Artificial intelligence (AI) promises to provide tools that will enhance the efficiency and accuracy of radiologic diagnoses. RSNA organizes AI challenges to spur the creation of artificial intelligence (AI) tools for radiology.
To build these tools, AI researchers need access to 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 defined tasks according to specified 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 Committee. Please direct questions about the AI data challenge program to email@example.com.
How does an AI challenge work?
There are two main phases of an AI challenge: training and evaluation.
In the training phase, researchers will 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 will be evaluated and scored against a portion of the dataset without labels. Winners will be determined based on the scores from this phase.