{"id":30624466,"url":"https://github.com/hilab-git/csal-3d","last_synced_at":"2025-08-30T17:16:49.393Z","repository":{"id":312023538,"uuid":"1008171496","full_name":"HiLab-git/CSAL-3D","owner":"HiLab-git","description":"[MICCAI 2025] Official code for CSAL-3D","archived":false,"fork":false,"pushed_at":"2025-08-28T03:28:00.000Z","size":995,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-28T10:29:41.546Z","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,"zenodo":null}},"created_at":"2025-06-25T06:24:04.000Z","updated_at":"2025-08-28T03:28:03.000Z","dependencies_parsed_at":"2025-08-28T10:30:47.325Z","dependency_job_id":"24ecc2cc-f34e-4b0f-8b96-16887dba9ac4","html_url":"https://github.com/HiLab-git/CSAL-3D","commit_stats":null,"previous_names":["hilab-git/csal-3d"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/HiLab-git/CSAL-3D","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FCSAL-3D","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FCSAL-3D/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FCSAL-3D/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FCSAL-3D/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HiLab-git","download_url":"https://codeload.github.com/HiLab-git/CSAL-3D/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiLab-git%2FCSAL-3D/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":272878333,"owners_count":25008340,"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","status":"online","status_checked_at":"2025-08-30T02:00:09.474Z","response_time":77,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":[],"created_at":"2025-08-30T17:16:48.794Z","updated_at":"2025-08-30T17:16:49.378Z","avatar_url":"https://github.com/HiLab-git.png","language":"Python","readme":"# [MICCAI 2025] CSAL-3D\nThis repository contains the official implementation of our paper:\n**CSAL-3D: Cold-start Active Learning for 3D Medical Image Segmentation via SSL-driven Uncertainty-Reinforced Diversity Sampling**, for 28th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2025, Early Accept).\n## 📌 Overall Framework\n![Framework](Workflow.png)\n\nThe overall CSAL-3D pipeline consists of:\n- A **CSAL-adapted Self-Supervised Learning (SSL)** framework for both 3D-aware feature extraction and uncertainty estimation.\n- An **Ensemble-based Uncertainty Estimation** strategy to generate sample-level uncertainty scores.\n- A **URDS (Uncertainty-Reinforced Diversity Sampling)** method that hierarchically combines diversity and uncertainty for one-shot sample selection.\n\n## 📁 Dataset and Dependency\nWe evaluate our method on three publicly available 3D medical image segmentation datasets from the **Medical Segmentation Decathlon (MSD)**:\n- **Brain Tumor (Task01_BrainTumour)** [MRI, multi-modality]\n- **Heart (Task02_Heart)** [MRI]\n- **Spleen (Task09_Spleen)** [CT]\n- Datasets can be downloaded from the official MSD website:\n👉 [http://medicaldecathlon.com/](http://medicaldecathlon.com/)\n\n### Environment Setup\n\nPython 3.8+ with PyTorch 2.3.1 and MONAI 1.3+.\n\n## 🙏 Acknowledgement \nOur codebase is built upon the excellent COLosSAL project (https://github.com/han-liu/COLosSAL), which provides a benchmark for Cold-Start Active Learning in 3D medical image segmentation.\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhilab-git%2Fcsal-3d","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhilab-git%2Fcsal-3d","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhilab-git%2Fcsal-3d/lists"}