wwu-mmll/deepbet

deepbet is a neural-network tool for extracting brain masks from T1-weighted MRI, exposed through a Python API, CLI, and GUI. Users select input images, output destinations, and optional threshold/dilation settings; the shared runner validates files and invokes brain extraction. Extraction uses a bounding-box model before full-resolution segmentation, then postprocesses the mask and saves requested brain images, masks, and TIV values. Utilities handle model loading, normalization, image orientation, masking, and connected components. Workflow details are based on the sampled source; the README also documents the same outputs and controls.