DATA Healthcare & Life Science.

Thanks to advancements in deep learning and imaging analytics, sophisticated algorithms have the potential of transforming radiology, promising big productivity gains with reduced diagnostic errors. However, if not validated properly, these AI algorithms can increase the risk of systemic errors. What does that mean for you? To mitigate the risk that comes with adopting new technology, you’ll need an understanding of its limitations through a high level of validation. To fully benefit from the right AI tool, you should “try before you buy” and make sure the algorithm works well on your unique patient population. Make plans now to watch this one hour webinar!

What You’ll Learn

      How can artificial intelligence better radiology?
      Is comparing accuracy, sensitivity and specificity score enough?
     What should I consider regarding data mismatch and bias?
     What does interpretability mean for machine learning?
     What are recommendations for validation of AI for your practice?

Our Panelists

Anouk Stein headshot

Anouk Stein
M.D., Board Certified in Diagnostic Radiology

Dr. Stein brings her unique blend of expertise in medicine and artificial intelligence. As a board-certified radiologist with additional instruction in computer programming, she’s been with for over two years. She has been involved with several major AI projects and has published articles on creating large annotated medical imaging datasets.

Haley Wight headshot

Haley Wight
Data Scientist
NTT DATA Healthcare and Life Sciences

Haley leverages big data and machine learning solutions for pharmaceutical and medical device companies. Her expertise has led her to bioinformatics research at the National Cancer Institute and U.S. Department of Agriculture where she implemented novel network clustering approaches and web-based visualization tools to allow user interaction with large, biological data.