The Brain Tumor Segmentation (BraTS) Challenge: Local Synthesis of Healthy Brain Tissue via Inpainting
This is an incremental effort to improve medical imaging analysis for brain tumor patients by creating a benchmark for inpainting methods.
The paper introduces the BraTS inpainting challenge to address the problem of algorithms designed for healthy brain MR images failing on pathological scans with tumors, by having participants use inpainting techniques to synthesize healthy tissue from lesioned images.
A myriad of algorithms for the automatic analysis of brain MR images is available to support clinicians in their decision-making. For brain tumor patients, the image acquisition time series typically starts with an already pathological scan. This poses problems, as many algorithms are designed to analyze healthy brains and provide no guarantee for images featuring lesions. Examples include, but are not limited to, algorithms for brain anatomy parcellation, tissue segmentation, and brain extraction. To solve this dilemma, we introduce the BraTS inpainting challenge. Here, the participants explore inpainting techniques to synthesize healthy brain scans from lesioned ones. The following manuscript contains the task formulation, dataset, and submission procedure. Later, it will be updated to summarize the findings of the challenge. The challenge is organized as part of the ASNR-BraTS MICCAI challenge.