[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83263-en":3,"doc-seo-83263-105":29,"detail-sidebar-cat-0-en-105":82},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},83263,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","AA-ViT: Anatomically Aware Vision Transformer for Contrast-Enhanced Brain MRI Synthesis","Accurate tumour localization and diagnosis in brain cancer require contrast enhanced MRI, yet chemical contrast agents are often infeasible due to safety constraints and limitations such as renal impairment risk. Standard MRI may lack sufficient contrast and show artifacts, motivating non-invasive CEMRI synthesis. The proposed AA-ViT uses pre-contrast modalities (T1, T2, FLAIR) with structural and frequency guidance to better preserve anatomical boundaries and tumour fine structures. Experiments on BraTS 2021 report improved PSNR and SSIM, with preliminary clinical validation from expert reviewers.","arXiv :2607 .07553v 1 [ cs .CV] 8 Jul 2026  \nAA-ViT: Anatomically Aware Vision Transformer with Structural and Frequency Guidance for Contrast Enhanced Brain MRI Synthesis  \nTalha Meraj 1 ,2 ,3 ,8 , Tom Flannery4 , Charlie Cummins5 , Matt Townend6 , Thomas C Booth5 ,6 , Peter Crossley4 , Michael McCann3 ,7 , Ian Overton8 , and  \nSaritha Unnikrishnan 1 ,2 ,3 ,∗  \n1 Department of Computing and Electronic Engineering, Atlantic Technological University, Sligo, Ireland  \n2 Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Faculty of Engineering and Design, Atlantic Technological University,  \nSligo, Ireland  \n3 JANUS Research Centre, Atlantic Technological University, Letterkenny, Ireland  \n4 Department of Neurosurgery, Belfast Health and Social Care Trust, Belfast, BT12 6BA, UK  \n5 Department of Neuroradiology, Ruskin Wing, King’s College Hospital NHS  \nFoundation Trust, London, SE5 9RS, UK  \n6 School of Biomedical Engineering & Imaging Sciences, King’s College London, UK  \n7 Department of Computing, Atlantic Technological University, Letterkenny, Ireland  \n8 Johnston Cancer Research Centre, Queen’s University Belfast, Belfast, BT9 7AE,  \nUK  \nAbstract. Accurate tumour localization and diagnosis is a critical component of clinical care for brain cancers. Magnetic Resonance Imaging (MRI) is the most commonly used imaging modality due to its superior soft-tissue contrast. However, standard MRI often exhibits limited contrast and imaging artifacts, which necessitates the use of contrast agents to enhance lesion visibility. The administration of chemical contrast agents is not always feasible and may be contraindicated in patients with renal impairment or other health conditions. As a result, developing accurate and non-invasive contrast enhanced MRI (CEMRI) synthesis methods has clinical importance. In recent years, numerous approaches for CEMRI synthesis have been proposed, predominantly relying on generative artificial intelligence models. While these methods demonstrate promising performance, their dependence on implicit feature learning often limits their ability to preserve anatomical boundaries and tumour-specific fine structures. To address these challenges, we propose an anatomically aware frequency-and-structure-guided vision transformer (AA-ViT), for CEMRI synthesis using pre-contrast MRI modalities (T1, T2, and FLAIR) . Experiments on the BraTS 2021 dataset demonstrate that the proposed method preserves anatomical and lesion boundaries, achieving higher PSNR and SSIM than state-of-the-art approaches. Clinical evaluation by three neuroradiologists and a neurosurgeon on 19 randomly selected cases across diverse gliomas yielded a meanscore of 3.94/5, providing preliminary clinical validation rarely seen in  \n2 T. Meraj et al.  \nprior studies. Synthetic post-contrast scans from our model could lower scanning costs, shorten imaging time, and avoid the potential risks of using gadolinium-based contrast agents.  \nKeywords: Brain Cancer · Synthesized MRI · Vision Transformer  \n1 Introduction  \nContrast enhanced magnetic resonance images (CEMRI) are indispensable for brain tumour evaluation and treatment planning [6, 14] . It provides high-resolution information on tumour boundaries and differentiation between active and necrotic regions [3, 15] . Gadolinium-based contrast agents (GBCAs) are used in CEMRI which poses safety concerns such as potential deposition in the brain [7], allergic reactions and nephrogenic system fibrosis [17], in addition to increasing scan time and cost [13] . The European Medicines Agency restricts the use of GBCAs while permitting continued use of safer macrocyclic agents [9] . Given this, eliminating contrast agents while preserving diagnostically relevant image contrast is highly desirable [13] . To reduce the usage of GBCAs in brain cancer treatment, recent research has focused on synthesizing CEMRIs from non-contrast MR images (T1, T2-weighted, and FLAIR scans) using ","cbCainHHIpwTw8wZ","https://ap.wps.com/l/cbCainHHIpwTw8wZ","pdf",6841753,1,11,"English","en",105,"# Introduction\n## Motivation and clinical importance\n## Prior methods for CEMRI synthesis\n## Proposed AA-ViT approach\n## Experimental and clinical evaluation (as described in abstract)","[{\"question\":\"How does AA-ViT address the limitations of earlier generative approaches?\",\"answer\":\"Earlier implicit feature learning can fail to preserve anatomical boundaries and tumour-specific fine structures. AA-ViT introduces anatomically aware structural and frequency guidance to better constrain edges and structures in the generated scans.\"}]",1784186370,28,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":77,"head_meta":79,"extra_data":81,"updated_unix":27},"aa-vit-anatomically-aware-vision-transformer-for-contrast-enhanced-brain-mri-synthesis","",{"@graph":35,"@context":76},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/aa-vit-anatomically-aware-vision-transformer-for-contrast-enhanced-brain-mri-synthesis/83263/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70],{"name":71,"@type":72,"acceptedAnswer":73},"How does AA-ViT address the limitations of earlier generative approaches?","Question",{"text":74,"@type":75},"Earlier implicit feature learning can fail to preserve anatomical boundaries and tumour-specific fine structures. AA-ViT introduces anatomically aware structural and frequency guidance to better constrain edges and structures in the generated scans.","Answer","https://schema.org",{"og:url":51,"og:type":78,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":80,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":83},[84,88,92,96,101,106,111,114,119,122,126],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":45,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":45,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":45,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general"]