RSNA kicks off annual AI challenge

RSNA has officially launched its third annual AI competition, the RSNA Intracranial Hemorrhage Detection and Classification Challenge.

For this challenge, researchers are tasked with developing algorithms that can identify hemorrhages on head CT scans and classify the specific subtype. The winning entries will be awarded $25,000 from Kaggle.

“The goal of an AI challenge is to explore and demonstrate the ways AI can benefit radiology and improve clinical diagnostics,” Luciano Prevedello, MD, MPH, chair of the RSNA Radiology Informatics Committee’s Machine Learning Steering Subcommittee, said in a prepared statement. “By organizing these data challenges, RSNA plays a critical role in demonstrating the capabilities of machine learning and fostering the development of AI in improving patient care.”

The competition’s dataset consists of more than 25,0000 CT scans, and the first wave of that data was shared with participants on Sept. 3. The training phase of the competition lasts through Nov. 4, and the evaluation phase goes on until Nov. 11.

The winning entries will be celebrated at the AI Showcase Theater at RSNA 2019 in Chicago.