[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83066-en":3,"doc-seo-83066-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83066,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","PhyMRI-SR: Toward Physics-Aware MRI Image Super-Resolution","Magnetic resonance imaging (MRI) super-resolution improves diagnostic accessibility, yet existing methods assume a deterministic mapping from a fixed low-resolution input to a high-resolution target. This ignores MRI acquisition physics where spatial resolution and signal-to-noise ratio (SNR) are inherently coupled, so each low-resolution scan reflects multiple possible acquisition trade-offs. The approach reframes super-resolution as physics-aware reconstruction by selecting an optimal resolution–SNR configuration and dynamically producing high-quality MRI. It adapts 2D Gaussian Splatting with resolution-agnostic rendering and adds prior-aware representation, physics-constrained signal modeling, and meta-learning for scarce paired data, validated on dynamic-resolution datasets.","PhyMRI-SR: Toward Physics-Aware MRI Image  \nSuper-Resolution  \nLihua Wei, Huatong Gao, Jia Gong, Zhiyu Tan, Hao Li, Jun Liu, and Zhihua Ren  \narXiv :2607 .06238v 1 [ cs .CV] 7 Jul 2026  \nAbstract—Magnetic resonance imaging (MRI) super-resolution is vital for improving diagnostic accessibility, yet most methods treat it as a deterministic mapping from a fixed low-resolution input to a high-resolution target. This overlooks a key property of MRI acquisition physics: spatial resolution and signal-tonoise ratio (SNR) are inherently coupled, making any given low-resolution scan merely one of many possible realizationsunder varying acquisition trade-offs. We rethink MRI superresolution as a physics-aware reconstruction problem, in which the goal is to identify the optimal resolution–SNR configuration and then super-resolve it to obtain high-quality MRI results. A key implication of this formulation is that MRI resolution becomes dynamic rather than fixed. To handle such resolutionheterogeneous inputs, we adapt 2D Gaussian Splatting (2D GS) to MRI by formulating reconstruction as a coordinate-based, resolution-agnostic rendering problem. To futher enhance the fidelity of MRI results, we introduce three innovations: (1) a prior-aware Gaussian representation that combines an Anatomical Structure Prior for tissue-specific kernel initialization with an Imaging System Prior that captures hardware characteristics via a covariance dictionary; (2) a physics-constrained signal modeling scheme that predicts intrinsic tissue parameters (proton density ρ and effective relaxation rate R2) and synthesizes intensities through governing physical equations, ensuring biophysically plausible contrast; and (3) a meta-learning framework that alleviates paired-data scarcity by pretraining on simulated data and adapting to real-world conditions. Extensive experiments on dynamic-resolution datasets and normal benchmark demonstrate that our method achieves state-of-the-art performance, highlighting its strong potential for clinical deployment. Project Page: [https://bio-med-i2-lab.github.io/projects/PhyMRI-SR](https://bio-med-i2-lab.github.io/projects/PhyMRI-SR).  \nIndex Terms—Deep learning, ultra-low-field Magnetic Resonance Imaging, super-resolution, 2D Gaussian splatting  \nI. INTRODUCTION  \nMagnetic resonance imaging (MRI) is a cornerstone of modern medical diagnostics, providing non-invasive, highcontrast visualization of soft tissues essential for detecting  \nLihua Wei is with the School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China.  \nHuatong Gao is with the School of Biomedical Engineering, ShanghaiTech University, Shanghai 201210, China, and also with the Shanghai Academy of AI for Science, Shanghai, China.  \nJia Gong is with the Shanghai Academy of AI for Science, Shanghai, China.  \nZhiyu Tan and Hao Li are with the Shanghai Academy of AI for Science, Shanghai, China, and also with Fudan University, Shanghai, China.  \nJun Liu is with the School of Computing and Communications, Lancaster University, Lancaster, U.K.  \nZhihua Ren is with the School of Biomedical Engineering & State Key Laboratory of Advanced Medical Materials and Devices, ShanghaiTech University, Shanghai 201210, China, and also with the Shanghai Clinical Research and Trial Center, Shanghai 200231, China.  \nLihua Wei, Huatong Gao and Jia Gong contributed equally to this work. Corresponding authors: Jia Gong and Zhihua Ren (e-mail: [gongjia@sais.com.cn](gongjia@sais.com.cn); [renzhih@shanghaitech.edu.cn](renzhih@shanghaitech.edu.cn)).  \nFig. 1. Illustration of the trade-off between spatial resolution and signalto-noise ratio (SNR) under a simulated ultra-low MRI system (64 mT) . In the high-resolution but low-SNR setting, severe noise leads to fragmented and discontinuous anatomical structures, as highlighted in the yellow boxes. The balanced regime produces more coherent and structurally consistent reconstructions, closely matching the HR reference. In the ","cbCaidjGNjNAeK5q","https://ap.wps.com/l/cbCaidjGNjNAeK5q","pdf",7802197,3,1,21,"English","en",105,"# Introduction\n## Physics-Aware Formulation\n## Prior and Signal Modeling\n## Meta-Learning and Adaptation","[{\"question\":\"Why do conventional MRI super-resolution methods fall short?\",\"answer\":\"They treat super-resolution as a deterministic low-resolution-to-fixed high-resolution mapping. This overlooks that MRI spatial resolution and SNR are coupled by acquisition physics.\"},{\"question\":\"How does the proposed method change the super-resolution objective?\",\"answer\":\"It formulates super-resolution as physics-aware reconstruction: identify an optimal resolution–SNR configuration, then super-resolve it to obtain high-quality MRI results.\"},{\"question\":\"What innovations improve reconstruction fidelity and practicality?\",\"answer\":\"It introduces (1) a prior-aware Gaussian representation, (2) physics-constrained signal modeling that predicts intrinsic tissue parameters and synthesizes intensities, and (3) a meta-learning framework to reduce paired-data scarcity via simulation pretraining and real-world adaptation.\"}]",1784184983,53,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"phymri-sr-toward-physics-aware-mri-image-super-resolution","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":20},"https://docshare.wps.com/document/research-report/",{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/phymri-sr-toward-physics-aware-mri-image-super-resolution/83066/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-21","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do conventional MRI super-resolution methods fall short?","Question",{"text":75,"@type":76},"They treat super-resolution as a deterministic low-resolution-to-fixed high-resolution mapping. This overlooks that MRI spatial resolution and SNR are coupled by acquisition physics.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method change the super-resolution objective?",{"text":80,"@type":76},"It formulates super-resolution as physics-aware reconstruction: identify an optimal resolution–SNR configuration, then super-resolve it to obtain high-quality MRI results.",{"name":82,"@type":73,"acceptedAnswer":83},"What innovations improve reconstruction fidelity and practicality?",{"text":84,"@type":76},"It introduces (1) a prior-aware Gaussian representation, (2) physics-constrained signal modeling that predicts intrinsic tissue parameters and synthesizes intensities, and (3) a meta-learning framework to reduce paired-data scarcity via simulation pretraining and real-world adaptation.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]