RSNA announces winners of annual AI challenge

RSNA announced the winners of its third annual AI competition, the RSNA Intracranial Hemorrhage Detection and Classification Challenge, at RSNA 2019 in Chicago. Kaggle contributed $25,000 in prize money for the winning teams to share.

For the competition, conducted on a platform provided by Kaggle, researchers were asked to develop AI algorithms that could identify intracranial hemorrhages on head CT scans. The provided dataset included more than 25,000 scans from a variety of institutions.

“The results produced by the winning teams achieved really impressive performance,” Luciano M. Prevedello, MD, MPH, chair of the RSNA Radiology Informatics Committee’s Machine Learning Steering Subcommittee said in a prepared statement. “The challenge demonstrates the increasing sophistication of the imaging AI research community and the real potential of this technology to improve the efficiency and quality of care in radiology.”

The challenge’s 10 winners are:

  1. SeuTao
  2. NoBrainer
  3. takuoko
  4. GZ
  5. Keep Digging Gold
  7. Big Head
  8. 賞金で焼肉
  9. Mind Blowers
  10. VinBDI.MedicalImagingTeam

Volunteers from the American Society of Neuroradiology labeled each exam in advance of the competition.  

“The dedication of the volunteers who contributed data and who worked on annotating the dataset was truly remarkable,” Charles E. Kahn Jr., MD, MS, chair of the RIC and editor of Radiology: Artificial Intelligence, said in the same statement. “They have created a resource of tremendous value for imaging research.”

The competition was officially launched back in September. An evaluation phase occurred from Nov. 4 to Nov. 11.

Around the web

The Palo Alto giant used exams from nearly 250,000 patients to upgrade its already robust algorithm.

Exams performed using the deep learning-based reconstruction tool also maintained high image quality, experts reported Wednesday.

Stratifying exams according to risk can reduce unnecessary imaging and downstream costs of care, Hawaiian researchers reported in Radiology.

Trimed Popup
Trimed Popup