AI challenges

AI promises to provide tools that will enhance the efficiency and accuracy of radiologic diagnoses. RSNA organizes AI challenges to spur the creation of AI tools for radiology. 

To build these tools, AI researchers need access to substantial volumes of imaging data annotated by expert radiologists. Data challenges engage the radiology community to develop such datasets, which provide the standard of truth in training AI systems to perform tasks relevant to diagnostic imaging. 

In a challenge, researchers compete on how well their AI models perform specific tasks such as detection, localization and categorization of abnormal features according to defined performance measures. Each AI challenge explores and demonstrates the ways AI can benefit radiology and improve patient care.

These AI data challenges are organized by the RSNA Radiology Informatics Council, often in collaboration with other radiological organizations from around the world.

Please direct questions about the AI data challenge program to informatics@rsna.org.

How does an AI challenge work?

There are two main phases of an AI challenge: training and evaluation. 

In the training phase, researchers develop models and run them against the labeled data to get feedback on how closely their results match the expert annotations. In the evaluation phase, models are evaluated and scored against a portion of the dataset without labels. Winners are determined based on their scores in this phase. 

2024 RSNA Lumbar Spine Degenerative Classification AI Challenge 

The 2024 RSNA Lumbar Spine Degenerative Classification AI Challenge is now in progress and all researchers are welcome to join the challenge.

This challenge will task researchers with building models that can detect and classify degenerative spine conditions using lumbar spine MR images. The models will be evaluated against a data set from more than 8 sites across five continents.

The RSNA Lumbar Spine Degenerative Classification AI Challenge (2024) is supported by Vision Radiology.

Past AI challenges

View information about past challenges here:

2023: RSNA Abdominal Trauma Detection AI Challenge
About the Abdominal Trauma Detection AI Challenge

2023: RSNA Screening Mammography Breast Cancer Detection AI Challenge
About the Screening Mammography AI Challenge

2022: RSNA Cervical Spine Fracture AI Challenge
About the Cervical Spine Fracture AI Challenge

2021: COVID-19 AI Detection Challenge
About the COVID-19 AI Detection Challenge  
Dataset description 

2021: Brain Tumor AI Challenge 
About the Brain Tumor AI Challenge 
Dataset description

2020: RSNA Pulmonary Embolism Detection Challenge
About the Pulmonary Embolism Detection Challenge 
Dataset description  

2019: RSNA Intracranial Hemorrhage Detection Challenge 
About the Intracranial Hemorrhage Detection Challenge 
Dataset description