SIIM, FISABIO, and RSNA Recognize Winners of the COVID-19 Detection and Localization Challenge on Kaggle

The Society for Imaging Informatics in Medicine (SIIM), in partnership with The Foundation for the Promotion of Health and Biomedical Research of Valencia Region (FISABIO) and the Radiological Society of North America (RSNA), announce the official results of their joint machine learning challenge at SIIM’s 6th annual Conference on Machine Intelligence in Medical Imaging (CMIMI).

The SIIM-FISABIO-RSNA Covid-19 Detection Challenge required teams to develop high quality computer vision models to detect and localize COVID-19 pneumonia to help doctors provide a quick and confident diagnosis. 1,786 participants on 1,305 teams from 82 countries took part in the competition.

The challenge made use of augmented annotations on the public chest radiograph datasets from the Medical Imaging Data Resource Center (MIDRC)—RSNA International COVID-19 Open Radiology Database and BIMCV-COVID-19 Dataset, created by an international group of volunteer radiologists from Brazil, Spain, and the U.S. using a commercial web-based tool from MD.ai.

“SIIM is excited to have hosted the COVID-19 Detection Challenge in conjunction with RSNA, FISABIO, Kaggle, HP and Intel,” says Paras Lakhani, MD, annotation lead and member of the SIIM Machine Learning Tools & Research Subcommittee. “Congratulations to the winners and contestants for their hard work, as the solutions have the potential to positively impact patient care and help clinicians manage COVID-19 patients.”

The competition was run on a Kaggle, Inc. platform (owned by Google LLC), which provides access to datasets, a discussion forum for participants, the repository of submitted results and a leaderboard that runs throughout the challenge.

This challenge was supported by the National Science Foundation (NSF) Convergence Accelerator Grant that SIIM, along with its collaborators, was awarded in September 2020. SIIM’s Corporate Impact Partners, HP and Intel, provided $100,000 in prizes, in addition to a special prize – a high-end workstation for the Best Student Team.

The top 10 winning teams are: