{"id":20507411,"url":"https://github.com/hahnec/rf-ulm","last_synced_at":"2025-07-31T10:17:02.737Z","repository":{"id":197874216,"uuid":"582267692","full_name":"hahnec/rf-ulm","owner":"hahnec","description":"RF-ULM: Ultrasound Localization Microscopy Learned from Radio-Frequency Wavefronts","archived":false,"fork":false,"pushed_at":"2024-09-05T08:57:56.000Z","size":127490,"stargazers_count":26,"open_issues_count":0,"forks_count":8,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-13T21:52:40.500Z","etag":null,"topics":["ceus","contrast-enhancement","deep-learning","imaging","localization","medical","medical-imaging","microbubble","microscopy","neural-network","pytorch","ulm","ultrasound","vascular","vascular-flow"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hahnec.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,"zenodo":null}},"created_at":"2022-12-26T09:23:52.000Z","updated_at":"2025-04-06T13:28:38.000Z","dependencies_parsed_at":"2023-12-26T20:50:15.892Z","dependency_job_id":"a4c4859f-879f-4746-be04-c4802ee9ca3e","html_url":"https://github.com/hahnec/rf-ulm","commit_stats":null,"previous_names":["hahnec/rf-ulm"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/hahnec/rf-ulm","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hahnec%2Frf-ulm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hahnec%2Frf-ulm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hahnec%2Frf-ulm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hahnec%2Frf-ulm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hahnec","download_url":"https://codeload.github.com/hahnec/rf-ulm/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hahnec%2Frf-ulm/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":268023444,"owners_count":24183101,"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":"2025-07-31T02:00:08.723Z","response_time":66,"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":["ceus","contrast-enhancement","deep-learning","imaging","localization","medical","medical-imaging","microbubble","microscopy","neural-network","pytorch","ulm","ultrasound","vascular","vascular-flow"],"created_at":"2024-11-15T20:13:56.957Z","updated_at":"2025-07-31T10:17:02.679Z","avatar_url":"https://github.com/hahnec.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## RF-ULM: Radio-Frequency Ultrasound Localization Microscopy\n\n[![arXiv paper link](https://img.shields.io/badge/paper-arXiv:2306.08281-red)](https://arxiv.org/pdf/2310.01545.pdf)\n\n### Overview\n\u003cdiv style=\"background-color: white;\"\u003e\n\u003cimg src=\"https://github.com/hahnec/rf-ulm/blob/master/docs/rf-ulm_concept.svg\" width=\"500\" scale=\"100%\"\u003e\n\u003c/div\u003e\nNMS: Non-Maximum-Suppression\n\u003cbr\u003e\nMap: Geometric point transformation from RF to B-mode coordinate space\n\u003cbr\u003e\n\u003cbr\u003e\n\n### SG-SPCN Architecture\n\u003cdiv style=\"background-color: white;\"\u003e\n\u003cimg src=\"https://github.com/hahnec/rf-ulm/blob/master/docs/rf-ulm_arch.svg\" width=\"780\" scale=\"100%\"\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\n### Demos\n#### 1. ULM Animation Demo\n\u003cvideo src=\"https://github.com/hahnec/rf-ulm/assets/33809838/e37aee11-c07f-4d9b-8672-5a9b466edd26\" controls autoplay loop muted\u003e\n    Link: https://github.com/hahnec/rf-ulm/assets/33809838/e37aee11-c07f-4d9b-8672-5a9b466edd26\n\u003c/video\u003e\n\u003cb\u003eNote\u003c/b\u003e: The video starts in slow motion and then exponentially increases the frame rate for better visualization.\n\u003cbr\u003e\n\n#### 2. Prediction Frames Demo\n\u003cvideo src=\"https://github.com/hahnec/rf-ulm/assets/33809838/4f4002bb-01e1-405f-aa56-e3c6b7a3b654\" controls autoplay loop muted\u003e\n    Link: https://github.com/hahnec/rf-ulm/assets/33809838/4f4002bb-01e1-405f-aa56-e3c6b7a3b654\n\u003c/video\u003e\n\n\u003cb\u003eNote\u003c/b\u003e: Colors represent localizations from each plane wave emission angle.\n\n### Datasets\n\n*In vivo* (inference): https://doi.org/10.5281/zenodo.7883227\n\n*In silico* (training+inference): https://doi.org/10.5281/zenodo.4343435\n\u003cbr\u003e\n\u003cbr\u003e\n\n### Short presentation at IUS 2023\n\n[\u003cimg src=\"https://img.youtube.com/vi/eJJXnXay-fU/hqdefault.jpg\" width=\"480\" height=\"360\"\n/\u003e](https://www.youtube.com/embed/eJJXnXay-fU)\n\n### Installation\n\nIt is recommended to use a UNIX-based system for development. For installation, run (or work along) the following bash script:\n\n```\n\u003e bash install.sh\n```\n\nNote that the dataloader module is missing in this repository. My implementation is a hacky version of the work found at https://github.com/AChavignon/PALA, which was used as a reference in this project. When using data other than mentioned here, one would need to start writing this part from scratch. The simpletracker repository has not been used in the TMI publication and can be ignored.\n\n### Citation\n\nIf you use this project for your work, please cite:\n\n```\n@article{hahne:2024:rfulm,\n  author={Hahne, Christopher and Chabouh, Georges and Chavignon, Arthur and Couture, Olivier and Sznitman, Raphael},\n  journal={IEEE Transactions on Medical Imaging}, \n  title={RF-ULM: Ultrasound Localization Microscopy Learned From Radio-Frequency Wavefronts}, \n  year={2024},\n  volume={43},\n  number={9},\n  pages={3253-3262},\n  keywords={Location awareness;Radio frequency;Array signal processing;Superresolution;Convolution;Ultrasonic imaging;Kernel;Super-resolution;ultrasound;localization;microscopy;deep learning;neural network;beamforming},\n  doi={10.1109/TMI.2024.3391297}\n}\n\n```\n\n\u003c!--\n```\n@inproceedings{hahne:2023:learning,\n    author = {Christopher Hahne and Georges Chabouh and Olivier Couture and Raphael Sznitman},\n    title = {Learning Super-Resolution Ultrasound Localization Microscopy from Radio-Frequency Data},\n    booktitle= {2023 IEEE International Ultrasonics Symposium (IUS)},\n    address={},\n    month={Sep},\n    year={2023},\n    pages={1-4},\n}\n```\n\n\n```\n@misc{rfulm:2023,\n      title={RF-ULM: Deep Learning for Radio-Frequency Ultrasound Localization Microscopy}, \n      author={Christopher Hahne and Georges Chabouh and Arthur Chavignon and Olivier Couture and Raphael Sznitman},\n      year={2023},\n      eprint={},\n      archivePrefix={arXiv},\n      primaryClass={cs.CV}\n}\n```\n--\u003e\n\n### Acknowledgment\n\nThis research is funded by the Hasler Foundation under project number 22027.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhahnec%2Frf-ulm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhahnec%2Frf-ulm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhahnec%2Frf-ulm/lists"}