{"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/coupled-dictionary-learning-for-multi","title":"Coupled Dictionary Learning for Multi-contrast MRI Reconstruction","arxiv_id":"1806.09930","date":"2018-06-26","proceeding":null,"authors":["Pingfan Song","Lior Weizman","Joao F. C. Mota","Yonina C. Eldar","Miguel R. D. Rodrigues"],"abstract":"Medical imaging tasks often involve multiple contrasts, such as T1- and\nT2-weighted magnetic resonance imaging (MRI) data. These contrasts capture\ninformation associated with the same underlying anatomy and thus exhibit\nsimilarities. In this paper, we propose a Coupled Dictionary Learning based\nmulti-contrast MRI reconstruction (CDLMRI) approach to leverage an available\nguidance contrast to restore the target contrast. Our approach consists of\nthree stages: coupled dictionary learning, coupled sparse denoising, and\n$k$-space consistency enforcing. The first stage learns a group of dictionaries\nthat capture correlations among multiple contrasts. By capitalizing on the\nlearned adaptive dictionaries, the second stage performs joint sparse coding to\ndenoise the corrupted target image with the aid of a guidance contrast. The\nthird stage enforces consistency between the denoised image and the\nmeasurements in the $k$-space domain. Numerical experiments on the\nretrospective under-sampling of clinical MR images demonstrate that\nincorporating additional guidance contrast via our design improves MRI\nreconstruction, compared to state-of-the-art approaches.","url_abs":"http://arxiv.org/abs/1806.09930v1","url_pdf":"http://arxiv.org/pdf/1806.09930v1.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":"coupled-dictionary-learning-for-multi","repo_url":"https://github.com/P-Song/CDLMRI","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"anatomy","task_name":"Anatomy"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"dictionary-learning","task_name":"Dictionary Learning"},{"task_slug":"mri-reconstruction","task_name":"MRI Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.09930","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}