RSNA launches Cervical Spine Fracture AI Challenge
July 29, 2022 – The Radiological Society of North America (RSNA), in collaboration with the American Society of Neuroradiology (ASNR) and the American Society of Spine Radiology (ASSR), launched the “RSNA Cervical Spine Fracture AI Challenge” to explore has gone. Can Artificial Intelligence (AI) be used to help detect and localize cervical spine injuries?
The international imaging dataset being compiled and curated for the challenge is the largest and most diverse of its kind, including detailed clinical labels, radiologist annotations and segmentation.
“A unique aspect of this year’s RSNA AI Challenge is the great diversity of the data,” said Errol Kolak, MD, FRCPC, assistant professor in the Department of Medical Imaging at the University of Toronto in Ontario, Canada. “Our team has compiled a large dataset of cervical spine CTs from 12 institutions in nine countries on six different continents. In addition, this year’s competition will feature data annotated in a variety of ways, including test level labels, vertebral body segmentation, and image level bounding boxes. ,
More than a million vertebral fractures and more than 17,000 spinal cord injuries occur annually in the United States. The most common site of spinal fracture is the cervical spine located in the neck. The elderly population is particularly vulnerable, and fractures may be more difficult to detect on imaging due to susceptible degenerative disease and osteoporosis.
Imaging diagnosis of adult spinal fractures is now almost exclusively done with computed tomography (CT) rather than X-rays. Prompt detection of the location of any vertebral fracture is essential to prevent neurological deterioration and paralysis after trauma. Researchers hope that AI can help to identify and localize fractures faster.
To create the Ground Truth dataset, the Challenge Planning Task Force collected imaging data from 12 sites on six continents, including more than 1,400 CT exams with diagnosed cervical spine fractures and an approximately equal number of negative tests. ASNR and ASSR’s spine radiology specialists provided expert image level annotation to these images to indicate the presence, vertebral level and location of any cervical spine fractures.
For the Challenge Competition, contestants will attempt to develop machine learning models that match radiologists’ performance in detecting and localizing fractures within the seven vertebrae containing the cervical spine.
“Machine learning models that have been developed as part of this challenge could help advance patient care by helping radiologists and other clinicians detect fractures, which can be a difficult task,” said Dr. Kolak said. “These models may be of particular value in under-served areas with limited access to specialist neuroradiologists. In addition, these models enhance patient care by prioritizing positive CT scans for radiologist review in high-volume clinical settings. can help.”
The RSNA Cervical Spine Fracture AI Challenge is being held on a platform provided by Kaggle, Inc., and is open to all. The competition phase will end in October. A total of $30,000 will be awarded to the top 10 performing contestants.
Winners will be recognized at the AI Showcase during the RSNA’s 108th Scientific Assembly and Annual Meeting at McCormick Place Chicago (RSNA 2022, November 27 – December 1).
For more information about the challenge, visit RSNA.org/AI-image-challenge
More RSNA22 Conference Coverage