{"id":"https://openalex.org/W4412888170","doi":"https://doi.org/10.18653/v1/2025.findings-acl.843","title":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","display_name":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888170","doi":"https://doi.org/10.18653/v1/2025.findings-acl.843"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.843","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.843","pdf_url":"https://aclanthology.org/2025.findings-acl.843.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.843.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014579261","display_name":"Che Liu","orcid":"https://orcid.org/0000-0002-9917-8487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061473466","display_name":"Zhongwei Wan","orcid":"https://orcid.org/0000-0002-2790-0290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongwei Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045137258","display_name":"Haozhe Wang","orcid":"https://orcid.org/0000-0002-7621-772X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haozhe Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033092050","display_name":"Yinda Chen","orcid":"https://orcid.org/0000-0002-1990-4224"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinda Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089967045","display_name":"Talha Qaiser","orcid":"https://orcid.org/0000-0002-5014-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talha Qaiser","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035445528","display_name":"Jin Chen","orcid":"https://orcid.org/0000-0003-1810-3828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072956692","display_name":"Nikolay Burlutskiy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikolay Burlutskiy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047112337","display_name":"Fariba Yousefi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fariba Yousefi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085852399","display_name":"Rossella Arcucci","orcid":"https://orcid.org/0000-0002-9471-0585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rossella Arcucci","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1519,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78952864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16401","last_page":"16421"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.881600022315979,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.881600022315979,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8762000203132629,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7092595100402832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5381098389625549},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5017094612121582},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4026457667350769},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3357105851173401},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32203608751296997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7092595100402832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5381098389625549},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5017094612121582},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4026457667350769},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3357105851173401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32203608751296997},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.843","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.843","pdf_url":"https://aclanthology.org/2025.findings-acl.843.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.843","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.843","pdf_url":"https://aclanthology.org/2025.findings-acl.843.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888170.pdf","grobid_xml":"https://content.openalex.org/works/W4412888170.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"MedicalVision-Language":[0],"Pre-training":[1],"(MedVLP)":[2],"has":[3],"made":[4,44],"significant":[5],"progress":[6],"in":[7,30,35,127,163,169],"enabling":[8,93],"zero-shot":[9,131,164],"tasks":[10],"for":[11],"medical":[12,32],"image":[13],"understanding.However,":[14],"training":[15,101],"MedVLP":[16,57,112,148,177],"models":[17,42,69,113,149,185],"typically":[18],"requires":[19],"large-scale":[20,49],"datasets":[21],"with":[22],"paired,":[23],"high-quality":[24,90],"image-text":[25,51],"data,":[26],"which":[27,190],"are":[28],"scarce":[29],"the":[31,54,106],"domain.Recent":[33],"advancements":[34],"Large":[36],"Language":[37],"Models":[38],"(LLMs)":[39],"and":[40,75,81,100,138,172,197],"diffusion":[41],"have":[43],"it":[45],"possible":[46],"to":[47,70,86,142],"generate":[48],"synthetic":[50,61,72,91,117,137,152,181],"pairs.This":[52],"raises":[53],"question:":[55],"Can":[56],"succeed":[58],"using":[59,133],"purely":[60],"data?To":[62],"address":[63],"this,":[64],"we":[65],"use":[66],"off-the-shelf":[67],"generative":[68],"create":[71],"radiology":[73],"reports":[74],"paired":[76],"Chest":[77],"X-ray":[78],"(CXR)":[79],"images,":[80],"propose":[82],"an":[83],"automated":[84],"pipeline":[85],"build":[87],"a":[88,94,134,143],"diverse,":[89],"dataset,":[92],"rigorous":[95],"study":[96],"that":[97,111],"isolates":[98],"model":[99],"settings,":[102],"focusing":[103],"entirely":[104],"from":[105],"data":[107,118,124,140,155,162,182],"perspective.Our":[108],"results":[109],"show":[110],"trained":[114,121,150,159,178,186],"exclusively":[115],"on":[116,122,130,151,160,179,187],"outperform":[119,157,184],"those":[120,158],"real":[123,139,161,188],"by":[125,194],"3.8%":[126],"averaged":[128],"AUC":[129],"classification.Moreover,":[132],"combination":[135],"of":[136,146],"leads":[141],"further":[144],"improvement":[145],"9.07%.Additionally,":[147],"or":[153],"mixed":[154],"consistently":[156],"grounding,":[165],"as":[166,168],"well":[167],"fine-tuned":[170],"classification":[171],"segmentation":[173],"tasks.Our":[174],"analysis":[175],"suggests":[176],"well-designed":[180],"can":[183],"datasets,":[189],"may":[191],"be":[192,202],"limited":[193],"lowquality":[195],"samples":[196],"long-tailed":[198],"distributions.The":[199],"code":[200],"will":[201],"released":[203],"at":[204],"https://":[205],"github.com/cheliu-computation/MedSyn-RepLearn.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}