The Brain Tumor Segmentation Challenge (2022 Continuous Updates & Generalizability Assessment)

Brain tumors are among the deadliest types of cancer. Specifically, glioblastoma, and diffuse astrocytic glioma with molecular features of glioblastoma (WHO Grade 4 astrocytoma), are the most common and aggressive malignant primary tumor of the central nervous system in adults, with extreme intrinsic heterogeneity in appearance, shape, and histology, with a median survival of approximately 12 months. Brain tumors in general are challenging to diagnose, hard to treat and inherently resistant to conventional therapy because of the challenges in delivering drugs to the brain. Years of extensive research to improve diagnosis, characterization, and treatment have decreased mortality rates in the U.S. by 7% over the past 30 years. Although modest, these research innovations have not translated to improvements in survival for adults and children in low- and middle-income countries,
particularly in sub-Saharan African (SSA) populations.

The Brain Tumor Segmentation (BraTS) 2022 challenge seeks current updates on the RSNA-ASNR-MICCAI BraTS 2021 challenge, enabled by the automated continuous benchmark of algorithmic developments through the Synapse platform. Specifically, the focus of BraTS 2022 is to identify the current state-of-the-art segmentation algorithms for brain diffuse glioma patients and their sub-regions, trained using the 2021 dataset and evaluated on i) the specific 2021 testing dataset of adult-type diffuse glioma, as well as to assess their generalization on out-ofsample data from ii) an independent multi-institutional dataset covering underrepresented  SSA patient populations of brain adult-type diffuse glioma (Africa-BraTS), and from iii) another independent population of pediatric-type diffuse glioma patients. All challenge data are routine clinically-acquired, multi-institutional multiparametric magnetic resonance imaging (mpMRI) scans of brain tumor patients.

The BraTS 2022 challenge participants are able to obtain the training and validation data of the RSNA-ASNRMICCAI BraTS 2021 challenge at any point from the Synapse platform. These data will be used to develop, containerize, and evaluate their algorithms in unseen validation data until July 2022, when the organizers will stop accepting new submissions and evaluate the submitted algorithms in 1) the hidden 2021 testing data, 2) the Africa-BraTS population data, and 3) the pediatric patient population. Top performing methods will be reported for each of these categories separately. Ground truth reference annotations for all datasets are created and approved by expert neuroradiologists for every subject included in the training, validation, and testing datasets to quantitatively evaluate the performance of the participating algorithms.

Participants are free to choose whether they want to focus on only one or multiple categories/tasks.