{"id":43406899,"url":"https://github.com/nibtehaz/MultiResUNet","last_synced_at":"2026-02-13T19:00:40.709Z","repository":{"id":45750179,"uuid":"169124414","full_name":"nibtehaz/MultiResUNet","owner":"nibtehaz","description":"MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation","archived":false,"fork":false,"pushed_at":"2022-10-24T15:32:06.000Z","size":450,"stargazers_count":370,"open_issues_count":3,"forks_count":83,"subscribers_count":11,"default_branch":"master","last_synced_at":"2023-10-25T18:34:53.694Z","etag":null,"topics":["medical-imaging","segmentation-models"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/nibtehaz.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":"2019-02-04T18:12:31.000Z","updated_at":"2023-10-23T09:21:26.000Z","dependencies_parsed_at":"2023-01-20T16:31:52.202Z","dependency_job_id":null,"html_url":"https://github.com/nibtehaz/MultiResUNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"purl":"pkg:github/nibtehaz/MultiResUNet","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nibtehaz%2FMultiResUNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nibtehaz%2FMultiResUNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nibtehaz%2FMultiResUNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nibtehaz%2FMultiResUNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nibtehaz","download_url":"https://codeload.github.com/nibtehaz/MultiResUNet/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nibtehaz%2FMultiResUNet/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29414342,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-13T06:24:03.484Z","status":"ssl_error","status_checked_at":"2026-02-13T06:23:12.830Z","response_time":78,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["medical-imaging","segmentation-models"],"created_at":"2026-02-02T16:00:36.768Z","updated_at":"2026-02-13T19:00:40.686Z","avatar_url":"https://github.com/nibtehaz.png","language":"Jupyter Notebook","funding_links":[],"categories":["📊 U-Net Variants"],"sub_categories":["📐 Multi-Scale Variants"],"readme":"# MultiResUNet \n#### Rethinking the U-Net architecture for multimodal biomedical image segmentation\n\nThis repository contains the original implementation of \"MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation\" in Keras (Tensorflow as backend).\n\n## Paper\n\nMultiResUNet has been published in Neural Networks\n\n\u003eIbtehaz, Nabil, and M. Sohel Rahman. \"MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation.\" Neural Networks 121 (2020): 74-87.\n\n\n* [Read the Paper](https://doi.org/10.1016/j.neunet.2019.08.025)\n* [View the Preprint](https://arxiv.org/abs/1902.04049)\n\n## Overview\n\nIn this project we take motivations from the phenomenal U-Net architecture for biomedical image segmentation and take an attempt to improve the already outstanding network.\n\n\u003cdiv style=\"text-align:center\"\u003e\n    \u003cimg src=\"imgs/unet.png\" width=\"70%\" /\u003e\n\u003c/div\u003e\n\n\nIn order to incorporate multiresolution analysis, taking inspiration from Inception family networks, we propose the following *MultiRes* block, and replace the pair of convolutional layer pairs in the original U-Net with it. This configuration basically is derived from factorizing 5x5 and 7x7 convolution operations to 3x3 ones, and reusing them to obtain results from 3x3, 5x5 and 7x7 convolution operations simultaneously. Moreover, a residual path is also added.\n\n\u003cdiv style=\"text-align:center\"\u003e\n    \u003cimg src=\"imgs/multires.png\" width=\"70%\" /\u003e\n\u003c/div\u003e\n\n\nConsequnetly, to elleviate the likely semantic distance between Encoder and Decoder networks, we introduce *Res* Paths. We include additional convolutions along the shortcut path, in proportionate to the expected gap between the two corresponding layers.\n\n\u003cdiv style=\"text-align:center\"\u003e\n    \u003cimg src=\"imgs/respath.png\" width=\"70%\" /\u003e\n\u003c/div\u003e\n\n\nTherefore, with the fusion of *MultiRes* blocks and *Res* paths, we obtain the proposed architecture ***MultiResUNet***.\n\n\u003cdiv style=\"text-align:center\"\u003e\n    \u003cimg src=\"imgs/multiresunet.png\" width=\"70%\" /\u003e\n\u003c/div\u003e\n\n\n## Codes\n\nThe model architecture codes can be found in\n\n### Tensorflow\n* [2D Model](https://github.com/nibtehaz/MultiResUNet/blob/master/tensorflow/MultiResUNet.py)\n\n* [3D Model](https://github.com/nibtehaz/MultiResUNet/blob/master/tensorflow/MultiResUNet3D.py)\n\n### Pytorch\n* [2D Model](https://github.com/nibtehaz/MultiResUNet/blob/master/pytorch/MultiResUNet.py)\n\n* [3D Model](https://github.com/nibtehaz/MultiResUNet/blob/master/pytorch/MultiResUNet3D.py)\n\n\n## Demo\n\nA demo can be found in [here](https://github.com/nibtehaz/MultiResUNet/blob/master/tensorflow/Demo.ipynb) (tensorflow)\n\n\n## License\n[![License](http://img.shields.io/:license-mit-blue.svg?style=flat-square)](http://badges.mit-license.org)\n\n[MIT license](https://github.com/nibtehaz/MultiResUNet/blob/master/LICENSE)\n\n\n## Citation Request\n\nIf you use ***MultiResUNet*** in your project, please cite the following paper\n\n```\n@article{ibtehaz2020multiresunet,\n  title={MultiResUNet: Rethinking the U-Net architecture for multimodal biomedical image segmentation},\n  author={Ibtehaz, Nabil and Rahman, M Sohel},\n  journal={Neural Networks},\n  volume={121},\n  pages={74--87},\n  year={2020},\n  publisher={Elsevier}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnibtehaz%2FMultiResUNet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fnibtehaz%2FMultiResUNet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fnibtehaz%2FMultiResUNet/lists"}