{"id":27169184,"url":"https://github.com/smilelab-fl/fedcvd","last_synced_at":"2025-06-27T10:08:24.588Z","repository":{"id":243057511,"uuid":"811178522","full_name":"SMILELab-FL/FedCVD","owner":"SMILELab-FL","description":"The First Real-World Federated Learning Benchmark on Cardiovascular Disease Data","archived":false,"fork":false,"pushed_at":"2025-02-20T08:01:41.000Z","size":2551,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-09T06:34:50.934Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/SMILELab-FL.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":"2024-06-06T05:08:02.000Z","updated_at":"2025-02-20T08:01:45.000Z","dependencies_parsed_at":"2025-04-09T06:41:51.986Z","dependency_job_id":null,"html_url":"https://github.com/SMILELab-FL/FedCVD","commit_stats":null,"previous_names":["smilelab-fl/fedcvd"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SMILELab-FL/FedCVD","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SMILELab-FL%2FFedCVD","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SMILELab-FL%2FFedCVD/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SMILELab-FL%2FFedCVD/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SMILELab-FL%2FFedCVD/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SMILELab-FL","download_url":"https://codeload.github.com/SMILELab-FL/FedCVD/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SMILELab-FL%2FFedCVD/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262235784,"owners_count":23279567,"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":"2025-04-09T06:31:42.485Z","updated_at":"2025-06-27T10:08:24.562Z","avatar_url":"https://github.com/SMILELab-FL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# FedCVD\nThe First Real-World Federated Learning Benchmark on Cardiovascular Disease Data\n\n## Framework\n\n![](./assets/framework.png)\n\n## Installation\n### Directory Structure\nWe recommend the user to use `FedCVD` following the directory structure below:\n\n    data:  store the raw data and preprocessed data for each client;\n    code:  use `FedCVD` in this directory;\n    output: store results and log files。\nThe directory structure is shown below:\n```grapha  \n├── workspace  \n│   └── data\n│   │   ├── ECG  \n│   │   │   ├── raw\n│   │   │   │   ├── SPH\n│   │   │   │   ├── PTB\n│   │   │   │   ├── SXPH\n│   │   │   │   ├── G12EC\n│   │   │   ├── preprocessed\n│   │   │   │   ├── client1\n│   │   │   │   ├── client2\n│   │   │   │   ├── client3\n│   │   │   │   ├── client4\n│   │   ├── ECHO    \n│   │   │   ├── raw\n│   │   │   │   ├── CAMUS\n│   │   │   │   ├── ECHONET\n│   │   │   │   ├── HMCQU\n│   │   │   ├── preprocessed\n│   │   │   │   ├── client1\n│   │   │   │   ├── client2\n│   │   │   │   ├── client3\n│   ├── output  \n│   └── code  \n│       └── FedCVD\n```  \n\nYou can run scripts below to create the directory structure:\n\n```bash\nmkdir workspace  \ncd workspace  \nmkdir data code output\ncd data\nmkdir -p ECG/raw ECG/preprocessed ECHO/raw ECHO/preprocessed\ncd ECG/raw\nmkdir SPH PTB SXPH G12EC\ncd ../../ECHO/raw\nmkdir CAMUS ECHONET HMCQU\ncd ../../../\ncd code  \n```  \n### Data Downloading\n Datasets for **Fed-ECG** can be downloaded from the URLs below:\n - client1: [SPH](https://springernature.figshare.com/collections/A_large-scale_multi-label_12-lead_electrocardiogram_database_with_standardized_diagnostic_statements/5779802/1)\n - client2: [PTB-XL](https://physionet.org/content/ptb-xl/1.0.3/)\n - client3: [SXPH](https://physionet.org/content/ecg-arrhythmia/1.0.0/)\n - client4: [G12EC](https://physionet.org/content/challenge-2020/1.0.2/)\n\nDatasets for **Fed-ECHO** can be downloaded from the URLs below:\n - client1: [CAMUS](https://humanheart-project.creatis.insa-lyon.fr/database/#collection/6373703d73e9f0047faa1bc8)\n - client2: [ECHONET-DYNAMIC](https://echonet.github.io/dynamic/index.html#access)\n - client3: [HMC-QU](https://www.kaggle.com/datasets/aysendegerli/hmcqu-dataset/data)\n\nNote that a Stanford AIMI account is required to access the ECHONET-DYNAMIC dataset and a Kaggle account is required to access the HMC-QU dataset.\n### Data Preprocessing\nMake sure the data is stored in the correct directory structure. The reference structure is shown below:\n- **SPH** directory must contain the following files or directories:\n```grapha\n├── SPH\n│   ├── ...\n│   ├── metadata.csv\n│   ├── records\n│   │   ├── A00001.h5\n│   │   ├── ...\n│   │   └── A25770.h5\n```\n- **PTB** directory must contain the following files or directories:\n```grapha\n├── PTB\n│   ├── ...\n│   ├── ptbxl_database.csv\n│   ├── records500\n│   │   ├── 00000\n│   │   │   ├── 00001_hr.dat\n│   │   │   ├── 00001_hr.hea\n│   │   │   └── ...\n│   │   ├── ...\n│   │   └── 21000\n```\n- **SXPH** directory must contain the following files or directories:\n```grapha\n├── SXPH\n│   ├── ...\n│   ├── WFDBRecords\n│   │   ├── 01\n│   │   │   ├── 010\n│   │   │   │   ├── JS00001.hea\n│   │   │   │   ├── JS00001.mat\n│   │   │   │   └── ...\n│   │   │   ├── ...\n│   │   ├── ...\n│   │   └── 46\n```\n- **G12EC** directory must contain the following files or directories:\n```grapha\n├── G12EC\n│   ├── g1\n│   │   ├── E00001.hea\n│   │   ├── E00001.mat\n│   │   └── ...\n│   ├── ...\n│   └── g11\n```\n- **CAMUS** directory must contain the following files or directories:\n```grapha\n├── CAMUS\n│   ├── training\n│   │   ├── patient0001\n│   │   ├── ...\n│   │   └── patient0450\n│   ├── testing\n│   │   ├── patient0001\n│   │   ├── ...\n│   │   └── patient0050\n```\n- **ECHONET** directory must contain the following files or directories:\n```grapha\n├── ECHONET\n│   ├── ...\n│   ├── FileList.csv\n│   ├── VolumeTracings.csv\n│   ├── Videos\n│   │   ├── 0X1A0A263B22CCD966.avi\n│   │   └── ...\n```\n- **HMCQU** directory must contain the following files or directories:\n```grapha\n├── HMCQU\n│   ├── ...\n│   ├── A4C.xlsx\n│   ├── HMC-QU\n│   │   ├── A4C\n│   │   │   ├── ES0001 _4CH_1.avi\n│   │   │   └── ...\n│   ├── LV Ground-truth Segmentation Masks\n│   │   ├── Mask_ES0001 _4CH_1.mat\n│   │   └── ...\n```\nAfter downloading the data, you can run the following scripts to preprocess and split the data:\n\n```bash\ncd code/FedCVD/\nbash scripts/preprocess/preprocess.sh\nbash scripts/preprocess/split.sh\n```\n\n### Environment Setup\nYou can use the following scripts to set up the environment:\n\n```bash\ncd code/FedCVD/\nconda create -n fedcvd_env python=3.11 -y\nconda activate fedcvd_env\npip install -r requirements.txt\n```\n\n## Usage\nYou can run the scripts in the `code/FedCVD/scripts` directory to reproduce our experiments.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmilelab-fl%2Ffedcvd","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsmilelab-fl%2Ffedcvd","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsmilelab-fl%2Ffedcvd/lists"}