Skip to content
@BraTS-inpainting

BraTS inpainting challenge

The Brain Tumor Segmentation (BraTS) Challenge: Local Synthesis of Healthy Brain Tissue via Inpainting

🎨 BraTS Inpainting Challenge

Welcome to the official GitHub organization of the Brain MRI Inpainting Challenge.

This challenge benchmarks generative methods for inpainting healthy brain tissue in T1-weighted MRI scans. Participants are provided with partially masked T1 scans from real patient data and are tasked with reconstructing the missing regions as realistically as possible — without seeing the original ground truth. The BraTS inpainting challenge started on MICCAI 2023.

The goal is to develop models that can perform anatomically plausible 3D completion of irregularly occluded areas in 3D brain MRI data. The challenge emphasizes perceptual quality and structural realism.


The full details of the dataset, task design, evaluation protocol, and results are described in our official publication:

Challenge paper 🔗 arXiv:2305.08992


📢 Follow us on Twitter/X


🎨 Happy inpainting!

Popular repositories Loading

  1. 2023_challenge 2023_challenge Public archive

    BraTS 2023 Inpainting Challenge (Local Synthesis) Repository for Participants. Includes baseline model and infill mask generation script.

    Jupyter Notebook 21 1

  2. 2024_challenge 2024_challenge Public

    BraTS 2024 Inpainting Challenge (Local Synthesis) Repository for Participants. Includes baseline model and infill mask generation script.

    Jupyter Notebook 7

  3. 2025_challenge 2025_challenge Public

    BraTS 2025 Inpainting Challenge (Local Synthesis Challenge)

    Jupyter Notebook 6 1

  4. inpainting inpainting Public

    Official package to compute metrics for the BraTS inpainting challenge https://arxiv.org/abs/2305.08992

    Python 4

  5. .github .github Public

Repositories

Showing 5 of 5 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…