RSNA Co-sponsors Brain Tumor AI Challenge
Challenge competition open for artificial intelligence researchers
RSNA, the American Society of Neuroradiology (ASNR) and the Medical Image Computing and Computer Assisted Interventions (MICCAI) society have launched the 10th annual Brain Tumor Segmentation (BraTS) challenge.
The RSNA/ASNR/MICCAI BraTS 2021 challenge focuses on brain tumor detection and classification, utilizing multi-parametric magnetic resonance imaging (mpMRI) scans. It represents the culmination of a decade of BraTS challenges, offering a large and diverse dataset with detailed annotations and an important associated biomarker.
“RSNA has significantly ‘upped their game’ with this year’s Brain Tumor Classification Challenge,” said Adam E. Flanders, MD, who serves on the RSNA Machine Learning Subcommittee. “It is our first AI Challenge to use MRI, and it is also our first to address an oncology problem—brain cancer.”
Another novel aspect of the challenge is that it addresses two very clinically relevant tasks: (1) to develop the most accurate automated method to measure the size of the visual components of a cancer—this has implications in being able to precisely track growth or response of the cancer to treatment—and (2) to develop a reliable non-invasive method to predict the presence of specific genetic features in the tumor from the MR images alone.
“These genetic markers are indicators of treatment response and survival,” Dr. Flanders said. “This has potential use in planning for customized therapies even before surgery is performed.”
Participants may choose to compete in one or both of the challenge tasks.
In the first task, Brain Tumor Segmentation, participants build models that produce detailed segmentations of brain tumor sub-regions that correspond to those created by neuroradiologists. Such segmentations could enable improvements in computer-assisted surgery, radiotherapy guidance and disease progression monitoring.
For second task, Brain Tumor Radiogenomic Classification, participants build models that use mpMRI imaging to predict MGMT (O-methylguanine-DNA methyltransferase) promoter methylation status. Such radiogenomic models could improve the efficiency and accuracy of diagnosis, prognosis and treatment planning for patients with glioblastoma.
Final model submission is due Oct. 12. Winners will be announced on Nov. 23 and recognized recognized in an event in the AI Showcase Theater at RSNA 2021 on Monday, Nov. 29. Prize money for the top entries in each task is provided by Intel, NeoSoma and RSNA.
For More Information
Learn more about the challenge, RSNA.org/AI-image-challenge.
- Segmentation leg: https://www.synapse.org/#!Synapse:syn25829067/wiki/610863
- Radiogenomic Classification leg: https://www.kaggle.com/c/rsna-miccai-brain-tumor-radiogenomic-classification
Learn more about the 2021 RSNA COVID-19 AI Detection Challenge.
Read previous RSNA News stories on detection challenge winners: