{"id":26507633,"url":"https://github.com/guaishou74851/dccm","last_synced_at":"2025-03-20T23:29:26.910Z","repository":{"id":185248842,"uuid":"645764096","full_name":"Guaishou74851/DCCM","owner":"Guaishou74851","description":"(Nature Communications Engineering 2024) Compressive Confocal Microscopy Imaging at the Single-Photon Level with Ultra-Low Sampling Ratios [PyTorch]","archived":false,"fork":false,"pushed_at":"2025-03-09T07:00:30.000Z","size":812,"stargazers_count":17,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-09T08:17:40.606Z","etag":null,"topics":["compressed-sensing","compressive-sampling","compressive-sensing","computer-vision","deep-neural-networks","deep-unfolding","deep-unrolling","image-reconstruction"],"latest_commit_sha":null,"homepage":"https://nature.com/articles/s44172-024-00236-x","language":"Python","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/Guaishou74851.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":"2023-05-26T11:35:55.000Z","updated_at":"2025-03-09T07:00:34.000Z","dependencies_parsed_at":"2024-05-19T11:32:26.710Z","dependency_job_id":"be4bd40f-c2ef-4d1b-9a3b-af1375d2d27a","html_url":"https://github.com/Guaishou74851/DCCM","commit_stats":null,"previous_names":["guaishou74851/dccm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Guaishou74851%2FDCCM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Guaishou74851%2FDCCM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Guaishou74851%2FDCCM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Guaishou74851%2FDCCM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Guaishou74851","download_url":"https://codeload.github.com/Guaishou74851/DCCM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244709580,"owners_count":20497097,"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":["compressed-sensing","compressive-sampling","compressive-sensing","computer-vision","deep-neural-networks","deep-unfolding","deep-unrolling","image-reconstruction"],"created_at":"2025-03-20T23:29:26.497Z","updated_at":"2025-03-20T23:29:26.904Z","avatar_url":"https://github.com/Guaishou74851.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# (Nature Communications Engineering 2024) Compressive Confocal Microscopy Imaging at the Single-Photon Level with Ultra-Low Sampling Ratios [PyTorch]\r\n\r\n[![icon](https://img.shields.io/badge/Nature-Paper-\u003cCOLOR\u003e.svg)](https://www.nature.com/articles/s44172-024-00236-x) ![visitors](https://visitor-badge.laobi.icu/badge?page_id=Guaishou74851.DCCM)\r\n\r\nShuai Liu\\*, [Bin Chen](https://scholar.google.com/citations?user=aZDNm98AAAAJ)\\*, Wenzhen Zou, [Hao Sha](https://scholar.google.com/citations?user=-mqUZ8oAAAAJ), Xiaochen Feng, [Sanyang Han](https://www.sigs.tsinghua.edu.cn/hsy/main.htm), [Xiu Li](https://scholar.google.com/citations?user=Xrh1OIUAAAAJ), Xuri Yao, [Jian Zhang](https://jianzhang.tech/)†, and [Yongbing Zhang](https://scholar.google.com/citations?user=0KlvTEYAAAAJ)†\r\n\r\n*Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China.*\r\n\r\n*School of Electronic and Computer Engineering, Peking University, Shenzhen, China.*\r\n\r\n*School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China.*\r\n\r\n*Center for Quantum Technology Research, School of Physics, Beijing Institute of Technology, Beijing, China.*\r\n\r\n\\* Equal contribution   † Corresponding authors\r\n\r\nAccepted for publication in [Communications Engineering](https://www.nature.com/commseng/) (Nature Communications) 2024.\r\n\r\n⭐ If DCCM is helpful to you, please star this repo. Thanks! 🤗\r\n\r\n## 📝 Abstract\r\n\r\nLaser-scanning confocal microscopy serves as a critical instrument for microscopic research in biology. However, it suffers from low imaging speed and high phototoxicity. Here we build a novel deep compressive confocal microscope, which employs a digital micromirror device as a coding mask for single-pixel imaging and a pinhole for confocal microscopic imaging respectively. Combined with a deep learning reconstruction algorithm, our system is able to achieve high-quality confocal microscopic imaging with low phototoxicity. Our imaging experiments with fluorescent microspheres demonstrate its capability of achieving single-pixel confocal imaging with a sampling ratio of only approximately 0.03% in specific sparse scenarios. Moreover, the deep compressive confocal microscope allows single-pixel imaging at the single-photon level, thus reducing the excitation light power requirement for confocal imaging and suppressing the phototoxicity. We believe that our system has great potential for long-duration and high-speed microscopic imaging of living cells.\r\n\r\n## 🍭 Overview\r\n\r\n![overview](figs/overview.png)\r\n\r\n## ⚙ Environment\r\n\r\n```shell\r\ntorch.__version__ == '2.2.1+cu121'\r\nnumpy.__version__ == '1.24.4'\r\nskimage.__version__ == '0.21.0'\r\n```\r\n\r\n## 📚 Data and Pretrained Model Weights\r\n\r\nDownload the [data](https://drive.google.com/file/d/1FCVwqjb8_J-yTc47t1E0mF8TlM-NdMp5/view) and [pretrained model weights](https://drive.google.com/file/d/1tHohEMx35Dg5qh8X-15CQesx6Q0mDTpv/view). Unzip the files into `./data` and `./code/weight` directories, respectively.\r\n\r\nThe paths of all files should be:\r\n\r\n```\r\n.\r\n├── README.md\r\n├── code\r\n│   ├── model.py\r\n│   ├── test.py\r\n│   ├── test.sh\r\n│   ├── train.py\r\n│   ├── train.sh\r\n│   ├── utils.py\r\n│   └── weight\r\n│       ├── f-actin\r\n│       │   └── layer_9_f_128\r\n│       │       └── net_params_30000.pkl\r\n│       ├── flureoscent_microsphere\r\n│       │   └── layer_9_f_128\r\n│       │       └── net_params_30000.pkl\r\n│       ├── nucleus\r\n│       │   └── layer_9_f_128\r\n│       │       └── net_params_30000.pkl\r\n│       └── potato_tuber\r\n│           └── layer_9_f_128\r\n│               └── net_params_30000.pkl\r\n├── data\r\n│   ├── A_128.npy\r\n│   ├── A_32.npy\r\n│   ├── f-actin\r\n│   │   ├── test_X.npy\r\n│   │   ├── test_X_WF.npy\r\n│   │   ├── test_Y128.npy\r\n│   │   ├── test_Y32.npy\r\n│   │   ├── train_X.npy\r\n│   │   ├── train_X_WF.npy\r\n│   │   ├── train_Y128.npy\r\n│   │   └── train_Y32.npy\r\n│   ├── flureoscent_microsphere\r\n│   │   ├── test_X.npy\r\n│   │   ├── test_X_WF.npy\r\n│   │   ├── test_Y128.npy\r\n│   │   ├── test_Y32.npy\r\n│   │   ├── train_X.npy\r\n│   │   ├── train_X_WF.npy\r\n│   │   ├── train_Y128.npy\r\n│   │   └── train_Y32.npy\r\n│   ├── nucleus\r\n│   │   ├── test_X.npy\r\n│   │   ├── test_X_WF.npy\r\n│   │   ├── test_Y128.npy\r\n│   │   ├── test_Y32.npy\r\n│   │   ├── train_X.npy\r\n│   │   ├── train_X_WF.npy\r\n│   │   ├── train_Y128.npy\r\n│   │   └── train_Y32.npy\r\n│   └── potato_tuber\r\n│       ├── test_X.npy\r\n│       ├── test_X_WF.npy\r\n│       ├── test_Y128.npy\r\n│       ├── test_Y32.npy\r\n│       ├── train_X.npy\r\n│       ├── train_X_WF.npy\r\n│       ├── train_Y128.npy\r\n│       └── train_Y32.npy\r\n└── figs\r\n    └── overview.png\r\n```\r\n\r\n## ⚡ Test\r\n\r\n```shell\r\ncd code\r\npython test.py --data_type=nucleus\r\npython test.py --data_type=flureoscent_microsphere\r\npython test.py --data_type=f-actin\r\npython test.py --data_type=potato_tuber\r\n```\r\n\r\nThe reconstructed images will be in `./code/result`.\r\n\r\n## 🔥 Train\r\n\r\n```shell\r\ncd code\r\npython train.py --data_type=nucleus\r\npython train.py --data_type=flureoscent_microsphere\r\npython train.py --data_type=f-actin\r\npython train.py --data_type=potato_tuber\r\n```\r\n\r\nThe log and model files will be in `./code/log` and `./code/weight`, respectively.\r\n\r\n## 🎓 Citation\r\n\r\nIf you find the code helpful in your research or work, please cite the following paper:\r\n\r\n```latex\r\n@article{liu2024compressive,\r\n  title={Compressive confocal microscopy imaging at the single-photon level with ultra-low sampling ratios},\r\n  author={Liu, Shuai and Chen, Bin and Zou, Wenzhen and Sha, Hao and Feng, Xiaochen and Han, Sanyang and Li, Xiu and Yao, Xuri and Zhang, Jian and Zhang, Yongbing},\r\n  journal={Communications Engineering},\r\n  volume={3},\r\n  number={1},\r\n  pages={88},\r\n  year={2024},\r\n  publisher={Nature Publishing Group UK London}\r\n}\r\n```\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fguaishou74851%2Fdccm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fguaishou74851%2Fdccm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fguaishou74851%2Fdccm/lists"}