RSNA Cervical Spine Fracture AI Challenge (2022)
The 2022 RSNA Cervical Spine Fracture AI Challenge invited participants to explore whether AI can be used to aid in the detection and localization of cervical spine fractures.
About the 2022 AI Challenge
Annually in the U.S., an estimated 1.5 million vertebral compression fractures occur — the most common located in the cervical spine where only 25–33% of incident radiographically identified vertebral fractures are clinically diagnosed.
Quickly detecting and determining the location of vertebral fractures is essential to prevent neurologic deterioration and paralysis after trauma, which is why RSNA, the American Society of Neuroradiology (ASNR) and the American Society of Spine Radiology (ASSR) co-hosted the Cervical Spine Fracture AI Challenge on the Kaggle competition platform.
Participants were challenged to develop machine learning models that matched the radiologists' performance in detecting and localizing fractures in the seven vertebrae that comprise the cervical spine.
About the imaging data
To create the ground truth dataset, the challenge planning task force:
- Collected imaging data sourced from 12 sites on six continents.
- Included over 1,400 CT studies with diagnosed cervical spine fractures and an approximately equal number of negative studies.
- Spine radiology specialists from the ASNR and ASSR provided expert image level annotations to indicate the presence, vertebral level and location of any cervical spine fractures.
Recognition for winning teams
The winning teams were recognized at an event during RSNA 2022 (Nov. 27 – Dec. 1). A $30,000 prize was awarded and split between the top teams.
Results
Access the RSNA Cervical Spine AI Challenge results on the Kaggle website.
Contact us
For questions, contact us at informatics@rsna.org.