{"id":18276258,"url":"https://github.com/hilab-git/fpl-plus","last_synced_at":"2025-07-31T22:39:12.920Z","repository":{"id":167267893,"uuid":"642867353","full_name":"HiLab-git/FPL-plus","owner":"HiLab-git","description":"FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation","archived":false,"fork":false,"pushed_at":"2024-06-03T13:13:22.000Z","size":22456,"stargazers_count":26,"open_issues_count":3,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-20T21:38:55.038Z","etag":null,"topics":[],"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/HiLab-git.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":"2023-05-19T14:20:53.000Z","updated_at":"2025-03-16T16:07:07.000Z","dependencies_parsed_at":"2024-03-27T12:25:46.406Z","dependency_job_id":"a741fbde-d9cf-431d-aa8c-527ec02f010f","html_url":"https://github.com/HiLab-git/FPL-plus","commit_stats":null,"previous_names":["hilab-git/fpl-v2","hilab-git/fpl-plus"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FFPL-plus","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FFPL-plus/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FFPL-plus/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FFPL-plus/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HiLab-git","download_url":"https://codeload.github.com/HiLab-git/FPL-plus/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247284911,"owners_count":20913691,"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":[],"created_at":"2024-11-05T12:15:34.968Z","updated_at":"2025-04-05T03:31:22.401Z","avatar_url":"https://github.com/HiLab-git.png","language":"Python","readme":"\u003c!-- # FPL+\ncode for \"FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation\"\n\nThe code is being gradually improved...\n\nTrain and test the FPL+:\n```\nexport CUDA_VISIBLE_DEVICES=0\nexport PYTHONPATH=$PYTHONPATH:./PyMIC\npython ./PyMIC/pymic/net_run_dsbn/net_run.py train ./config_dual/unet2d_dsbn_bst_t2s.cfg\npython ./PyMIC/pymic/net_run_dsbn/net_run.py test ./config_dual/unet2d_dsbn_bst_t2s.cfg\n``` --\u003e\n\n\n# FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation\nby [Jianghao Wu](https://jianghaowu.github.io/), et.al. \n\n## Introduction\n\nThis repository is for our IEEE TMI paper **FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation**. \n\n\n![](./FPL-plus.png)\n\n## Data Preparation\n\n### Dataset\n[ Vestibular Schwannoma Segmentation Dataset](https://www.nature.com/articles/s41597-021-01064-w) | [BraTS 2020](https://www.med.upenn.edu/cbica/brats2020/data.html) | [MMWHS](http://www.sdspeople.fudan.edu.cn/zhuangxiahai/0/mmwhs/)\n\nFor VS dataset, preprocess original data according to `./data/preprocess_vs.py`.\n\n### Cross domian data augmentation \nTraining [CycleGAN](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix), and convert source domain data into source domian-like set and target domian-like set, refer the folder `./dataset`.\n\n### File Organization\nUsing `./write_csv.py` to write your data into a `csv` file \n\nFor vs data, ceT1 as the source domain, hrT2 as the target domain, the`csv `file can be seen in `./config_dual/data_vs`: \n``` \n├──config_dual/data_vs\n    ├── [train_ceT1_like.csv]\n        ├──image,label\n        ├──./dataset/ceT1/img/vs_gk_99_t1.nii.gz,./dataset/ceT1/lab/vs_gk_99_t1_seg.nii.gz\n        ├──./dataset/fake_data/ceT1-hrT2-ceT1_cc/vs_gk_99_t1.nii.gz,./dataset/ceT1/lab/vs_gk_99_t1.nii.gz\n        ├──./dataset/fake_data/ceT1-hrT2-ceT1_ac/vs_gk_99_t1.nii.gz,./dataset/ceT1/lab/vs_gk_99_t1.nii.gz\n        ...\n    ├── [train_hrT2_like.csv]\n        ├──image,label\n        ├──./dataset/fake_data/ceT1-hrT2_cyc/vs_gk_99_t1.nii.gz,./dataset/ceT1/lab/vs_gk_99_t1.nii.gz\n        ├──./dataset/fake_data/ceT1-hrT2_auxcyc/vs_gk_99_t1.nii.gz,./dataset/ceT1/lab/vs_gk_99_t1.nii.gz\n        ...\n```\n\n## Training and Testing\n\n### Train pseudo labels generator and get pseudo label\nWrite your training config file in `config_dual/vs_t1s_g.cfg`\n\n```\nexport CUDA_VISIBLE_DEVICES=0\nexport PYTHONPATH=$PYTHONPATH:./PyMIC\n## train pseudo label generator\npython ./PyMIC/pymic/net_run_dsbn/net_run.py train ./config_dual/vs_t1s_g.cfg\n## get pseudo label\npython ./PyMIC/pymic/net_run_dsbn/net_run.py test ./config_dual/vs_t1s_g.cfg\n## get the pseudo label of fake source image\npython ./PyMIC/pymic/net_run_dsbn/net_run.py test ./config_dual/vs_t1s_g_fake.cfg\n## get image-level weights\npython ./PyMIC/pymic/net_run_dsbn/net_run.py test ./config_dual/vs_t1s_weights.cfg\n```\nWeights are saved on `[testing][fpl_uncertainty_sorted]` and `[testing][fpl_uncertainty_weight]`, run:\n```\npython data/get_pixel_weight.py\npython data/get image_weight.py\n```\n### Train final segmentor\n```\nexport CUDA_VISIBLE_DEVICES=0\nexport PYTHONPATH=$PYTHONPATH:./PyMIC\npython ./PyMIC/pymic/net_run_dsbn/net_run.py train ./config_dual/vs_t1s_S.cfg\npython ./PyMIC/pymic/net_run_dsbn/net_run.py test ./config_dual/vs_t1s_S.cfg\n```\n\n\n\u003c!-- ## Acknowledgement\nThe U-Net model is borrowed from [Fed-DG](https://github.com/liuquande/FedDG-ELCFS). The Style Augmentation (SA) module is based on the nonlinear transformation in [Models Genesis](https://github.com/MrGiovanni/ModelsGenesis). The Dual-Normalizaiton is borrow from [DSBN](https://github.com/wgchang/DSBN). We thank all of them for their great contributions. --\u003e\n\n## Citation\nIf you find this project useful for your research, please consider citing:\n\n```bibtex\n@article{wu2024fpl+,\n  title={FPL+: Filtered Pseudo Label-based Unsupervised Cross-Modality Adaptation for 3D Medical Image Segmentation},\n  author={Wu, Jianghao and Guo, Dong and Wang, Guotai and Yue, Qiang and Yu, Huijun and Li, Kang and Zhang, Shaoting},\n  journal={IEEE Transactions on Medical Imaging},\n  year={2024},\n  publisher={IEEE}\n}\n``` \n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhilab-git%2Ffpl-plus","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhilab-git%2Ffpl-plus","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhilab-git%2Ffpl-plus/lists"}