{"id":"https://openalex.org/W7165931140","doi":"https://doi.org/10.48550/arxiv.2606.25255","title":"Cross-Modality Structural Guidance in 3D Latent Diffusion for Robust FLAIR Super-Resolution","display_name":"Cross-Modality Structural Guidance in 3D Latent Diffusion for Robust FLAIR Super-Resolution","publication_year":2026,"publication_date":"2026-06-24","ids":{"openalex":"https://openalex.org/W7165931140","doi":"https://doi.org/10.48550/arxiv.2606.25255"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.25255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.25255","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031490441","display_name":"Haoyu Lan","orcid":"https://orcid.org/0000-0002-4398-9053"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan, Haoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491863","display_name":"Jiazhen Zhang","orcid":"https://orcid.org/0000-0002-3078-1907"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiazhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138484020","display_name":"John Onofrey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Onofrey, John","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137285837","display_name":"Bino Varghese","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Varghese, Bino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089247690","display_name":"Nasim Sheikh\u2010Bahaei","orcid":"https://orcid.org/0000-0001-7029-7215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheikh-Bahaei, Nasim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014949118","display_name":"Arthur W. Toga","orcid":"https://orcid.org/0000-0001-7902-3755"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toga, Arthur W.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012771982","display_name":"Jeiran Choupan","orcid":"https://orcid.org/0000-0002-4760-7796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choupan, Jeiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.517300009727478,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11105","display_name":"Advanced Image Processing Techniques","score":0.517300009727478,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.19429999589920044,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.05649999901652336,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.7281000018119812},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.6139000058174133},{"id":"https://openalex.org/keywords/fluid-attenuated-inversion-recovery","display_name":"Fluid-attenuated inversion recovery","score":0.5781000256538391},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5630000233650208},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.4406999945640564},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4196999967098236},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.3303999900817871},{"id":"https://openalex.org/keywords/diffusion-mri","display_name":"Diffusion MRI","score":0.32749998569488525}],"concepts":[{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7281000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6563000082969666},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6139000058174133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5806999802589417},{"id":"https://openalex.org/C101070640","wikidata":"https://www.wikidata.org/wiki/Q3737215","display_name":"Fluid-attenuated inversion recovery","level":3,"score":0.5781000256538391},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5630000233650208},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.427700012922287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C149550507","wikidata":"https://www.wikidata.org/wiki/Q899360","display_name":"Diffusion MRI","level":3,"score":0.32749998569488525},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C58693492","wikidata":"https://www.wikidata.org/wiki/Q551875","display_name":"Neuroimaging","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27129998803138733},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C84787856","wikidata":"https://www.wikidata.org/wiki/Q3076659","display_name":"Tractography","level":4,"score":0.2531999945640564},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.25255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.25255","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25255","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.7223023772239685,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High-resolution":[0],"(HR)":[1],"MRI":[2],"acquisition":[3],"is":[4],"often":[5,33],"hampered":[6],"by":[7],"scan":[8],"time":[9],"constraints,":[10],"resulting":[11],"in":[12,72],"anisotropic":[13],"or":[14],"low-resolution":[15,97],"scans":[16,69],"(e.g.,":[17],"thick-slice":[18,67],"FLAIR)":[19],"that":[20,55],"limit":[21],"diagnostic":[22],"accuracy.":[23],"While":[24,188],"deep":[25],"learning-based":[26],"super-resolution":[27],"(SR)":[28],"methods":[29],"show":[30],"promise,":[31],"they":[32],"hallucinate":[34],"anatomical":[35,104],"details,":[36],"which":[37,83],"can":[38],"compromise":[39],"brain":[40],"structural":[41,59,81,85],"integrity.":[42],"To":[43],"mitigate":[44],"this":[45],"limitation,":[46],"we":[47,113],"introduce":[48],"MR-DiffuSR,":[49],"a":[50,115,123,138,199],"Multi-Resolution":[51],"Diffusion-based":[52],"Super-Resolution":[53],"framework":[54],"incorporates":[56],"HR":[57,90],"T1w":[58,91],"image":[60],"priors":[61],"to":[62,95,128,131,142],"guide":[63],"the":[64,73,89,96,120,149],"restoration":[65],"of":[66,125,164,167,171,202],"FLAIR":[68,98],"and":[70,92,156,169],"operates":[71],"3D":[74],"latent":[75,99],"space.":[76],"Our":[77],"architecture":[78],"introduces":[79],"cross-modality":[80],"swin-attention,":[82],"derives":[84],"attention":[86],"maps":[87],"from":[88,106],"applies":[93],"them":[94],"features.":[100],"This":[101],"design":[102],"disentangles":[103],"structure":[105],"modality-specific":[107],"contrast,":[108],"effectively":[109],"preventing":[110],"hallucinations.":[111],"Furthermore,":[112],"employ":[114],"mixed-scale":[116],"degradation":[117],"strategy,":[118],"training":[119],"model":[121,184],"on":[122,148],"continuum":[124],"downsampling":[126,175],"factors":[127],"ensure":[129],"robustness":[130],"varying":[132],"slice":[133,210],"thicknesses,":[134],"while":[135],"optimizing":[136],"with":[137],"DINOv3-based":[139],"perceptual":[140],"loss":[141],"preserve":[143],"high-frequency":[144],"semantic":[145],"details.":[146],"Evaluated":[147],"ADNI-4":[150],"dataset,":[151],"MR-DiffuSR":[152,197],"surpasses":[153],"both":[154],"CNN":[155],"2D":[157],"diffusion":[158],"approaches,":[159],"achieving":[160],"an":[161],"average":[162],"PSNR":[163],"32.46dB,":[165],"SSIM":[166],"0.97,":[168],"LPIPS":[170],"0.07":[172],"across":[173],"all":[174],"factors.":[176],"In":[177],"downstream":[178],"white":[179],"matter":[180],"hyperintensity":[181],"segmentation,":[182],"our":[183],"demonstrates":[185],"exceptional":[186],"robustness.":[187],"baseline":[189],"performance":[190],"collapses":[191],"at":[192,207],"10x":[193],"down-sampling":[194],"(Dice:":[195],"0.51),":[196],"maintains":[198],"Dice":[200],"score":[201],"0.63,":[203],"preserving":[204],"utility":[205],"even":[206],"7mm":[208],"equivalent":[209],"thickness.":[211]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-26T00:00:00"}