{"id":"https://openalex.org/W4406948859","doi":"https://doi.org/10.1109/tmi.2025.3534436","title":"Enhancing Medical Vision-Language Contrastive Learning via Inter-Matching Relation Modeling","display_name":"Enhancing Medical Vision-Language Contrastive Learning via Inter-Matching Relation Modeling","publication_year":2025,"publication_date":"2025-01-29","ids":{"openalex":"https://openalex.org/W4406948859","doi":"https://doi.org/10.1109/tmi.2025.3534436","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031323"},"language":"en","primary_location":{"id":"doi:10.1109/tmi.2025.3534436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2025.3534436","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Medical Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049073141","display_name":"Mingjian Li","orcid":"https://orcid.org/0009-0001-5591-5385"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingjian Li","raw_affiliation_strings":["Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0009-0001-5591-5385","affiliations":[{"raw_affiliation_string":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022712090","display_name":"Mingyuan Meng","orcid":"https://orcid.org/0000-0002-9562-1613"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mingyuan Meng","raw_affiliation_strings":["Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9562-1613","affiliations":[{"raw_affiliation_string":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082979981","display_name":"Michael Fulham","orcid":"https://orcid.org/0000-0003-0602-6319"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Michael Fulham","raw_affiliation_strings":["Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0602-6319","affiliations":[{"raw_affiliation_string":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068891693","display_name":"Dagan Feng","orcid":"https://orcid.org/0000-0002-3381-214X"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dagan Feng","raw_affiliation_strings":["Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3381-214X","affiliations":[{"raw_affiliation_string":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015039086","display_name":"Lei Bi","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lei Bi","raw_affiliation_strings":["Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9759-0200","affiliations":[{"raw_affiliation_string":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100614820","display_name":"Jinman Kim","orcid":"https://orcid.org/0000-0001-5960-1060"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jinman Kim","raw_affiliation_strings":["Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5960-1060","affiliations":[{"raw_affiliation_string":"Biomedical Data Analysis and Visualization Laboratory, School of Computer Science, The University of Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Biomedical data analysis and visualization lab, University of Sydney, NSW, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":2.6181,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8918095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"44","issue":"6","first_page":"2463","last_page":"2476"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.882099986076355,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.882099986076355,"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/T10028","display_name":"Topic Modeling","score":0.8478999733924866,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.777400016784668,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.7658034563064575},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6903880834579468},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6254171133041382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6160115599632263},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5027434825897217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4842357337474823},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.41459906101226807},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.118539959192276},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11071646213531494}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.7658034563064575},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6903880834579468},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6254171133041382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6160115599632263},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5027434825897217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4842357337474823},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.41459906101226807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.118539959192276},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11071646213531494},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007090","descriptor_name":"Image Interpretation, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tmi.2025.3534436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2025.3534436","pdf_url":null,"source":{"id":"https://openalex.org/S58069681","display_name":"IEEE Transactions on Medical Imaging","issn_l":"0278-0062","issn":["0278-0062","1558-254X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Medical Imaging","raw_type":"journal-article"},{"id":"pmid:40031323","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031323","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on medical imaging","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G3587879924","display_name":"A technology platform for multiple body site image-omics","funder_award_id":"DP200103748","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1905882502","https://openalex.org/W2194775991","https://openalex.org/W2611650229","https://openalex.org/W2776207810","https://openalex.org/W2914203365","https://openalex.org/W2963466845","https://openalex.org/W2995225687","https://openalex.org/W3034922525","https://openalex.org/W3035605030","https://openalex.org/W3118694826","https://openalex.org/W3170841864","https://openalex.org/W3173909648","https://openalex.org/W3201906559","https://openalex.org/W3209047863","https://openalex.org/W3213233983","https://openalex.org/W4212852978","https://openalex.org/W4288391456","https://openalex.org/W4291023040","https://openalex.org/W4295917908","https://openalex.org/W4295934705","https://openalex.org/W4296027312","https://openalex.org/W4312266387","https://openalex.org/W4312533035","https://openalex.org/W4362603432","https://openalex.org/W4365143687","https://openalex.org/W4367055910","https://openalex.org/W4384162023","https://openalex.org/W4384615843","https://openalex.org/W4385245566","https://openalex.org/W4385347692","https://openalex.org/W4385573131","https://openalex.org/W4387211247","https://openalex.org/W4388336515","https://openalex.org/W4390872339","https://openalex.org/W4390872699","https://openalex.org/W6745537798","https://openalex.org/W6755207826","https://openalex.org/W6761260114","https://openalex.org/W6774670964","https://openalex.org/W6784185929","https://openalex.org/W6798001135","https://openalex.org/W6803870738","https://openalex.org/W6846055702","https://openalex.org/W6849714168","https://openalex.org/W6853667637","https://openalex.org/W6859614911"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W2378782423","https://openalex.org/W2388988621","https://openalex.org/W2357797405","https://openalex.org/W2366623913","https://openalex.org/W2374905595","https://openalex.org/W2516693588","https://openalex.org/W2116112408"],"abstract_inverted_index":{"Medical":[0],"image":[1,26,51,164,225],"representations":[2,27,226],"can":[3,28,221],"be":[4,29],"learned":[5,25],"through":[6,21],"medical":[7,13,36,224],"vision-language":[8],"contrastive":[9,138],"learning":[10,139],"(mVLCL)":[11],"where":[12],"imaging":[14],"reports":[15],"are":[16,85],"used":[17],"as":[18,40,57],"weak":[19],"supervision":[20,162],"image-text":[22],"alignment.":[23],"These":[24,76,210],"transferred":[30],"to":[31,49,80,92,104,114,157],"and":[32,43,53,96,101,151,186,207],"benefit":[33],"various":[34],"downstream":[35,178],"vision":[37],"tasks":[38],"such":[39,106],"disease":[41,94],"classification":[42],"segmentation.":[44],"Recent":[45],"mVLCL":[46,126,200],"methods":[47,61,77,201],"attempt":[48],"align":[50],"sub-regions":[52],"the":[54,71,93,97,130,192,198,218],"report":[55,161],"keywords":[56],"local-matchings.":[58],"However,":[59],"these":[60],"aggregate":[62],"all":[63],"local-matchings":[64,83,89,109,134],"via":[65,135],"simple":[66],"pooling":[67],"operations":[68],"while":[69],"ignoring":[70],"inherent":[72],"relations":[73,132],"between":[74,82,133],"them.":[75],"therefore":[78],"fail":[79,103],"reason":[81],"that":[84,90,112,128,213],"semantically":[86],"related,":[87],"e.g.,":[88,118],"correspond":[91,113],"word":[95,99],"location":[98],"(semantic-relations),":[100],"also":[102],"differentiate":[105],"clinically":[107],"important":[108],"from":[110],"others":[111],"less":[115],"meaningful":[116],"words,":[117],"conjunction":[119],"words":[120],"(importance-relations).":[121],"Hence,":[122],"we":[123,144],"propose":[124],"a":[125,136,146],"method":[127,170],"models":[129],"inter-matching":[131,219],"relation-enhanced":[137],"framework":[140],"(RECLF).":[141],"In":[142],"RECLF,":[143,215],"introduce":[145],"semantic-relation":[147],"reasoning":[148,154],"module":[149,155],"(SRM)":[150],"an":[152],"importance-relation":[153],"(IRM)":[156],"enable":[158],"more":[159],"fine-grained":[160],"for":[163],"representation":[165],"learning.":[166],"We":[167],"evaluated":[168],"our":[169,195,214],"using":[171],"six":[172],"public":[173],"benchmark":[174],"datasets":[175],"on":[176],"four":[177],"tasks,":[179],"including":[180],"segmentation,":[181],"zero-shot":[182],"classification,":[183,185],"linear":[184],"cross-modal":[187,208],"retrieval.":[188],"Our":[189],"results":[190,211],"demonstrated":[191],"superiority":[193],"of":[194],"RECLF":[196],"over":[197],"state-of-the-art":[199],"with":[202,227],"consistent":[203],"improvements":[204],"across":[205],"single-modal":[206],"tasks.":[209],"suggest":[212],"by":[216],"modeling":[217],"relations,":[220],"learn":[222],"improved":[223],"better":[228],"generalization":[229],"capabilities.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-02T14:50:37.381335","created_date":"2025-01-30T00:00:00"}
