{"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/mri-reconstruction-via-cascaded-channel-wise","title":"MRI Reconstruction via Cascaded Channel-wise Attention Network","arxiv_id":"1810.08229","date":"2018-10-18","proceeding":null,"authors":["Qiaoying Huang","Dong Yang","Pengxiang Wu","Hui Qu","Jingru Yi","Dimitris Metaxas"],"abstract":"We consider an MRI reconstruction problem with input of k-space data at a\nvery low undersampled rate. This can practically benefit patient due to reduced\ntime of MRI scan, but it is also challenging since quality of reconstruction\nmay be compromised. Currently, deep learning based methods dominate MRI\nreconstruction over traditional approaches such as Compressed Sensing, but they\nrarely show satisfactory performance in the case of low undersampled k-space\ndata. One explanation is that these methods treat channel-wise features\nequally, which results in degraded representation ability of the neural\nnetwork. To solve this problem, we propose a new model called MRI Cascaded\nChannel-wise Attention Network (MICCAN), highlighted by three components: (i) a\nvariant of U-net with Channel-wise Attention (UCA) module, (ii) a long skip\nconnection and (iii) a combined loss. Our model is able to attend to salient\ninformation by filtering irrelevant features and also concentrate on\nhigh-frequency information by enforcing low-frequency information bypassed to\nthe final output. We conduct both quantitative evaluation and qualitative\nanalysis of our method on a cardiac dataset. The experiment shows that our\nmethod achieves very promising results in terms of three common metrics on the\nMRI reconstruction with low undersampled k-space data.","url_abs":"http://arxiv.org/abs/1810.08229v2","url_pdf":"http://arxiv.org/pdf/1810.08229v2.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":"mri-reconstruction-via-cascaded-channel-wise","repo_url":"https://github.com/charwing10/isbi2019miccan","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mri-reconstruction","task_name":"MRI Reconstruction"},{"task_slug":"compressed-sensing","task_name":"compressed sensing"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}