{"id":"https://openalex.org/W4416239686","doi":"https://doi.org/10.1109/tip.2025.3628469","title":"Local Alignment for Medical Vision-Language Pre-Training","display_name":"Local Alignment for Medical Vision-Language Pre-Training","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416239686","doi":"https://doi.org/10.1109/tip.2025.3628469","pmid":"https://pubmed.ncbi.nlm.nih.gov/41212704"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2025.3628469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3628469","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","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/A5100652907","display_name":"Huimin Yan","orcid":"https://orcid.org/0009-0000-8342-7605"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Yan","raw_affiliation_strings":["Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0009-0000-8342-7605","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018266083","display_name":"Xian Yang","orcid":"https://orcid.org/0000-0002-1496-8923"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xian Yang","raw_affiliation_strings":["Alliance Manchester Business School, The University of Manchester, Manchester, U.K"],"raw_orcid":"https://orcid.org/0000-0002-1496-8923","affiliations":[{"raw_affiliation_string":"Alliance Manchester Business School, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046818326","display_name":"Liang Bai","orcid":"https://orcid.org/0000-0002-0380-2995"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Bai","raw_affiliation_strings":["Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0002-0380-2995","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106626932","display_name":"Jiye Liang","orcid":"https://orcid.org/0000-0001-5887-9327"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiye Liang","raw_affiliation_strings":["Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China"],"raw_orcid":"https://orcid.org/0000-0001-5887-9327","affiliations":[{"raw_affiliation_string":"Institute of Intelligent Information Processing, Shanxi University, Taiyuan, China","institution_ids":["https://openalex.org/I181877577"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.452,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65965527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"34","issue":null,"first_page":"7321","last_page":"7334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7462000250816345,"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":0.7462000250816345,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.061900001019239426,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.0414000004529953,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.48510000109672546},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4453999996185303},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43959999084472656},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40130001306533813},{"id":"https://openalex.org/keywords/unified-medical-language-system","display_name":"Unified Medical Language System","score":0.39410001039505005},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.3880999982357025},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.3564000129699707},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.3481999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7202000021934509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6572999954223633},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43959999084472656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.421099990606308},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.39410001039505005},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.30709999799728394},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.26969999074935913},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25679999589920044},{"id":"https://openalex.org/C2779255053","wikidata":"https://www.wikidata.org/wiki/Q370424","display_name":"Local color","level":2,"score":0.2517000138759613}],"mesh":[{"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":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D007091","descriptor_name":"Image Processing, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/tip.2025.3628469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2025.3628469","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41212704","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41212704","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 image processing : a publication of the IEEE Signal Processing Society","raw_type":"Journal Article"},{"id":"pmh:oai:pure.atira.dk:publications/b01bc1a8-368b-4ce8-b80a-4e18b8769651","is_oa":false,"landing_page_url":"https://research.manchester.ac.uk/en/publications/b01bc1a8-368b-4ce8-b80a-4e18b8769651","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Yan, H, Yang, X, Bai, L & Liang, J 2025, 'Local Alignment for Medical Vision-Language Pre-Training', IEEE Transactions on Image Processing, vol. 34, pp. 7321-7334. https://doi.org/10.1109/TIP.2025.3628469","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1957301425","display_name":null,"funder_award_id":"202303021223004","funder_id":"https://openalex.org/F4320322666","funder_display_name":"Natural Science Foundation of Shanxi Province"},{"id":"https://openalex.org/G2176691914","display_name":null,"funder_award_id":"62432006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6929609165","display_name":null,"funder_award_id":"62276159","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322666","display_name":"Natural Science Foundation of Shanxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Establishing":[0],"local":[1,65,81,95,138],"semantic":[2,54,91,156],"correspondences":[3],"between":[4],"medical":[5,15,44,69,200],"images":[6,30],"and":[7,42,80,83,155,166,193],"their":[8],"corresponding":[9],"reports":[10,45,165],"is":[11,110,159],"crucial":[12],"for":[13,68],"effective":[14],"vision-language":[16,70,201],"pre-training.":[17,71,202],"However,":[18],"existing":[19,183],"methods":[20],"encounter":[21],"two":[22],"major":[23],"challenges:":[24],"(1)":[25],"lesion":[26,115,134],"regions":[27,116],"in":[28,199],"radiological":[29],"are":[31],"often":[32],"small,":[33],"blurry,":[34],"or":[35,49],"lack":[36],"clear":[37],"boundaries,":[38],"complicating":[39],"accurate":[40,173],"localization;":[41],"(2)":[43],"typically":[46],"contain":[47],"redundant":[48],"non-diagnostic":[50],"words,":[51],"hindering":[52],"precise":[53],"alignment.":[55,157],"To":[56,93],"overcome":[57],"these":[58],"issues,":[59],"we":[60,97,142],"propose":[61],"MedAligner,":[62],"a":[63,99,104,137,144],"specialized":[64],"alignment":[66],"network":[67],"MedAligner":[72,180],"employs":[73],"dual":[74],"encoders":[75],"to":[76,88,112],"extract":[77],"both":[78,151],"global":[79,85],"representations":[82],"uses":[84],"contrastive":[86,139],"learning":[87],"maintain":[89],"coarse":[90],"consistency.":[92],"enhance":[94],"alignment,":[96],"introduce":[98],"Word-Region":[100],"Alignment,":[101],"which":[102],"generates":[103],"learnable":[105],"word-pixel":[106,169],"similarity":[107],"matrix":[108],"that":[109,148,179],"sparsified":[111],"identify":[113],"salient":[114],"accurately.":[117],"Additionally,":[118],"our":[119],"Diagnostic":[120],"Term":[121],"Filtering":[122],"dynamically":[123],"samples":[124],"high-importance":[125],"diagnostic":[126,164],"terms":[127],"from":[128],"reports,":[129],"aligning":[130],"them":[131],"with":[132],"identified":[133],"areas":[135],"via":[136],"loss.":[140],"Importantly,":[141],"adopt":[143],"progressive":[145],"training":[146],"strategy":[147],"gradually":[149],"refines":[150],"the":[152],"input":[153],"text":[154],"This":[158],"achieved":[160],"by":[161],"reconstructing":[162],"concise":[163],"progressively":[167],"updating":[168],"similarity,":[170],"generating":[171],"increasingly":[172],"image-text":[174,191],"pairs.":[175],"Extensive":[176],"experiments":[177],"demonstrate":[178],"significantly":[181],"surpasses":[182],"approaches":[184],"on":[185],"tasks":[186],"such":[187],"as":[188],"phrase":[189],"grounding,":[190],"retrieval,":[192],"zero-shot":[194],"classification,":[195],"setting":[196],"new":[197],"benchmarks":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-11-10T00:00:00"}