BraTS (Brain Tumor Segmentation)
N/A
GitHub Stars
N/A
Open Issues
N/A
Docker Support
N/A
Last Updated
Technical Summary
The Brain Tumor Segmentation (BraTS) dataset is a cornerstone resource for medical image analysis, focusing on the evaluation of state-of-the-art methods for the segmentation of brain tumors in multimodal magnetic resonance imaging (MRI) scans.
Key Capabilities
- Multimodal MRI: Includes native (T1), post-contrast T1-weighted (T1Gd), T2-weighted (T2), and T2 Fluid Attenuated Inversion Recovery (T2-FLAIR) volumes.
- Detailed 3D Annotations: Expertly annotated 3D volumes identifying the enhancing tumor, the peritumoral edema, and the necrotic/non-enhancing tumor core.
- Global Benchmark: Acts as the official dataset for the annual BraTS challenge at the MICCAI conference, driving algorithmic improvements in the field.
Usage in Healthcare
BraTS is critical for developing AI models that can assist neuro-oncologists and radiologists in treatment planning, surgical navigation, and disease progression monitoring for patients with glioblastoma and lower-grade gliomas.
Model Card Details
Architecture
N/A
Intended Use Cases
Training 3D computer vision models for automated segmentation of brain tumors (gliomas) in multiparametric MRI.