August 10, 2017 — The Radiological Society of North America (RSNA) is organizing a challenge intended to show the application of machine learning and artificial intelligence on medical imaging and the ways in which these emerging tools and methodologies may improve diagnostic care.
The RSNA Pediatric Bone Age Machine Learning Challenge addresses a familiar image analysis activity for pediatric radiologists: assessment of bone age from hand radiographs of pediatric patients used to evaluate growth and diagnose developmental disorders. The Challenge uses a dataset of hand radiographs provided by a consortium of leading research institutions — Stanford University, the University of California, Los Angeles and the University of Colorado — that have associated bone age assessments provided by multiple expert observers.
Participants in the challenge will be judged by how well the bone age evaluations produced by their algorithms accord with the expert observers’ evaluations. Participants will have the opportunity to directly compare their algorithms in a structured way using this carefully curated dataset. The RSNA Machine Learning Challenge organizing committee will select a small group of the most successful entries for recognition at the RSNA annual meeting, Nov. 26-Dec. 1 in Chicago. Recognition of Challenge participants will be part of a broad range of educational events and exhibits focusing on machine learning at the RSNA annual meeting.
The milestone activities scheduled for the Challenge include:
- Training data phase: Aug. 1-30
- Leader board phase: Sept. 1-Oct. 7
- Submission of results: Oct. 7-15
- Review and confirmation of results: Oct. 15
- Notification of awardees: Oct. 15
- Public announcement of results: Monday, Nov. 27 at the RSNA 2017 annual meeting
At the challenge site, prospective participants may review the terms and conditions, evaluation criteria and other details of participation as well as, register to participate and download the training dataset to begin the Challenge.
The Challenge is hosted on the MedICI platform (built by CodaLab) provided by Jayashree Kalpathy-Cramer, Ph.D., and Massachusetts General Hospital, supported through NIH grants and a contract from Leidos.
For more information: www.rsnachallenges.cloudapp.net
