RSNA announces winners of abdominal trauma AI challenge
The Radiological Society of North America (RSNA) has revealed the winners of a challenge that tasked researchers with developing artificial intelligence (AI) models capable of detecting severe injuries to the abdomen.
The RSNA Abdominal Trauma Detection AI Challenge focused on the detection and classification of traumatic injuries across various organs, including the liver, spleen, kidneys and bowel. RSNA calls the competition its “most ambitious AI challenge to date”.
The international imaging dataset was provided for the models to use. Data included CT exams of the abdomen from 23 sites in 14 countries on six continents, featuring over 4,000 scans. Cases both with and without injuries were included in the mix.
“The dataset is annotated at multiple levels, including the presence of injuries in four solid organs with injury grading, image level annotations for active extravasations and bowel injury, and voxelwise segmentations of each of the potentially injured organs,” Jeff Rudie, MD, PhD, of the Department of Radiology at the University of California, San Diego, said in a statement.
The challenge, launched over the summer and hosted on a platform provided by Kaggle, attracted 1,125 teams worldwide, all seeking to develop machine learning models that match the proficiency of a trained radiologist in detecting, locating and classifying the severity of abdominal injuries.
The competition concluded in October, and the winning solutions were assessed by a team of volunteer AI experts. The nine teams submitting the highest-scoring algorithms shared $50,000 in total prize money:
- Team Oxygen
- On Strike
- [Aillis.jp] Yuji Ariyasu
- Sheep
- Sushi Master
- wangh
- Ian Pan
- [Rist] Happy1650
- Tattaka + yu4u
“The artificial intelligence models developed as part of this challenge have significant potential to advance patient care by assisting radiologists and other physicians to detect and grade different traumatic abdominal injuries, which is a particularly difficult task, requiring a lot of careful image review,” Rudie said.
The competition was conducted in collaboration with the American Society of Emergency Radiology (ASER) and the Society for Abdominal Radiology (SAR). Winners will be recognized during RSNA’s annual meeting in Chicago on Nov. 26-30.
Chad is an award-winning writer and editor with over 15 years of experience working in media. He has a decade-long professional background in healthcare, working as a writer and in public relations.