{"id":24126704,"url":"https://github.com/djoerch/randomised_filtering","last_synced_at":"2025-06-12T18:34:47.610Z","repository":{"id":164495328,"uuid":"346217292","full_name":"djoerch/randomised_filtering","owner":"djoerch","description":"Code for randomised tractogram filtering using rSIFT","archived":false,"fork":false,"pushed_at":"2023-07-14T21:33:01.000Z","size":123,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-03-01T00:59:15.796Z","etag":null,"topics":["streamlines","tractogram-filtering","tractography"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/djoerch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2021-03-10T03:17:41.000Z","updated_at":"2022-08-25T14:52:29.000Z","dependencies_parsed_at":null,"dependency_job_id":"a41ec0d3-7027-49a7-a7f6-9e3b7080c0e6","html_url":"https://github.com/djoerch/randomised_filtering","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/djoerch/randomised_filtering","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djoerch%2Frandomised_filtering","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djoerch%2Frandomised_filtering/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djoerch%2Frandomised_filtering/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djoerch%2Frandomised_filtering/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/djoerch","download_url":"https://codeload.github.com/djoerch/randomised_filtering/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/djoerch%2Frandomised_filtering/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259519289,"owners_count":22870331,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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":["streamlines","tractogram-filtering","tractography"],"created_at":"2025-01-11T16:35:26.971Z","updated_at":"2025-06-12T18:34:47.570Z","avatar_url":"https://github.com/djoerch.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Randomised Filtering\n\nThis repository provides the code for the experiments on the method called\n_randomized SIFT_ (rSIFT) as described in\n\nA. Hain, D. Jörgens, R. Moreno,\n\"_Randomized Iterative Spherical-Deconvolution Informed Tractogram Filtering_\",\n[NeuroImage](https://doi.org/10.1016/j.neuroimage.2023.120248), 2023.\n\n## Installation Instructions\n\n#### Dependencies\n\nMake sure that the following dependencies are installed:\n - Python 3.8\n - `mrtrix3` (follow instructions at\n    https://mrtrix.readthedocs.io/en/latest/index.html)\n - `scilpy` (follow instructions at https://github.com/scilus/scilpy)\n - CUDA (Make sure to match the CUDA version with the tensorflow version specified in the requirements.)\n\n#### Installation\n\nCreate a virtual environment using by:\n```\nvirtualenv -p $(which python3) \u003cpath_to_environment\u003e\n```\n\nThen, install the package in the activated environment:\n```\nsource \u003cpath_to_environment\u003e/bin/activate\npip install -e \u003cpath_to_randomised_filtering_repo\u003e\n```\n\nAfter that, the **python** scripts in the `scripts` folder will be available through\nautocompletion in the command line whenever the virtual environment is activated.\n\n## Model weights\n\nThe weights of the best performing CV model for each classifier type are provided in the folder `data/models`.\nThese weights were obtained with the tensorflow version specified in `requirements.txt`.\n\n## Data\n\n - Data must be downloaded from the Human Connectome Project website at \n   https://www.humanconnectome.org/study/hcp-young-adult.\n - Tractograms can be created following the description at\n   https://zenodo.org/record/1477956#.YVTb3jqxU5l\n - For streamline compression, use the Dipy function `compress_streamlines`\n   with tol_error=0.35\n   (https://dipy.org/documentation/1.4.1./reference/dipy.tracking/#dipy.tracking.streamline.compress_streamlines)\n\n\n## How to use\n\nThe script `sift_experiment.sh` is the anchor and launches all commands for one rSIFT\nexperiment. The individual scripts `rf_*` can be launched individually, too. Each\nprovides a brief help text when invoked with the option `-h`.\n\nThe collection of different rSIFT experiments (with different parameters) can be\nlaunched using the script `main.sh`.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdjoerch%2Frandomised_filtering","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdjoerch%2Frandomised_filtering","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdjoerch%2Frandomised_filtering/lists"}