{"id":"https://openalex.org/W7135037486","doi":"https://doi.org/10.48550/arxiv.2603.10967","title":"Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI","display_name":"Med-DualLoRA: Local Adaptation of Foundation Models for 3D Cardiac MRI","publication_year":2026,"publication_date":"2026-03-11","ids":{"openalex":"https://openalex.org/W7135037486","doi":"https://doi.org/10.48550/arxiv.2603.10967"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.10967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10967","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.10967","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128833591","display_name":"Joan Perramon-Lluss\u00e0","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Perramon-Lluss\u00e0, Joan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025859249","display_name":"Amelia Jim\u00e9nez-S\u00e1nchez","orcid":"https://orcid.org/0000-0001-7870-0603"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jim\u00e9nez-S\u00e1nchez, Amelia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014439080","display_name":"Grzegorz Skorupko","orcid":"https://orcid.org/0000-0002-1059-6915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Skorupko, Grzegorz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120640119","display_name":"Fotis Avgoustidis","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avgoustidis, Fotis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068958617","display_name":"Carlos Mart\u00edn-Isla","orcid":"https://orcid.org/0000-0003-4270-4009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mart\u00edn-Isla, Carlos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078391768","display_name":"Karim Lekadir","orcid":"https://orcid.org/0000-0002-9456-1612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lekadir, Karim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006692999","display_name":"Polyxeni Gkontra","orcid":"https://orcid.org/0000-0001-8828-6143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gkontra, Polyxeni","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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.39329999685287476,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.39329999685287476,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T14510","display_name":"Medical Imaging and Analysis","score":0.14069999754428864,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.11659999936819077,"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/scalability","display_name":"Scalability","score":0.6089000105857849},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5236999988555908},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.5015000104904175},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4174000024795532},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.3569999933242798},{"id":"https://openalex.org/keywords/vendor","display_name":"Vendor","score":0.33399999141693115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080000042915344},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6089000105857849},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5236999988555908},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.42980000376701355},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C2777338717","wikidata":"https://www.wikidata.org/wiki/Q1762621","display_name":"Vendor","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3188999891281128},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C2987145844","wikidata":"https://www.wikidata.org/wiki/Q5038325","display_name":"Cardiac magnetic resonance","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.10967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10967","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.10967","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.10967","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Foundation":[0],"models":[1],"(FMs)":[2],"show":[3,144],"great":[4],"promise":[5],"for":[6,83,170,213],"robust":[7],"downstream":[8],"performance":[9,33,152,191],"across":[10,127],"medical":[11,218],"imaging":[12],"tasks":[13],"and":[14,34,66,88,102,111,125,142,175],"modalities,":[15],"including":[16],"cardiac":[17],"magnetic":[18],"resonance":[19],"(CMR),":[20],"following":[21],"task-specific":[22],"adaptation.":[23],"However,":[24],"adaptation":[25,216],"using":[26,173],"single-site":[27],"data":[28,43,65],"may":[29],"lead":[30],"to":[31,48,198],"suboptimal":[32],"increased":[35],"model":[36],"bias,":[37],"while":[38,137,153,203],"centralized":[39],"fine-tuning":[40,52,82,94],"on":[41,161],"clinical":[42,222],"is":[44,123],"often":[45],"infeasible":[46],"due":[47],"privacy":[49],"constraints.":[50,223],"Federated":[51],"offers":[53],"a":[54,91,162,183,210],"privacy-preserving":[55],"alternative;":[56],"yet":[57],"conventional":[58],"approaches":[59],"struggle":[60],"under":[61,220],"heterogeneous,":[62],"non-IID":[63],"multi-center":[64,163],"incur":[67],"substantial":[68],"communication":[69,140,205],"overhead":[70],"when":[71],"adapting":[72,146],"large":[73],"models.":[74],"In":[75],"this":[76],"work,":[77],"we":[78],"study":[79],"federated":[80,96,184,200,215],"FM":[81,168],"3D":[84,166],"CMR":[85,167],"disease":[86,171],"detection":[87,172],"propose":[89],"Med-DualLoRA,":[90],"client-aware":[92],"parameter-efficient":[93],"(PEFT)":[95],"framework":[97],"that":[98,145],"disentangles":[99],"globally":[100],"shared":[101,124],"local":[103,112,130,214],"low-rank":[104],"adaptations":[105],"(LoRA)":[106],"through":[107],"additive":[108],"decomposition.":[109],"Global":[110],"LoRA":[113],"modules":[114],"are":[115],"trained":[116],"locally,":[117],"but":[118],"only":[119,147],"the":[120],"global":[121],"component":[122],"aggregated":[126],"sites,":[128],"keeping":[129],"adapters":[131],"private.":[132],"This":[133],"design":[134],"improves":[135],"personalization":[136],"significantly":[138],"reducing":[139],"cost,":[141],"experiments":[143],"two":[148],"transformer":[149],"blocks":[150],"preserves":[151],"further":[154],"improving":[155],"efficiency.":[156,206],"We":[157],"evaluate":[158],"our":[159],"method":[160],"state-of-the-art":[164],"cine":[165],"fine-tuned":[169],"ACDC":[174],"combined":[176],"M\\&Ms":[177],"datasets,":[178],"treating":[179],"each":[180],"vendor":[181],"as":[182],"client.":[185],"Med-DualLoRA":[186],"achieves":[187],"statistically":[188],"significant":[189],"improved":[190],"(balanced":[192],"accuracy":[193],"0.768,":[194],"specificity":[195],"0.612)":[196],"compared":[197],"other":[199],"PEFT":[201],"baselines,":[202],"maintaining":[204],"Our":[207],"approach":[208],"provides":[209],"scalable":[211],"solution":[212],"of":[217],"FMs":[219],"realistic":[221]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-13T00:00:00"}