{"id":22326116,"url":"https://github.com/mrphys/hyperslice","last_synced_at":"2025-06-27T10:06:56.326Z","repository":{"id":174930357,"uuid":"648157253","full_name":"mrphys/HyperSLICE","owner":"mrphys","description":null,"archived":false,"fork":false,"pushed_at":"2023-11-21T16:22:36.000Z","size":60736,"stargazers_count":0,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-27T10:05:31.350Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/mrphys.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":"2023-06-01T10:34:41.000Z","updated_at":"2023-06-13T09:13:12.000Z","dependencies_parsed_at":"2025-01-31T07:39:06.189Z","dependency_job_id":null,"html_url":"https://github.com/mrphys/HyperSLICE","commit_stats":null,"previous_names":["mrphys/hyperslice"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mrphys/HyperSLICE","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mrphys%2FHyperSLICE","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mrphys%2FHyperSLICE/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mrphys%2FHyperSLICE/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mrphys%2FHyperSLICE/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mrphys","download_url":"https://codeload.github.com/mrphys/HyperSLICE/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mrphys%2FHyperSLICE/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":262235780,"owners_count":23279566,"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":"2024-12-04T02:15:47.283Z","updated_at":"2025-06-27T10:06:56.284Z","avatar_url":"https://github.com/mrphys.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"HyperSLICE: HyperBand optimised Spiral for Low-latency Interactive Cardiac Examination\n======================================================================================\n\nDr. Olivier Jaubert, Dr. Javier Montalt-Tordera, Dr. Daniel Knight, Pr.\nSimon Arridge, Dr. Jennifer Steeden, Pr. Vivek Muthurangu\n\nSynopsis: \n---------\n\nA modified FastDVDnet \\[1\\] network is trained for interactive and low latency cardiac MRI imaging.\nProvided code provides optimized trajectory, model training and offline reconstruction as implemented for the paper.\n\nThe ethics does not allow sharing medical image data. \nThe code uses natural images of roses with additional simulation of the coils and simple motion.   \n\nExample with abrupt image change: Input - Truth - Reconstructed\n-------\n\n\nhttps://github.com/mrphys/HyperSLICE/assets/68073827/373de9ca-e23e-4adb-ae22-36ef758b539a\n\n------------------------------------------------------\n\nInstallation\n============\n\nAll required packages can be installed using conda in a virtual environment:\n\n``` {.console}\n$ conda env create --name hyperslice --file environment.yml\n```\n\nNote that only Linux is supported.\n\nTraining and testing\n====================\n\nOnce the environment created, activate using:\n\n``` {.console}\n$ conda activate hyperslice\n```\n\nYou can then run:\n\n-   the python file example.py file from project directory.\n\n``` {.console}\n$ python example.py\n```\n\n-   or the ipython notebook example.ipynb (to see intermediate results)\n\nResults are saved in ./Training\\_folder (as in the already trained\nexemple model ./Training\\_folder/Exemple\\_Trained\\_FastDVDnet)\n\nLogs can be visualised using tensorboard:\n\n``` {.console}\n$ tensorboard --logdir path_to_directory\n```\n\nAcknowledgments\n===============\n\nNetwork architecture inspired from original FastDVDnet \\[1\\].\nCode relies heavily on TensorFlow \\[2\\] and TensorFlow\\_MRI \\[3\\].\n\n\\[1\\] ​​Tassano, M., Delon, J., \u0026 Veit, T. (2020). FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1351–1360.\n\n\\[2\\] Abadi M, Barham P, Chen J, et al. TensorFlow: A System for Large-Scale Machine Learning TensorFlow: A system for large-scale machine learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation 2016:265--283.\n\n\\[3\\] Montalt Tordera J. TensorFlow MRI. 2022 doi:10.5281/ZENODO.7120930.\nhttps://pypi.org/project/tensorflow-mri/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmrphys%2Fhyperslice","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmrphys%2Fhyperslice","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmrphys%2Fhyperslice/lists"}