mRALE Mastermind Challenge.
Last updated July 21, 2023
The “MIDRC mRALE Mastermind Challenge: AI to predict COVID severity on chest radiographs” has now concluded.
Congratulations to all test phase participants and the best performing mRALE Masterminds! Performances were great overall.
The mRALE Mastermind webinar video has been posted on our YouTube channel; The top 3 teams discuss their approaches and answer questions from the audience.
Full list of high-performing teams
Ian Pan, Brigham and Women's
Ran Zhang, University of Wisconsin-Madison
Finn Behrendt, University of Technology Hamburg
Team MALTA, Pontifícia Universidade Católica do Rio Grande do Sul
Christian Mattjie
Luis Vinicius de Moura
Rafaela Cappelari Ravazio
Otavio Parraga
Lucas Silveira Kupssinskü
Adilson
Rodrigo Coelho Barros
5. Yijie Yuan JHMI
6. Team University of Kentucky
Cohen Archbold
Imran Abdullah-Al-Zubaer
Atik Ahamed
7. Mathieu Goulet, Centre régional intégré de cancérologie (CRIC)
8. Team University of Waterloo
Yifan Wu
Hayden Gunraj
Chengzong Zhao
Yuhao Chen, PhD
Alexander Wong
Pengcheng Xi
9. Team National Library of Medicine (NLM)
Stanley Liang
Sameer Antani
Zhiyun Xue
Sivaramakrishnan Rajaraman
Feng Yang
Many thanks to the expert radiologist annotators who participated in the annotation event and scored portable chest radiographs for COVID severity in terms of mRALE score [1] to provide a reference standard for our mRALE Mastermind Challenge.
Did you miss our informational webinar on the challenge process and are interested in participating in a future MIDRC Challenge? Watch the video from the informational webinar on Tuesday June 6, 10am Eastern Time.
Prizes for mRALE Mastermind
Winner and runner-up team: MIDRC support to take your method/model through the FDA regulatory process.
Cash prizes through 7th place!
1st Place - $ 15,000
2nd Place - $ 8,000
3rd Place - $ 7,000
4th - 7th Place - $ 5,000 each
The acronym mRALE stands for modified RALE score which, in turn, stands for Radiographic Assessment of Lung Edema. This grading scale was originally validated for use in pulmonary edema assessment in acute respiratory distress syndrome and incorporates the extent and density of alveolar opacities on chest radiographs. The grading system is relevant to COVID-19 patients as the chest radiograph findings tend to involve multifocal alveolar opacities, and many hospitalized COVID-19 patients develop acute respiratory distress syndrome. To obtain an mRALE score, each lung is assigned a score for the extent of involvement by consolidation or ground glass/hazy opacities (0 = "none"; 1 = "≤ 25%"; 2 = "25%–50%"; 3 = "51%–75%"; 4 = ">75%" involvement). Each lung score is then multiplied by an overall density score (1 = "hazy", 2 = "moderate", 3 = "dense"). The sum of scores from each lung is the mRALE score. Thus, a normal chest radiograph receives a score of 0, while a chest radiograph with complete consolidation of both lungs receives the maximum score of 24.
The task of this Challenge is to develop AI to predict COVID-19 severity in terms of mRALE score from portable chest X-ray radiographs obtained within 2 days of a positive COVID test. Check out the Challenge platform for details and registration, and the MIDRC mRALE Mastermind GitHub for materials.
May the best mRALE Mastermind win!
