{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/denoising-of-3d-magnetic-resonance-images","title":"Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network","arxiv_id":"1712.08726","date":"2017-12-23","proceeding":null,"authors":["Dongsheng Jiang","Weiqiang Dou","Luc Vosters","Xiayu Xu","Yue Sun","Tao Tan"],"abstract":"The denoising of magnetic resonance (MR) images is a task of great importance\nfor improving the acquired image quality. Many methods have been proposed in\nthe literature to retrieve noise free images with good performances. Howerever,\nthe state-of-the-art denoising methods, all needs a time-consuming optimization\nprocesses and their performance strongly depend on the estimated noise level\nparameter. Within this manuscript we propose the idea of denoising MRI Rician\nnoise using a convolutional neural network. The advantage of the proposed\nmethodology is that the learning based model can be directly used in the\ndenosing process without optimization and even without the noise level\nparameter. Specifically, a ten convolutional layers neural network combined\nwith residual learning and multi-channel strategy was proposed. Two training\nways: training on a specific noise level and training on a general level were\nconducted to demonstrate the capability of our methods. Experimental results\nover synthetic and real 3D MR data demonstrate our proposed network can achieve\nsuperior performance compared with other methods in term of both of the peak\nsignal to noise ratio and the global of structure similarity index. Without\nnoise level parameter, our general noise-applicable model is also better than\nthe other compared methods in two datasets. Furthermore, our training model\nshows good general applicability.","url_abs":"http://arxiv.org/abs/1712.08726v2","url_pdf":"http://arxiv.org/pdf/1712.08726v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"denoising-of-3d-magnetic-resonance-images","repo_url":"https://github.com/Dongshengjiang/Denoising-of-3D-magnetic-resonance-images-with-multi-channel-residual-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1712.08726","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}