{"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/reducing-uncertainty-in-undersampled-mri","title":"Reducing Uncertainty in Undersampled MRI Reconstruction with Active Acquisition","arxiv_id":"1902.03051","date":"2019-02-08","proceeding":"CVPR 2019 6","authors":["Zizhao Zhang","Adriana Romero","Matthew J. Muckley","Pascal Vincent","Lin Yang","Michal Drozdzal"],"abstract":"The goal of MRI reconstruction is to restore a high fidelity image from\npartially observed measurements. This partial view naturally induces\nreconstruction uncertainty that can only be reduced by acquiring additional\nmeasurements. In this paper, we present a novel method for MRI reconstruction\nthat, at inference time, dynamically selects the measurements to take and\niteratively refines the prediction in order to best reduce the reconstruction\nerror and, thus, its uncertainty. We validate our method on a large scale knee\nMRI dataset, as well as on ImageNet. Results show that (1) our system\nsuccessfully outperforms active acquisition baselines; (2) our uncertainty\nestimates correlate with error maps; and (3) our ResNet-based architecture\nsurpasses standard pixel-to-pixel models in the task of MRI reconstruction. The\nproposed method not only shows high-quality reconstructions but also paves the\nroad towards more applicable solutions for accelerating MRI.","url_abs":"http://arxiv.org/abs/1902.03051v1","url_pdf":"http://arxiv.org/pdf/1902.03051v1.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":"reducing-uncertainty-in-undersampled-mri","repo_url":"https://github.com/ezerilli/fast_MRI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mri-reconstruction","task_name":"MRI Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.03051","atlas_url":"https://app.syntology.ai/?focus=1902.03051","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}