{"id":13717016,"url":"https://github.com/AICAN-Research/FAST-Pathology","last_synced_at":"2025-05-07T06:31:55.396Z","repository":{"id":37823925,"uuid":"196004095","full_name":"AICAN-Research/FAST-Pathology","owner":"AICAN-Research","description":"⚡ Open-source software for deep learning-based digital pathology","archived":false,"fork":false,"pushed_at":"2024-06-14T22:59:49.000Z","size":85097,"stargazers_count":133,"open_issues_count":26,"forks_count":27,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-05-02T09:06:36.957Z","etag":null,"topics":["computational-pathology","convolutional-neural-networks","cplusplus","deep-learning","deployment","digital-pathology","fastpathology","free-to-use","inference","machine-learning","opencl","opengl","openvino","pytorch","software","tensorflow","tensorrt"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AICAN-Research.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":".github/CODE_OF_CONDUCT.md","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":"2019-07-09T12:28:00.000Z","updated_at":"2025-04-27T23:21:14.000Z","dependencies_parsed_at":"2023-11-15T11:28:49.548Z","dependency_job_id":"9f8ece8f-0cbc-47f1-b1ae-45c3ea680cc4","html_url":"https://github.com/AICAN-Research/FAST-Pathology","commit_stats":{"total_commits":465,"total_committers":4,"mean_commits":116.25,"dds":0.2989247311827957,"last_synced_commit":"25769bf2c7b76b2b4b84a1982ba56e76a6032b77"},"previous_names":[],"tags_count":12,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AICAN-Research%2FFAST-Pathology","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AICAN-Research%2FFAST-Pathology/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AICAN-Research%2FFAST-Pathology/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AICAN-Research%2FFAST-Pathology/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AICAN-Research","download_url":"https://codeload.github.com/AICAN-Research/FAST-Pathology/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252826897,"owners_count":21810200,"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":["computational-pathology","convolutional-neural-networks","cplusplus","deep-learning","deployment","digital-pathology","fastpathology","free-to-use","inference","machine-learning","opencl","opengl","openvino","pytorch","software","tensorflow","tensorrt"],"created_at":"2024-08-03T00:01:16.861Z","updated_at":"2025-05-07T06:31:50.386Z","avatar_url":"https://github.com/AICAN-Research.png","language":"C++","funding_links":[],"categories":["Pathology"],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\u003cimg src=\"data/Icons/fastpathology_logo.png\" width=\"128\"\u003e\n\u003ch1 align=\"center\"\u003eFastPathology\u003c/h1\u003e\n\u003ch3 align=\"center\"\u003eOpen-source software for deep learning-based digital pathology\u003c/h3\u003e\n\n[![License](https://img.shields.io/badge/License-BSD%202--Clause-orange.svg)](https://opensource.org/licenses/BSD-2-Clause)\n![CI](https://github.com/AICAN-Research/FAST-Pathology/workflows/Build%20Windows/badge.svg?branch=master\u0026event=push)\n![CI](https://github.com/AICAN-Research/FAST-Pathology/workflows/Build%20Ubuntu/badge.svg?branch=master\u0026event=push)\n![CI](https://github.com/AICAN-Research/FAST-Pathology/workflows/Build%20macOS/badge.svg?branch=master\u0026event=push)\n \n**FastPathology** was created by researchers at SINTEF and the Norwegian University of Science and Technology (NTNU). A paper presenting the software and some benchmarks has been published in [IEEE Access](https://ieeexplore.ieee.org/document/9399433).\n \n \u003cimg src=\"data/Videos/fp_demo_v1.gif\" style=\"background-color:black\"\u003e\n\u003c/div\u003e\n\n## 💻 Getting started\n\nTo install FastPathology, follow the instructions for your operating system:\n\n\u003cdetails open\u003e\n\u003csummary\u003e\n\n### Windows (10 or newer)\u003c/summary\u003e\n* Download and run the Windows installer from the [release page](https://github.com/AICAN-Research/FAST-Pathology/releases/). \n  *Note: Windows might prompt you with a security warning, to proceed you must press \"More info\" followed by \"Run anyway\".*\n* Run **fastpathology** from your start menu.\n* To **uninstall** the application, go to start menu -\u003e remove programs -\u003e find fastpathology and select uninstall.\n  Optionally you can also delete your `C:/Users/\"your username\"/fastpathology/` which includes stored project results, pipelines, and models.\n  And the folder `C:/ProgramData/FAST/` which contains a cache.\n  \n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\n\n### Ubuntu Linux (18.04 or newer)\u003c/summary\u003e\n\n- Install OpenCL for Linux by downloading an implementation depending on the CPU/GPU you have:\n   - **NVIDIA** - Install [CUDA](https://developer.nvidia.com/cuda-downloads).\n   - **Intel** - Install the [OpenCL NEO driver](https://github.com/intel/compute-runtime/releases).\n   - **AMD** - Install the [ROCm stack](https://rocmdocs.amd.com/en/latest/Installation_Guide/Installation-Guide.html).\n   - If none of the above fits, you can try the [Portable Computing Lanauge (PCOL)](http://portablecl.org), although reduced performance is likely.\n* Download the debian package from the [release page](https://github.com/AICAN-Research/FAST-Pathology/releases/).\n* Install the debian package from the terminal or by double-clicking it:\n```bash\nsudo dpkg -i fastpathology_ubuntu*.deb\n```\n* Go to the folder `/opt/fastpathology/bin/` and run the **fastpathology** executable, or run it from the ubuntu menu (`windows button-\u003etype fastpathology`).\n* To **uninstall** the application, run the following in your terminal:\n```bash\nsudo apt remove fastpathology\n# Optionally, you can also delete your fastpathology folder \n# which includes stored project results, pipelines and models.\n# and the FAST folder which stores cache files.\nrm -Rf $HOME/fastpathology\nrm -Rf $HOME/FAST\n```\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\n\n### macOS (10.13 or newer)\u003c/summary\u003e\n\n*Note that the macOS version of FastPathology is experimental.*\n\n* Install [homebrew](https://brew.sh/) if you don't already have it. Then, install the following packages using homebrew:\n```bash\nbrew install openslide libomp\n```\n* Download and run the macOS installer (.dmg) from the [release page](https://github.com/AICAN-Research/FAST-Pathology/releases/). Download the x86_64 file if you have an Intel CPU, or download the arm64 file if you have an Apple Silicon (M1/M2) CPU.\n* In the installer, drag-and-drop the `FastPathology` bundle to the `Applications` directory.\n* When the copy is finished, double-click the `Applications` icon in the installer and right-click + open `FastPathology` from the Applications menu.\n* A warning should be prompted `\"macOS cannot verify the developer of FastPathology (...)\"`, click `open` and the program should launch.\n\n *Note: This is only required to be done once. For all future usage, launch FastPathology as a regular App bundle.*\n* To **uninstall** the application, delete the extracted folder.\n  Optionally, you can also delete the `/Users/\"your username\"/fastpathology/` folder, which includes stored project results, pipelines, and models.\n  And the folder `/Users/\"your username\"/FAST/` which contains a cache.\n\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\n\n### Optional: NVIDIA GPU Inference\u003c/summary\u003e\n\nIf you have an NVIDIA GPU on your machine you can enable high-speed inference by downloading and installing the following:\n* [CUDA 11](https://developer.nvidia.com/cuda-toolkit-archive)\n* [cuDNN 8.2](https://developer.nvidia.com/rdp/cudnn-archive)\n* [TensorRT 8.2](https://developer.nvidia.com/nvidia-tensorrt-download)\n\n**Note: Make sure to download the correct versions. NVIDIA GPU inference is not supported on Mac.**\n\n\u003c/details\u003e\n\n## License\n\nThe source code of FastPathology is licensed under the BSD 2-clause license, however the FastPathology program use and are linked with many great third-party libraries which have several different open source licenses, see the licenses folder in the installation folder for more details.\n\n## 📹 Demos and tutorials\n\nVery simple demonstrations of the platform can be found on [Youtube](https://www.youtube.com/channel/UC4GM2KW54-vEZ0M1kH5-oig). More in-depth demonstrations will be added in the future. Wikis and tutorials can be found in the [wiki](https://github.com/SINTEFMedtek/FAST-Pathology/wiki). More information can be found from the **pages** section on the right in the wiki home.\n\n[![Watch the video](doc/images/snapshot-youtube.png)](https://youtu.be/1s7jU6T7S3U?t=435)\n\n## 🎊 Features\n\nThe software is implemented in C++ based using [FAST](https://github.com/smistad/FAST). A wide range of features have been added to make working with whole slide images (WSIs) a piece of cake!\n* **Graphical User Interface -** User-friendly GUI for working with WSIs without any code interaction.\n* **Deep learning -** Deployment and support for multi-input/output convolutional neural networks (CNNs).\n* **Visualization -** Real-time streaming of predictions on top of the WSI with low memory cost.\n* **Use cases -** Patch-wise classification, low and high-resolution segmentation, and object detection are supported.\n* **Inference Engines -** FAST includes a variety of different inference engines, i.e. TensorFlow CPU/CUDA (support both TF v1 and v2 models), TensorRT (UFF and ONNX), OpenVINO (CPU/GPU/VPU), and ONNX Runtime (CPU/GPU).\n* **Text pipelines -** Possibility to create your own pipelines using the built-in script editor.\n* **Formats -** Through [OpenSlide](https://openslide.org/) FastPathology supports various WSI formats.\n\n## 🔬 Applications of FastPathology\n\n* Pettersen et al., Code-free development and deployment of deep segmentation models for digital pathology (2022), Frontiers in Medicine, https://doi.org/10.3389/fmed.2021.816281\n* Pedersen et al., H2G-Net: A multi-resolution refinement approach for segmentation of breast cancer region in gigapixel histopathological images (2022), Frontiers in Medicine, https://doi.org/10.3389/fmed.2022.971873\n* Røyset et al., Deep learning-based image analysis reveals significant differences in the number and distribution of mucosal CD3 and γδ T cells between Crohn's disease and ulcerative colitis (2022), The Journal of Pathology, https://doi.org/10.1002/cjp2.301\n* Høibø et al., Immunohistochemistry guided segmentation of benign epithelial cells, in situ lesions, and invasive epithelial cells in breast cancer slides (2023), arXiv (preprint), https://doi.org/10.48550/arXiv.2311.13261\n* Chiou et al., An immunohistochemical atlas of necroptotic pathway expression (2024), EMBO Molecular Medicine, https://doi.org/10.1038/s44321-024-00074-6\n\n\u003cdetails\u003e\n\u003csummary\u003e\n\n## 🔨 Development setup\u003c/summary\u003e\n\n1. Either\n   - [Download and install a release of FAST](https://fast.eriksmistad.no/install.html).\n   - [Compile and install FAST on your system](https://fast.eriksmistad.no/building-fast.html).\n2. Clone this repository\n   ```bash\n   git clone https://github.com/AICAN-Research/FAST-Pathology.git\n   ```\n3. Setup build environment using CMake  \n   *Linux (Ubuntu)*\n   ```bash\n   mkdir build\n   cd build\n   cmake .. -DFAST_DIR=/path/to/FAST/cmake/\n   ``` \n   *Windows (Visual Studio)*\n   Modify generator -G string to match your Visual studio version. This command will create a visual studio solution in your build folder.\n   ```bash\n   mkdir build\n   cd build\n   cmake .. -DFAST_DIR=C:\\path\\to\\FAST\\cmake\\ -G \"Visual Studio 16 2019\" -A x64\n   ```\n4. Build\n   ```bash\n   cmake --build . --config Release --target fastpathology\n   ```\n5. Run\n   *Linux (Ubuntu)*\n   ```bash\n   ./fastpathology\n   ```\n   *Windows*\n   ```powershell\n   cd Release\n   fastpathology.exe\n   ```\n\n**NOTE:** Visual Studio 19 has been tested with both FAST and FastPathology and works well.\n\n\u003c/details\u003e\n\n## ✨ How to cite\nPlease, consider citing our paper, if you find the work useful:\n\u003cpre\u003e\n@article{pedersen2021fastpathology,\n    author={Pedersen, André and Valla, Marit and Bofin, Anna M. and De Frutos, Javier Pérez and Reinertsen, Ingerid and Smistad, Erik},\n    journal={IEEE Access}, \n    title={{FastPathology: An Open-Source Platform for Deep Learning-Based Research and Decision Support in Digital Pathology}}, \n    year={2021},\n    volume={9},\n    number={},\n    pages={58216-58229},\n    doi={10.1109/ACCESS.2021.3072231}\n}\n\u003c/pre\u003e\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAICAN-Research%2FFAST-Pathology","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FAICAN-Research%2FFAST-Pathology","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FAICAN-Research%2FFAST-Pathology/lists"}