{"id":19473286,"url":"https://github.com/xinario/sagan","last_synced_at":"2025-04-25T12:31:30.943Z","repository":{"id":53207431,"uuid":"105169515","full_name":"xinario/SAGAN","owner":"xinario","description":"Sharpness-aware Low Dose CT Denoising Using Conditional Generative Adversarial Network","archived":false,"fork":false,"pushed_at":"2022-01-04T00:25:38.000Z","size":800,"stargazers_count":131,"open_issues_count":6,"forks_count":31,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-04-03T22:01:42.803Z","etag":null,"topics":["computed-tomography","convolutional-neural-networks","deep-learning","denoising","gan","generative-adversarial-network","image-to-image-translation","kaggle","low-dose"],"latest_commit_sha":null,"homepage":"","language":"Lua","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/xinario.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}},"created_at":"2017-09-28T16:04:02.000Z","updated_at":"2025-03-17T11:51:16.000Z","dependencies_parsed_at":"2022-09-10T07:10:14.349Z","dependency_job_id":null,"html_url":"https://github.com/xinario/SAGAN","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinario%2FSAGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinario%2FSAGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinario%2FSAGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinario%2FSAGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xinario","download_url":"https://codeload.github.com/xinario/SAGAN/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250817670,"owners_count":21492198,"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":["computed-tomography","convolutional-neural-networks","deep-learning","denoising","gan","generative-adversarial-network","image-to-image-translation","kaggle","low-dose"],"created_at":"2024-11-10T19:18:00.262Z","updated_at":"2025-04-25T12:31:29.778Z","avatar_url":"https://github.com/xinario.png","language":"Lua","funding_links":[],"categories":[],"sub_categories":[],"readme":"## SAGAN\n#### Update 2019.01.22\nFor those who want to use the piglet dataset for CT denoising research and use this work as a baseline, please refer to this [issue](https://github.com/xinario/SAGAN/issues/8#issue-401978079) for details on how I used it.\n\n#### Update 2018.03.27\nThe piglet dataset we used in the publication is now open for download! Please find the link in my [personal webpage](https://xinario.github.io). (Note: for non-commercial use only)\n\n##\nThis repo provides the trained denoising model and testing code for low dose CT denoising as described in our [paper](https://link.springer.com/article/10.1007/s10278-018-0056-0).\nHere are some randomly picked denoised results on low dose CTs from this [kaggle challenge](https://www.kaggle.com/c/data-science-bowl-2017/data). \n\u003cimg src=\"imgs/sample.jpg\" width=\"900px\"/\u003e\n\n## How to use\nTo better use this repo, please make sure the dose level of the LDCTs are larger than 0.71 mSv.\n### Prerequistites\n- Linux or OSX\n- NVIDIA GPU\n- Python 3.x\n- Torch7\n\n### Getting Started\n- Install [Torch7](http://torch.ch/docs/getting-started.html#_)\n- Install torch packages nngraph and hdf5\n```bash\nluarocks install nngraph\nluarocks install hdf5\n```\n- Install [Python 3.x](https://www.anaconda.com/download/#macos) (recommend using Anaconda)\n- Install python dependencies \n```\npip install -r requirements.txt\n```\n- Clone this repo:\n```bash\ngit clone git@github.com:xinario/SAGAN.git\ncd SAGAN\n```\n\n\n- Download the pretrained denoising model from [here](https://1drv.ms/u/s!Aj4IQl4ug0_9gj4TTqVW1JhhHG5f) and put it into the \"checkpoints/SAGAN\" folder\n\n- Prepare your test set with the provided python script\n```bash\n#make a directory inside the root SAGAN folder to store your raw dicoms, e.g. ./dicoms\nmkdir dicoms\n#then put all your low dose CT images of dicom format into this folder and run\npython pre_process.py  --input ./dicoms --output ./datasets/experiment/test\n#all your test images would now be saved as uint16 png format inside folder ./datasets/experiment/test. \n\n```\n- Test the model:\n```bash\nDATA_ROOT=./datasets/experiment name=SAGAN which_direction=AtoB phase=test th test.lua\n#the results are saved in ./result/SAGAN/latest_net_G_test/result.h5\n```\n- Display the result with a specific window, e.g. abdomen. Window type can be changed to 'abdomen', 'bone' or 'none'\n```bash\npython post_process.py --window 'abdomen'\n```\nNow you can view the result by open the html file index.html sitting in the root folder\n\n### Citations\nIf you find it useful and are using the code/model/dataset provided here in a publication, please cite our paper:\n\nYi, X. \u0026 Babyn, P. J Digit Imaging (2018). https://doi.org/10.1007/s10278-018-0056-0\n\n\n\n### Acknowlegements\nCode borrows heavily from [pix2pix](https://github.com/phillipi/pix2pix)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinario%2Fsagan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxinario%2Fsagan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinario%2Fsagan/lists"}