{"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/medsrgan-medical-images-super-resolution","title":"MedSRGAN: medical images super-resolution using generative adversarial networks","arxiv_id":null,"date":"2020-05-13","proceeding":"Springer 2020 5","authors":["Yuchong Gu","Zitao Zen","Haibin Chen","Jun Wei","Yaqin Zhang","Binghui Chen","Yingqin Li","Yujuan Qin","Qing Xie","Zhuoren Jiang","Yao Lu"],"abstract":"Super-resolution (SR) in medical imaging is an emerging application in medical\r\nimaging due to the needs of high quality images acquired with limited radiation\r\ndose, such as low dose Computer Tomography (CT), low field magnetic resonance\r\nimaging (MRI). However, because of its complexity and higher visual requirements\r\nof medical images, SR is still a challenging task in medical imaging. In this study,\r\nwe developed a deep learning based method called Medical Images SR using\r\nGenerative Adversarial Networks (MedSRGAN) for SR in medical imaging. A\r\nnovel convolutional neural network, Residual Whole Map Attention Network\r\n(RWMAN) was developed as the generator network for our MedSRGAN in\r\nextracting the useful information through different channels, as well as paying\r\nmore attention on meaningful regions. In addition, a weighted sum of content loss,\r\nadversarial loss, and adversarial feature loss were fused to form a multi-task loss\r\nfunction during the MedSRGAN training. 242 thoracic CT scans and 110 brain\r\nMRI scans were collected for training and evaluation of MedSRGAN. The results\r\nshowed that MedSRGAN not only preserves more texture details but also generates\r\nmore realistic patterns on reconstructed SR images. A mean opinion score (MOS)\r\ntest on CT slices scored by five experienced radiologists demonstrates the efficiency of our methods.","url_abs":"https://link.springer.com/article/10.1007%2Fs11042-020-08980-w","url_pdf":"https://link.springer.com/article/10.1007%2Fs11042-020-08980-w","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":"medsrgan-medical-images-super-resolution","repo_url":"https://github.com/04RR/MedSRGAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"super-resolution","task_name":"Super-Resolution"}],"methods":[],"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}