{"id":18785302,"url":"https://github.com/andreped/fp-dsa-plugin","last_synced_at":"2025-04-13T12:33:53.750Z","repository":{"id":109858512,"uuid":"604341123","full_name":"andreped/FP-DSA-plugin","owner":"andreped","description":"Digital Slide Archive plugin to enable FAST deployment of pretrained CNNs for digital pathology","archived":false,"fork":false,"pushed_at":"2023-11-16T14:58:08.000Z","size":7104,"stargazers_count":7,"open_issues_count":2,"forks_count":1,"subscribers_count":5,"default_branch":"main","last_synced_at":"2025-04-13T05:36:26.184Z","etag":null,"topics":["cpp","deep-learning","digital-pathology","digital-slide-archive","fast","fastpathology","gpu","histopathology","large-image","plugin","python","real-time","tensorrt"],"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/andreped.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":"2023-02-20T21:17:42.000Z","updated_at":"2024-07-07T15:43:49.000Z","dependencies_parsed_at":"2023-06-12T07:45:42.759Z","dependency_job_id":"2c9bfca2-2785-4038-8e90-84dfa89249dd","html_url":"https://github.com/andreped/FP-DSA-plugin","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreped%2FFP-DSA-plugin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreped%2FFP-DSA-plugin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreped%2FFP-DSA-plugin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andreped%2FFP-DSA-plugin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andreped","download_url":"https://codeload.github.com/andreped/FP-DSA-plugin/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248714740,"owners_count":21149959,"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":["cpp","deep-learning","digital-pathology","digital-slide-archive","fast","fastpathology","gpu","histopathology","large-image","plugin","python","real-time","tensorrt"],"created_at":"2024-11-07T20:46:14.730Z","updated_at":"2025-04-13T12:33:52.122Z","avatar_url":"https://github.com/andreped.png","language":"Python","readme":"# FastPathology Digital Slide Archive (FP-DSA) extension\n\n[![License](https://img.shields.io/badge/License-MIT-green.svg)](https://opensource.org/licenses/MIT)\n[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.8124068.svg)](https://doi.org/10.5281/zenodo.8124068)\n\n**DISCLAIMER:** This is a work in progress. When I have the plugin properly working and stable, I will make a public docker image, and make a release here.\n\nNote that this setup has been tested against Ubuntu 18.04 and 20.04. It should likely work on Windows 10, but on macOS there is a conflict between OpenGL/OpenCL resulting in a `RuntimeError: clGetPlatformIDs`.\n\nClick `watch` in the top right if this project interests you and want to be updated when it is ready to be tested.\n\n\u003cp style=\"text-align: center;\"\u003e\n  \u003cimg src=\"assets/snapshot_nuclei.png\" width=\"45%\" style=\"background-color:black\"\u003e\n  \u003cimg src=\"assets/snapshot_classification.png\" width=\"45%\" style=\"background-color:black\"\u003e\n\u003c/p\u003e\n\n\n## 🎊 Features\n\nThe software is still in development, but some key features have been added such as:\n\n* Uses pyFAST backend to run FAST pipelines (FPLs)\n* Developed generic backend tool for running FPLs through the UI and convert predictions to the JSON format\n* Ability to run patch-wise classification and segmentation models\n* Render classification predictions as heatmaps and segmentation objects as boundaries\n* Store predictions in database, access, download, and modify these through the UI\n\n\n## 🐳 Requirements\n\nDSA needs to be installed. Follow the instructions [here](https://github.com/DigitalSlideArchive/digital_slide_archive/tree/master/devops/dsa) on how to do so.\n\nIn addition, docker need to be setup such that it works with pyFAST. For that I strongly recommend installing Docker desktop. You might also need to install the nvidia docker to make it work properly:\n\n```\nsudo apt update\nsudo apt-get install -y nvidia-docker2\nsudo systemctl restart docker\n```\n\n\n## 💻 Installation\n\nClone the repository:\n```\ngit clone https://github.com/andreped/FP-dsa-plugin.git\n```\n\nBuild the docker image for the plugin:\n```\ncd dsa/\ndocker build -t fastpathology .\n```\n\nTo add the plugin to DSA, choose `Upload new Task` under `Slicer CLI Web Tasks` in the DSA web UI, and write `fastpathology:latest` and click `Import image`. The plugin can then be used from the Analysis Page.\n\n\n## 👏 Acknowledgements\n\nThe core was built based on [pyFAST](https://github.com/smistad/FAST), and the plugin was inspired by the plugins made for [MONAILabel](https://github.com/Project-MONAI/MONAILabel/tree/main/plugins/dsa) and [HistomicsTK](https://github.com/DigitalSlideArchive/HistomicsTK/tree/master/histomicstk/cli). Conversion of pyFAST's pyramidal TIFF annotations to HistomicsTK's JSON annotations was enabled using [OpenCV](https://github.com/opencv/opencv).\n\nThe plugin was made for the [Digital Slide Archive](https://github.com/DigitalSlideArchive/digital_slide_archive) which has developed an open and extremely robust and user-friendly web solution for archiving, visualizing, processing, and annotating large microscopy images. Building our methods on top of DSA was done with ease and credit to the developers such as [manthey](https://github.com/manthey) and [dgutman](https://github.com/dgutman) for addressing any issue and concerns we had at impressive speed!\n\n\n## ✨ License\n\nThe plugin has [MIT-License](https://github.com/andreped/FP-dsa-plugin/blob/main/LICENSE).\n\nNote that the different components used have their respective licenses. However, to the best of our knowledge, all dependencies used have permissive licenses with no real proprietary limitations.\n\n\n## 🔬 Citation\n\nIf you found this project relevant for your research, consider citing it by:\n```\n@software{pedersen2023fp_dsa_plugin,\n  author       = {André Pedersen},\n  title        = {andreped/FP-DSA-plugin: v0.0.1},\n  month        = jul,\n  year         = 2023,\n  publisher    = {Zenodo},\n  version      = {v0.0.1},\n  doi          = {10.5281/zenodo.8124068},\n  url          = {https://doi.org/10.5281/zenodo.8124068}\n}\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandreped%2Ffp-dsa-plugin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandreped%2Ffp-dsa-plugin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandreped%2Ffp-dsa-plugin/lists"}