Cancer3.AI › AI in Oncology › Datasets › BraTS — Brain Tumor Segmentation Challenge
Benchmark / challenge Free registration challenge terms (registration on Synapse)

BraTS — Brain Tumor Segmentation Challenge

The long-running benchmark for brain tumour segmentation from MRI; nnU-Net-based methods have dominated its leaderboards.

Dataset site { } JSON

At a glance

ProviderBraTS organisers (University of Pennsylvania, Indiana University, MICCAI)
AccessFree registration
Licencechallenge terms (registration on Synapse)
patients1 250
Size notes≥1,250 glioma cases since 2021; later editions add paediatric, metastasis, meningioma and Sub-Saharan Africa tracks
FormatsNIfTI
Data typeMRI
TaskSegmentation
CancerAdult-Type Diffuse Gliomas

Labels and annotations

Expert-approved voxel labels: enhancing tumour, peritumoural oedema, necrotic core on T1, T1-Gd, T2, FLAIR.

Details

Not yet documented on this card.

Models trained or evaluated on it

  • benchmark nnU-Net German Cancer Research Center (DKFZ), Division of Medical Image Computing — standard glioma segmentation benchmark where nnU-Net variants placed first repeatedly

Sources

  1. BraTS on Synapse
  2. Baid U et al. The RSNA-ASNR-MICCAI BraTS 2021 Benchmark. arXiv 2021

This page is educational — it is not medical advice and does not replace consultation with an oncologist. Diagnostic and treatment decisions are made solely by specialist physicians.