The RSNA Intracranial Hemorrhage Detection and Classification Challenge required teams to develop algorithms that can identify and classify subtypes of hemorrhages on head CT scans. The dataset, comprised of more than 25,000 head CT scans contributed by several research institutions, is the first multiplanar dataset used in an RSNA AI challenge.
RSNA subcommittees worked with volunteer specialists from the American Society of Neuroradiology (ASNR) to label these exams for the presence of five subtypes of intracranial hemorrhage.
Kaggle (a subsidiary of Alphabet, the parent company of Google) provided the platform for the challenge, which included access to datasets and also a discussion forum for participants, the repository of submitted results, and a leaderboard that ran throughout the challenge. In addition, Kaggle provided $25,000 in prize money to be shared among the winning entries.
The researchers started in September to develop and "train" algorithms, which were then evaluated in early November. Results were compared with the annotations on the testing dataset, and an evaluation metric was applied to rate their performance and determine the winners. A list of the winning teams is available on the RSNA website.
Copyright © 2019 AuntMinnie.com