SIIM-ACR Pneumothorax Segmentation Kaggle Challenge
The Society for Imaging Informatics in Medicine (SIIM) and the American College of Radiology (ACR) has collaborated with the Society of Thoracic Radiology (STR) and MD.ai to host a Machine Learning Challenge on Pneumothorax Detection and Localization on Kaggle, using augmented annotations on the public chest radiograph dataset from the National Institutes of Health (NIH).
In this competition, participants were asked to develop a model to classify (and segment) pneumothorax from a set of chest radiographic images to help aid in the early recognition of pneumothoraces.
1,475 teams participated in the challenge, and 352 teams submitted results during the evaluation phase of the competition.
Top 10 Winning Teams
The Top 10 winning teams took home a total of $30,000 in prize money.
Winning algorithms are being open sourced to benefit radiology and improve patient care.
Winning Teams Models
1st Place – [dsmlkz] sneddy
2nd Place – X5
3rd Place – Bestfitting
4th Place – [ods.ai] amirassov
5th Place – Earhian
6th Place – Xknife
7th Place – See & Eduardo
8th Place – Ian Pan & Felipe Kitamura
9th Place - Scizzo
10th Place – [ods.ai] Yury & Konstantin
Participation Map and Top 10 Countries
Special Thanks To
