{"id":17284313,"url":"https://github.com/fepegar/resseg-ijcars","last_synced_at":"2025-02-25T05:33:42.365Z","repository":{"id":53512676,"uuid":"326773199","full_name":"fepegar/resseg-ijcars","owner":"fepegar","description":"Code, data and model for Pérez-García et al. 2021, \"A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections\"","archived":false,"fork":false,"pushed_at":"2024-02-06T23:32:37.000Z","size":49,"stargazers_count":12,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-02-07T00:32:00.644Z","etag":null,"topics":["computer-vision","convolutional-neural-networks","epilepsy","medical-image-computing","mri","segmentation","tumor"],"latest_commit_sha":null,"homepage":"https://link.springer.com/article/10.1007/s11548-021-02420-2","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/fepegar.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}},"created_at":"2021-01-04T18:27:46.000Z","updated_at":"2024-01-08T08:52:19.000Z","dependencies_parsed_at":"2022-09-12T01:40:23.823Z","dependency_job_id":null,"html_url":"https://github.com/fepegar/resseg-ijcars","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fepegar%2Fresseg-ijcars","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fepegar%2Fresseg-ijcars/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fepegar%2Fresseg-ijcars/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fepegar%2Fresseg-ijcars/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fepegar","download_url":"https://codeload.github.com/fepegar/resseg-ijcars/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":219844490,"owners_count":16556485,"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":["computer-vision","convolutional-neural-networks","epilepsy","medical-image-computing","mri","segmentation","tumor"],"created_at":"2024-10-15T09:53:46.882Z","updated_at":"2024-10-15T09:53:46.972Z","avatar_url":"https://github.com/fepegar.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## RESSEG: segmentation of postoperative brain cavities on 3D MRI using deep learning\n\n![Segmentation of intraoperative\nMRI](https://media.springernature.com/full/springer-static/image/art%3A10.1007%2Fs11548-021-02420-2/MediaObjects/11548_2021_2420_Fig6_HTML.jpg)\n\nThis is the code for [Pérez-García et al., 2021, *A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections* - International Journal of Computer Assisted Radiology and\nSurgery (IJCARS)](https://doi.org/10.1007/s11548-021-02420-2).\n\nIf you use this code or the [EPISURG](https://github.com/fepegar/SlicerEPISURG)\ndataset for your research, please cite this publication as:\n\n\u003e Pérez-García, F., Dorent, R., Rizzi, M. et al. A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections. Int J CARS (2021). https://doi.org/10.1007/s11548-021-02420-2\n\nBibTeX:\n\n```bibtex\n@article{perez-garcia_self-supervised_2021,\n\ttitle = {A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections},\n\tissn = {1861-6429},\n\turl = {https://doi.org/10.1007/s11548-021-02420-2},\n\tdoi = {10.1007/s11548-021-02420-2},\n\tlanguage = {en},\n\turldate = {2021-06-14},\n\tjournal = {International Journal of Computer Assisted Radiology and Surgery},\n\tauthor = {P{\\'e}rez-Garc{\\'i}a, Fernando and Dorent, Reuben and Rizzi, Michele and Cardinale, Francesco and Frazzini, Valerio and Navarro, Vincent and Essert, Caroline and Ollivier, Ir{\\`e}ne and Vercauteren, Tom and Sparks, Rachel and Duncan, John S. and Ourselin, S{\\'e}bastien},\n\tmonth = jun,\n\tyear = {2021},\n}\n```\n\n## Installation\n\n```shell\n$ conda create -n ijcars python=3.7 ipython -y \u0026\u0026 conda activate ijcars\n$ conda install pytorch=1.7.1 torchvision=0.8.2 cudatoolkit=11.0 -c pytorch -y\n$ pip install -r requirements.txt\n```\n\n## Related projects\n\n### `resseg`\n\nThe trained models can be used to segment easily using [`resseg`](https://github.com/fepegar/resseg).\n\n### `resector`\n\nResections can be simulated on 3D MRI using [`resector`](https://github.com/fepegar/resector).\n\n### EPISURG dataset\n\nSee the [EPISURG extension for 3D Slicer](https://github.com/fepegar/SlicerEPISURG).\n\n## Commands used for training\n\n### Using simulated resections only\n\n#### Augmentation\n\n```\npython main.py with config/simulated/config_simulated_no_augment.yml\n```\n\n#### Shape\n\n##### Cuboids\n\n```\npython main.py with config/simulated/shape/config_simulated_shape_cuboid.yml\n```\n\n##### Ellipsoids\n\n```\npython main.py with config/simulated/shape/config_simulated_shape_ellipsoid.yml\n```\n\n##### Noisy ellipsoids (baseline)\n\n```\npython main.py with config/simulated/config_simulated_baseline.yml\n```\n\n#### Texture\n\n##### Percentile 1\n\n```\npython main.py with config/simulated/texture/config_simulated_texture_dark.yml\n```\n\n##### Percentile 1, 99\n\n```\npython main.py with config/simulated/texture/config_simulated_texture_random.yml\n```\n\n##### CSF (baseline)\n\n```\npython main.py with config/simulated/config_simulated_baseline.yml\n```\n\n##### CSF + WM\n\n```\npython main.py with config/simulated/texture/config_simulated_texture_wm.yml\n```\n\n##### CSF + BC\n\n```\npython main.py with config/simulated/texture/config_simulated_texture_clot.yml\n```\n\n##### CSF + WM + BC\n\n```\npython main.py with config/simulated/texture/config_simulated_texture_clot_wm.yml\n```\n\n### Using clinical data from hospitals in UK, Italy and France\n\n#### Train\n\n#### Load and tune\n\n```\npython main.py with config/real/config_load_train.yml with dataset_name $DATASET\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffepegar%2Fresseg-ijcars","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffepegar%2Fresseg-ijcars","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffepegar%2Fresseg-ijcars/lists"}