The challenge is a competition among AI researchers to create applications that perform a defined task according to specified performance measures. It will be based on a publicly available dataset published by the U.S. National Institutes of Health (NIH) that has been annotated by multiple expert reviewers. The RSNA Machine Learning Steering Subcommittee collaborated with volunteer specialists from the Society of Thoracic Radiology to annotate the dataset, identifying abnormal areas in the lung images and assessing the probability of pneumonia.
Kaggle, a subsidiary of Alphabet (the parent company of Google), will provide the competition platform with a homepage for the challenge, controlled access to the challenge datasets, a discussion forum for participants, and a repository where participants submit their results. Kaggle will provide $30,000 in prize money for the winning entries.
The challenge will have two phases: training and evaluation. During the training phase, which starts on August 27 and runs until October 17, participants will use the training portion of the dataset to develop algorithms that duplicate the annotations provided by radiologist observers. In the evaluation phase, which takes place October 18-24, participants will use their algorithms on the testing portion of the dataset, from which the annotations are withheld.
October 24 is the deadline for test results submission; the results will then be compared with the "ground-truth" values supplied by the annotations of the expert observers to determine the winners. The results will be announced in early November, and the top submissions will be recognized on November 26 in a session at the Machine Learning Showcase during RSNA 2018.
Radiologists interested in participating can set up a free account on the Kaggle site and express their interests and qualifications in the forum for the RSNA Pneumonia Detection Challenge. Information is available on the challenge site or by contacting RSNA staff at firstname.lastname@example.org.
Copyright © 2018 AuntMinnie.com