{"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/cycle-consistent-adversarial-denoising","title":"Cycle Consistent Adversarial Denoising Network for Multiphase Coronary CT Angiography","arxiv_id":"1806.09748","date":"2018-06-26","proceeding":null,"authors":["Eunhee Kang","Hyun Jung Koo","Dong Hyun Yang","Joon Bum Seo","Jong Chul Ye"],"abstract":"In coronary CT angiography, a series of CT images are taken at different\nlevels of radiation dose during the examination. Although this reduces the\ntotal radiation dose, the image quality during the low-dose phases is\nsignificantly degraded. To address this problem, here we propose a novel\nsemi-supervised learning technique that can remove the noises of the CT images\nobtained in the low-dose phases by learning from the CT images in the routine\ndose phases. Although a supervised learning approach is not possible due to the\ndifferences in the underlying heart structure in two phases, the images in the\ntwo phases are closely related so that we propose a cycle-consistent\nadversarial denoising network to learn the non-degenerate mapping between the\nlow and high dose cardiac phases. Experimental results showed that the proposed\nmethod effectively reduces the noise in the low-dose CT image while the\npreserving detailed texture and edge information. Moreover, thanks to the\ncyclic consistency and identity loss, the proposed network does not create any\nartificial features that are not present in the input images. Visual grading\nand quality evaluation also confirm that the proposed method provides\nsignificant improvement in diagnostic quality.","url_abs":"http://arxiv.org/abs/1806.09748v3","url_pdf":"http://arxiv.org/pdf/1806.09748v3.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":"cycle-consistent-adversarial-denoising","repo_url":"https://github.com/hyeongyuy/CT-CYCLE_IDNETITY_GAN_tensorflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"diagnostic","task_name":"Diagnostic"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}