{"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/aespa-attention-guided-self-supervised","title":"AeSPa : Attention-guided Self-supervised Parallel Imaging for MRI Reconstruction","arxiv_id":null,"date":"2025-01-01","proceeding":"CVPR 2025 1","authors":["Jinho Joo","Hyeseong Kim","Hyeyeon Won","Deukhee Lee","Taejoon Eo","Dosik Hwang"],"abstract":"    This study introduces a novel zero-shot scan-specific self-supervised reconstruction method for magnetic resonance imaging (MRI) to reduce scan times. Conventional supervised reconstruction methods require large amounts of fully-sampled reference data, which is often impractical to obtain and can lead to artifacts by overly emphasizing learned patterns. Existing zero-shot scan-specific methods have attempted to overcome this data dependency but show limited performance due to insufficient utilization of k-space information and constraints derived from MRI forward model. To address these limitations, we introduce a framework utilizing all acquired k-space measurements for both network inputs and training targets. While this framework suffers from training instability, we resolve these challenges through three key components: an Attention-guided K-space Selective Mechanism (AKSM) that provides indirect constraints for non-sampled k-space points, Iteration-wise K-space Masking (IKM) that enhances training stability, and a robust sensitivity map estimation model utilizing cross-channel constraint that performs effectively even at high reduction factors. Experimental results on the FastMRI knee and brain datasets with reduction factors of 4 and 8 demonstrate that the proposed method achieves superior reconstruction quality and faster convergence compared to existing zero-shot scan-specific methods, making it suitable for practical clinical applications. The implementation of our proposed method is publicly available at https://github.com/joojinho97/AeSPa.git.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2025/html/Joo_AeSPa__Attention-guided_Self-supervised_Parallel_Imaging_for_MRI_Reconstruction_CVPR_2025_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2025/papers/Joo_AeSPa__Attention-guided_Self-supervised_Parallel_Imaging_for_MRI_Reconstruction_CVPR_2025_paper.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":"aespa-attention-guided-self-supervised","repo_url":"https://github.com/joojinho97/aespa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mri-reconstruction","task_name":"MRI Reconstruction"}],"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}