The winning teams have been announced in a challenge to develop machine-learning algorithms for the detection of COVID-19. The names of the top 10 winning teams were released at this week's Conference on Machine Intelligence in Medical Imaging (C-MIMI).
The challenge asked teams to develop high-quality computer vision models to detect and localize pneumonia caused by COVID-19. The competition drew over 1,700 participants on more than 1,300 teams from 82 countries, and it was sponsored by the Society for Imaging Informatics in Medicine (SIIM) in partnership with RSNA and the Foundation for the Promotion of Health and Biomedical Research of Valencia Region (FISABIO) in Spain.
Developers trained algorithms on public datasets of chest radiographs with augmented annotations that were drawn from the Medical Imaging Data Resource Center (MIDRC), the RSNA International COVID-19 Open Radiology Database (RICORD), and the BIMCV-COVID-19 Dataset, created by an international group of volunteer radiologists from Brazil, Spain, and the U.S.
The top 10 winning teams split $100,000 in prize money:
- 25 Minutes
- A Team
- [Aillis] Yuji & Ian
- RTX 4090, which won a special prize for the best student team
- Ayushman Nischay Shivam
- Quanta AI Lab
- [dsmlkz] School Zerde
- RTX 3090
- Watercooled
- Guanshuo Xu
Full results and more information about the challenge are available on the SIIM website, as well as from Kaggle, which hosted the competition.
