{"id":37063829,"url":"https://github.com/wwu-mmll/deepbet","last_synced_at":"2026-01-14T07:18:35.885Z","repository":{"id":188434752,"uuid":"678710069","full_name":"wwu-mmll/deepbet","owner":"wwu-mmll","description":"Fast brain extraction using neural networks","archived":false,"fork":false,"pushed_at":"2024-07-23T10:42:58.000Z","size":29450,"stargazers_count":42,"open_issues_count":2,"forks_count":3,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-11-30T23:40:39.944Z","etag":null,"topics":["brain-extraction","deep-learning","neuroimaging","python","segmentation","skull-stripping"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/wwu-mmll.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-15T07:26:16.000Z","updated_at":"2025-11-18T01:54:00.000Z","dependencies_parsed_at":null,"dependency_job_id":"e6d58b3d-3df4-4b84-877c-5cf49cfcb2f0","html_url":"https://github.com/wwu-mmll/deepbet","commit_stats":null,"previous_names":["wwu-mmll/deepbet"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/wwu-mmll/deepbet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wwu-mmll%2Fdeepbet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wwu-mmll%2Fdeepbet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wwu-mmll%2Fdeepbet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wwu-mmll%2Fdeepbet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wwu-mmll","download_url":"https://codeload.github.com/wwu-mmll/deepbet/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wwu-mmll%2Fdeepbet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28412819,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-14T05:26:33.345Z","status":"ssl_error","status_checked_at":"2026-01-14T05:21:57.251Z","response_time":107,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["brain-extraction","deep-learning","neuroimaging","python","segmentation","skull-stripping"],"created_at":"2026-01-14T07:18:35.332Z","updated_at":"2026-01-14T07:18:35.871Z","avatar_url":"https://github.com/wwu-mmll.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003e\n\u003cimg src='https://github.com/wwu-mmll/deepbet/assets/55840648/ceff1fcc-e14b-4938-8f03-2cb28712eec1' width='700'\u003e\n\u003c/h1\u003e\u003cbr\u003e\n\nThis is the official implementation of the [deepbet paper](https://www.sciencedirect.com/science/article/pii/S0010482524009302?dgcid=author).\n\ndeepbet is a neural network based tool, which achieves state-of-the-art results for brain extraction of T1w MR images \nof healthy adults, while taking ~1 second per image.\n\n## Usage\nAfter installation, there are three ways to use deepbet\n1. ```deepbet-gui``` runs the **Graphical User Interface (GUI)**\n\n![deepbet-gui](https://github.com/user-attachments/assets/3a90c38d-f387-4c7d-a7e5-0e42efdfc9e9)\n\n2. ```deepbet-cli``` runs the **Command Line Interface (CLI)**\n\n```bash\ndeepbet-cli -i /path/to/inputs -o /path/to/output/brains\n```\n\n3. Run deepbet directly in Python\n\n```python\nfrom deepbet import run_bet\n\ninput_paths = ['path/to/sub_1/t1.nii.gz', 'path/to/sub_2/t1.nii.gz']\nbrain_paths = ['path/to/sub_1/brain.nii.gz', 'path/to/sub_2/brain.nii.gz']\nmask_paths = ['path/to/sub_1/mask.nii.gz', 'path/to/sub_2/mask.nii.gz']\ntiv_paths = ['path/to/sub_1/tiv.csv', 'path/to/sub_2/tiv.csv']\nrun_bet(input_paths, brain_paths, mask_paths, tiv_paths, threshold=.5, n_dilate=0, no_gpu=False)\n```\n\nBesides the `input paths` and the output paths\n\n- `brain_paths`: Destination filepaths of input nifti **files with brain extraction applied**\n- `mask_paths`: Destination filepaths of **brain mask nifti files**\n- `tiv_paths`: Destination filepaths of **.csv-files containing the total intracranial volume (TIV)** in cm³\n    - Simpler than it sounds: TIV = Voxel volume * Number of 1-Voxels in brain mask\n\nyou can additionally do\n\n- **Fine adjustments** via `threshold`: deepbet internally predicts values between 0 and 1 for each voxel and then includes each voxel which is above 0.5. \nYou can change this threshold (e.g. to 0.1 to include more voxels).\n- **Coarse adjustments** via `n_dilate`: Enlarges/shrinks mask by successively adding/removing voxels adjacent to mask surface.\n\nand choose if you want to **use GPU (only NVIDIA supported) for speedup**\n\n- `no_gpu`: deepbet automatically uses the NVIDIA GPU if available. If you do not want that, set no_gpu=True.\n\n## Installation\nFor accelerated processing via GPU, it is recommended to first install PyTorch separately via a [command customized for your system](https://pytorch.org/get-started/locally/).\n\nThen the package itself can be installed via\n```bash\npip install deepbet\n```\nDue to [this issue](https://github.com/ContinuumIO/anaconda-issues/issues/6833), the GUI can look ugly, which can be resolved via\n```bash\nconda install -c conda-forge tk=*=xft_*\n```\n\n## Citation\nIf you find this code useful in your research, please consider citing\n\n```bibtex\n@article{deepbet,\n    title = {deepbet: Fast brain extraction of T1-weighted MRI using Convolutional Neural Networks},\n    journal = {Computers in Biology and Medicine},\n    volume = {179},\n    pages = {108845},\n    year = {2024},\n    issn = {0010-4825},\n    doi = {https://doi.org/10.1016/j.compbiomed.2024.108845},\n    url = {https://www.sciencedirect.com/science/article/pii/S0010482524009302},\n    author = {Lukas Fisch and Stefan Zumdick and Carlotta Barkhau and Daniel Emden and Jan Ernsting and Ramona Leenings and Kelvin Sarink and Nils R. Winter and Benjamin Risse and Udo Dannlowski and Tim Hahn},\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwwu-mmll%2Fdeepbet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwwu-mmll%2Fdeepbet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwwu-mmll%2Fdeepbet/lists"}