{"id":15176691,"url":"https://github.com/cgalaz01/supinn","last_synced_at":"2026-02-08T19:03:00.768Z","repository":{"id":254085904,"uuid":"845417716","full_name":"cgalaz01/supinn","owner":"cgalaz01","description":"This repository contains the source code for the paper: \"PINNing Cerebral Blood Flow: Analysis of Perfusion MRI in Infants using Physics-Informed Neural Networks\"","archived":false,"fork":false,"pushed_at":"2024-08-22T12:44:11.000Z","size":1243,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-09-27T13:41:02.274Z","etag":null,"topics":["neuroimaging","physics-informed-neural-networks","pinns","tensorflow"],"latest_commit_sha":null,"homepage":"","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/cgalaz01.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-08-21T07:59:52.000Z","updated_at":"2024-08-22T12:44:14.000Z","dependencies_parsed_at":"2024-08-21T10:30:01.926Z","dependency_job_id":"2c021ede-dce1-4cca-a4d8-942bcc875eaf","html_url":"https://github.com/cgalaz01/supinn","commit_stats":{"total_commits":3,"total_committers":2,"mean_commits":1.5,"dds":"0.33333333333333337","last_synced_commit":"ddd9098d85f560b49b1a2ec2d9424684d6a266f9"},"previous_names":["cgalaz01/supinn"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cgalaz01%2Fsupinn","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cgalaz01%2Fsupinn/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cgalaz01%2Fsupinn/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cgalaz01%2Fsupinn/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cgalaz01","download_url":"https://codeload.github.com/cgalaz01/supinn/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":219862887,"owners_count":16555951,"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":["neuroimaging","physics-informed-neural-networks","pinns","tensorflow"],"created_at":"2024-09-27T13:40:24.516Z","updated_at":"2026-02-08T19:03:00.762Z","avatar_url":"https://github.com/cgalaz01.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# PINNing Cerebral Blood Flow: Analysis of Perfusion MRI in Infants using Physics-Informed Neural Networks\n\n## Abstract\n\nThis repository contains the source code, data, and supplementary materials for the research paper titled **\"PINNing Cerebral Blood Flow: Analysis of Perfusion MRI in Infants using Physics-Informed Neural Networks\"** by Christoforos Galazis, Ching-En Chiu, Tomoki Arichi, Anil A. Bharath and Marta Varela.\n\nThis project introduces SUPINN, a novel spatial uncertainty-based physics-informed neural network (PINN) (see Fig.2), designed to estimate cerebral blood flow (CBF) and other parameters from noisy arterial spin labeling (ASL) MRI data in infants (see Fig.1). By incorporating spatial uncertainties, SUPINN outperforms traditional methods in estimating CBF, bolus arrival time, and blood relaxation time, providing physiologically plausible and spatially smooth results. This framework has the potential to improve our understanding of infant cardio-brain networks, aiding in the detection and management of neurological issues in this vulnerable population.\n\n| ![asl](figures/pwi_example.png \"Example of a perfusion weighted image acquired using aterial spin labelling\") | \n|:--:|\n| _\u003cspan id=\"Fig1\"\u003eFig. 1\u003c/span\u003e_ A representative 32-week postmenstrual case showing: A) $T_2$-weighted image highlighting the ASL imaging slice (orange); B) Subsampled perfusion-weighted image time series; and C) The measured perfusion signal of a single voxel over the entire duration, along with the corresponding ground-truth analytical model. |\n\n| ![supinn](figures/model.png \"Overview of the proposed SUPINN\") | \n|:--:|\n| _\u003cspan id=\"Fig2\"\u003eFig. 2\u003c/span\u003e_ Overview of our proposed SUPINN model, depicted here in a 2-branch variant for illustration purposes, but adaptable to larger configurations. This study employs a 3-branch model based on empirical findings. |\n\n\n## Repository Structure\n\n```plaintext\n.\n├── data_mat/                 # The expected location of the dataset (research data is not currently available)\n├── src/                      # Source code for the models and experiments\n│   ├── data/                 # Code related to data loading and processing\n│   ├── model/                # Code related to PINN model\n│   └── run_training.py       # The main execution file\n├── figures/                  # Figures used in the paper\n├── README.md                 # This README file\n└── environment.yml           # Required packages and dependencies\n```\n\n## Installation\n\n### Requirements\n\nEnsure you have Anaconda or Miniconda installed.\n\n### Setup\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/cgalaz01/supinn.git\n   cd supinn\n   ```\n \n2. Create a new conda environment and isntall packages:\n   ```bash\n   conda env create -f environment.yml\n   ```\n   Please note that the YAML file includes instructions specifically for installing the CPU version of TensorFlow. See https://www.tensorflow.org/install/pip on how to install the GPU version on your system. \n   \n   \n3. Activate new environment:\n   ```bash\n   conda activate supinn\n   ```\n   \n## Usage\n\nRun the PINN training script using the following command:\n   ```bash\n   python run_training.py [options]\n   ```\n   \nTo see available options run:\n   ```bash\n   python run_training.py --help\n   ```\n   \nThe default arguments are used to setup the proposed SUPINN model.\n\n## License\n\nThis project is licensed under the MIT License - see the LICENSE file for details.\n\n## Contact\n\nFeel free to open an issue or submit a pull request if you find any issues or have suggestions for improvements.\n\n## Citation\n\nIf you found this code useful for your project please cite as:\n```\n@article{galazis2025pinning,\n  title={PINNing cerebral blood flow: analysis of perfusion MRI in infants using physics-informed neural networks},\n  author={Galazis, Christoforos and Chiu, Ching-En and Arichi, Tomoki and Bharath, Anil A and Varela, Marta},\n  journal={Frontiers in Network Physiology},\n  volume={5},\n  pages={1488349},\n  year={2025},\n  publisher={Frontiers Media SA}\n}\n```\n\t\n## Acknowledgement\n\nThis work was supported by the UK Research and Innovation (UKRI) Centres of Doctoral Training (CDT) in Artificial Intelligence for Healthcare (AI4H) (http://ai4health.io) (Grant No. EP/S023283/1), St George’s Hospital Charity, the NIHR Imperial Biomedical Research Centre (BRC), and the British Heart Foundation Centre of Research Excellence at Imperial College London (RE/18/4/34215).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcgalaz01%2Fsupinn","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcgalaz01%2Fsupinn","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcgalaz01%2Fsupinn/lists"}