COVID-19 AI Detection Challenge (2021)
The 2021 COVID-19 AI Detection Challenge invited participants to help medical professionals around the world quickly diagnose and treat COVID-19. Participants were tasked with building models to detect and localize COVID-19 pneumonia and grade radiographs based on their appearance (typical, atypical or indeterminate).
RSNA, the Society for Imaging Informatics in Medicine (SIIM) and the Foundation for the Promotion of Health and Biomedical Research of Valencia Region (FISABIO) co-hosted the COVID-19 AI Detection Challenge on the Kaggle competition platform.
Winning teams and entries
A total of 1,786 participants from 82 countries formed 1,305 teams to take part in the competition.
Participants used augmented annotations on public chest radiograph datasets from the Medical Imaging Data Resource Center (MIDRC) – RSNA International COVID-19 Open Radiology Database (RICORD) and the BIMCV-COVID-19 Dataset.
The winning entries are listed below.
Dataset
Review the COVID-19 AI Detection Challenge dataset description.
| Team name | Video | Solution | Code |
|---|---|---|---|
| [VinDr.ai] DungNB | Video | Solution | Code |
| Video | Solution | Code | A Team |
| [Ailllis] Yuji & Ian | Video | Solution | Code |
| Video | Solution | RTX 4090 | Code |
| Ayushman Nischay Shivam | Video | Solution | Code |
| Quanta AI Lab | Video | Solution | Code |
| Video | Solution | [dsmlkz] School Zerde | Code |
| RTX 3090 | Video | Solution | Code |
| Watercooled | Video | Solution | Code |
| Guanshuo Xu | Video | Solution | Code |
|
Team name: [VinDr.ai] DungNB Video: Video Solution: Solution Code: Code |
|
Team name: Video Video: Solution Solution: Code Code: A Team |
|
Team name: [Ailllis] Yuji & Ian Video: Video Solution: Solution Code: Code |
|
Team name: Video Video: Solution Solution: RTX 4090 Code: Code |
|
Team name: Ayushman Nischay Shivam Video: Video Solution: Solution Code: Code |
|
Team name: Quanta AI Lab Video: Video Solution: Solution Code: Code |
|
Team name: Video Video: Solution Solution: [dsmlkz] School Zerde Code: Code |
|
Team name: RTX 3090 Video: Video Solution: Solution Code: Code |
|
Team name: Watercooled Video: Video Solution: Solution Code: Code |
|
Team name: Guanshuo Xu Video: Video Solution: Solution Code: Code |
Results
Winners were announced September 19, 2021 at the SIIM Conference on Machine Intelligence in Medical Imaging (CMIMI).
Access the COVID-19 AI Detection Challenge results on the Kaggle website.