RSNA names winners of brain tumor AI challenge

By staff writers

November 24, 2021 -- The RSNA, the Medical Image Computing and Computer Assisted Interventions Society (MICCAI), and the American Society of Neuroradiology announced the winners of their brain tumor artificial intelligence challenge.

This year's challenge featured two tasks. In the first task, participants built models that segment and classify brain tumors into clinically acquired multiparametric magnetic resonance imaging (mpMRI) scans. This particular challenge was the culmination of Brain Tumor Segmentation (BraTS) challenges conducted in conjunction with MICCAI over the last decade, according to the societies.

The second task involved using algorithms to utilize the same mpMRI scans to predict the status of MGMT promoter methylation -- a radiogenomic marker that's an important factor in the prognosis and treatment of brain tumors.

More than 1,200 participants from five continents registered for the first challenge, and more than 1,500 teams signed up for the second task. The teams that submitted the eight best-performing algorithms in each leg of the challenge will split $60,000 in prize money contributed by RSNA, Intel, and Neosoma.

The winners for the segmentation task included:

  • Kaist-MRI-Lab
  • DeepX
  • Mfnv
  • VAuto
  • FightBrainTumor
  • Future-Processing-Healthcare
  • NGResearch

The winners of the radiogenomic classification task included:

  • Minh Phan
  • Cedric Soares
  • Leaky Folds
  • Random
  • Train4Ever
  • Igor Lashkov
  • ArturHugo

The RSNA will recognize the top performers, as well as all challenge participants and organizers, in an RSNA 2021 event, which will be held on November 29 from 4-5 p.m. CT in the AI Showcase Theater at McCormick Place.

Copyright © 2021

To read this and get access to all of the exclusive content on create a free account or sign-in now.

Member Sign In:
MemberID or Email Address:  
Do you have a password?
No, I want a free membership.
Yes, I have a password:  
Forgot your password?
Sign in using your social networking account:
Sign in using your social networking