RSNA Pediatric Bone Age Challenge (2017)
As part of its efforts to spur the creation of artificial intelligence (AI) tools for radiology, in 2017 RSNA conducted a challenge to assess bone age from pediatric hand radiographs, a routine task that determines an important developmental indicator.
About the 2017 RSNA Pediatric Bone Age Challenge
The 2017 RSNA AI data challenge used a dataset developed by Stanford University and the University of Colorado and was annotated by multiple expert observers.
Over 250 participants, including AI developers, data scientists, radiologists and other medical specialists, competed in the challenge. Participants worked in 37 teams to submit the outcomes of their algorithms. Teams with the most accurate predictions were recognized at RSNA 2017.
Download the datasets
You may access and use the imaging datasets and annotations for the purposes of academic research and education, and other non-commercial purposes, as long as you meet the attribution requirements linked below.
Please note: These are large data files. Please ensure that you have sufficient internet bandwidth and storage available before beginning to download the datasets.• Dataset description
• Download training dataset (9.6 GB)
• Download training dataset annotations
• Download validation dataset (1.1 GB)
Terms of use and acknowledgments
• RSNA Pediatric Bone Age Challenge Acknowledgements• RSNA Pediatric Bone Age Challenge Terms of Use and Attribution
Research citations for further reading
- Halabi SS, Prevedello LM, Kalpathy-Cramer J, et al. The RSNA Pediatric Bone Age Machine Learning Challenge. Radiology 2018; 290(2):498-503.
- Siegel EL. What Can We Learn from the RSNA Pediatric Bone Age Machine Learning Challenge? Radiology 2018; 290(2):504-505.
- Larson DB, Chen MC, Lungren MP, et al. Performance of a Deep-Learning Neural Network Model in Assessing Skeletal Maturity on Pediatric Hand Radiographs. Radiology 2017;287(1):313-322.