{"id":"https://openalex.org/W3164654615","doi":"https://doi.org/10.1109/jbhi.2022.3207502","title":"Multi-Modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","display_name":"Multi-Modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","publication_year":2022,"publication_date":"2022-09-19","ids":{"openalex":"https://openalex.org/W3164654615","doi":"https://doi.org/10.1109/jbhi.2022.3207502","mag":"3164654615","pmid":"https://pubmed.ncbi.nlm.nih.gov/36121943"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2022.3207502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2022.3207502","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"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 Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.11333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031793369","display_name":"Jong Hak Moon","orcid":"https://orcid.org/0000-0002-6708-3918"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jong Hak Moon","raw_affiliation_strings":["Graduate School of AI, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024130663","display_name":"Hyungyung Lee","orcid":"https://orcid.org/0000-0003-4583-4271"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyungyung Lee","raw_affiliation_strings":["Graduate School of AI, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012141622","display_name":"Woncheol Shin","orcid":"https://orcid.org/0000-0002-2390-3638"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Woncheol Shin","raw_affiliation_strings":["Graduate School of AI, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012996842","display_name":"Young\u2010Hak Kim","orcid":"https://orcid.org/0000-0002-3610-486X"},"institutions":[{"id":"https://openalex.org/I116631150","display_name":"Ulsan College","ror":"https://ror.org/02tec3785","country_code":"KR","type":"education","lineage":["https://openalex.org/I116631150"]},{"id":"https://openalex.org/I2801680663","display_name":"Asan Medical Center","ror":"https://ror.org/03s5q0090","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I2801680663","https://openalex.org/I4210167194"]},{"id":"https://openalex.org/I40542001","display_name":"University of Ulsan","ror":"https://ror.org/02c2f8975","country_code":"KR","type":"education","lineage":["https://openalex.org/I40542001"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Hak Kim","raw_affiliation_strings":["Department of Cardiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Cardiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea","institution_ids":["https://openalex.org/I40542001","https://openalex.org/I2801680663","https://openalex.org/I116631150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034622258","display_name":"Edward Choi","orcid":"https://orcid.org/0000-0002-5958-3509"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Edward Choi","raw_affiliation_strings":["Graduate School of AI, KAIST, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of AI, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031793369"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":18.7937,"has_fulltext":false,"cited_by_count":197,"citation_normalized_percentile":{"value":0.99669207,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"26","issue":"12","first_page":"6070","last_page":"6080"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9945999979972839,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9922000169754028,"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":0.8506320118904114},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6256773471832275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6175954937934875},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5609036087989807},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5122110247612},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5050600171089172},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.448399156332016},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.43618646264076233},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4292464256286621},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.42460885643959045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4072737991809845},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3544313311576843},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.28682467341423035}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8506320118904114},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6256773471832275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6175954937934875},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5609036087989807},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5122110247612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5050600171089172},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.448399156332016},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.43618646264076233},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4292464256286621},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.42460885643959045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4072737991809845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3544313311576843},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28682467341423035},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"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":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1109/jbhi.2022.3207502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2022.3207502","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"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 Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:36121943","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36121943","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 journal of biomedical and health informatics","raw_type":null},{"id":"pmh:oai:arXiv.org:2105.11333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.11333","pdf_url":"https://arxiv.org/pdf/2105.11333","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.11333","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.11333","pdf_url":"https://arxiv.org/pdf/2105.11333","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G8157424046","display_name":null,"funder_award_id":"NRF-2020H1D3A2A03100945","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G820894990","display_name":null,"funder_award_id":"IO201211-08109-01","funder_id":"https://openalex.org/F4320332195","funder_display_name":"Samsung"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1422227952","https://openalex.org/W1514535095","https://openalex.org/W1933349210","https://openalex.org/W1995972830","https://openalex.org/W2064305374","https://openalex.org/W2108017642","https://openalex.org/W2137961864","https://openalex.org/W2152772232","https://openalex.org/W2194775991","https://openalex.org/W2525778437","https://openalex.org/W2592929672","https://openalex.org/W2611650229","https://openalex.org/W2745461083","https://openalex.org/W2896457183","https://openalex.org/W2901770990","https://openalex.org/W2911489562","https://openalex.org/W2925863688","https://openalex.org/W2929309437","https://openalex.org/W2947706148","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963446712","https://openalex.org/W2963466845","https://openalex.org/W2963967185","https://openalex.org/W2964121744","https://openalex.org/W2964317695","https://openalex.org/W2966715458","https://openalex.org/W2968124245","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W2970608575","https://openalex.org/W2970854840","https://openalex.org/W2975357369","https://openalex.org/W2975501350","https://openalex.org/W2979525559","https://openalex.org/W2981521947","https://openalex.org/W2981851019","https://openalex.org/W2995225687","https://openalex.org/W2997591391","https://openalex.org/W2998356391","https://openalex.org/W3001555892","https://openalex.org/W3014611590","https://openalex.org/W3041987782","https://openalex.org/W3086789505","https://openalex.org/W3089089004","https://openalex.org/W3100221118","https://openalex.org/W3101156210","https://openalex.org/W3103694015","https://openalex.org/W3110570034","https://openalex.org/W3128510757","https://openalex.org/W3173460036","https://openalex.org/W3201264086","https://openalex.org/W3209274285","https://openalex.org/W4385245566","https://openalex.org/W6727690538","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6757168802","https://openalex.org/W6760721734","https://openalex.org/W6761260114","https://openalex.org/W6763301180","https://openalex.org/W6766904570","https://openalex.org/W6767853649","https://openalex.org/W6769248286","https://openalex.org/W6773248631","https://openalex.org/W6775188310","https://openalex.org/W6780746354"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"Recently":[0],"a":[1,35,64,69],"number":[2],"of":[3,38,129],"studies":[4],"demonstrated":[5],"impressive":[6],"performance":[7,78,128],"on":[8,108],"diverse":[9],"vision-language":[10,81,94],"multi-modal":[11,27,39,71],"tasks":[12,42,83,111],"such":[13],"as":[14],"image":[15],"captioning":[16],"and":[17,51,93,102,119],"visual":[18,90],"question":[19,91],"answering":[20],"by":[21],"extending":[22],"the":[23,44,52,105,124],"BERT":[24],"architecture":[25,66],"with":[26,68,112],"pre-training":[28],"objectives.":[29],"In":[30],"this":[31],"work":[32],"we":[33,121],"explore":[34],"broad":[36],"set":[37],"representation":[40],"learning":[41],"in":[43],"medical":[45,86,89],"domain,":[46],"specifically":[47],"using":[48],"radiology":[49],"images":[50],"unstructured":[53],"report.":[54],"We":[55],"propose":[56],"Medical":[57],"Vision":[58],"Language":[59],"Learner":[60],"(MedViLL),":[61],"which":[62],"adopts":[63],"BERT-based":[65],"combined":[67],"novel":[70],"attention":[72],"masking":[73],"scheme":[74],"to":[75],"maximize":[76],"generalization":[77],"for":[79],"both":[80],"understanding":[82],"(diagnosis":[84],"classification,":[85],"image-report":[87,115],"retrieval,":[88],"answering)":[92],"generation":[95],"task":[96,127],"(radiology":[97],"report":[98],"generation).":[99],"By":[100],"statistically":[101],"rigorously":[103],"evaluating":[104],"proposed":[106],"model":[107],"four":[109],"downstream":[110,126],"three":[113],"radiographic":[114],"datasets":[116],"(MIMIC-CXR,":[117],"Open-I,":[118],"VQA-RAD),":[120],"empirically":[122],"demonstrate":[123],"superior":[125],"MedViLL":[130],"against":[131],"various":[132],"baselines,":[133],"including":[134],"task-specific":[135],"architectures.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":83},{"year":2024,"cited_by_count":56},{"year":2023,"cited_by_count":39},{"year":2022,"cited_by_count":6}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}