{"id":"https://openalex.org/W4404509535","doi":"https://doi.org/10.3389/frai.2024.1430984","title":"Vision-language models for medical report generation and visual question answering: a review","display_name":"Vision-language models for medical report generation and visual question answering: a review","publication_year":2024,"publication_date":"2024-11-19","ids":{"openalex":"https://openalex.org/W4404509535","doi":"https://doi.org/10.3389/frai.2024.1430984","pmid":"https://pubmed.ncbi.nlm.nih.gov/39628839"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2024.1430984","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1430984","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1430984/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1430984/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082579603","display_name":"Iryna Hartsock","orcid":"https://orcid.org/0000-0001-9896-872X"},"institutions":[{"id":"https://openalex.org/I3019308854","display_name":"Moffitt Cancer Center","ror":"https://ror.org/01xf75524","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I3019308854"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Iryna Hartsock","raw_affiliation_strings":["Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States","institution_ids":["https://openalex.org/I3019308854"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045996251","display_name":"Ghulam Rasool","orcid":"https://orcid.org/0000-0001-8551-0090"},"institutions":[{"id":"https://openalex.org/I3019308854","display_name":"Moffitt Cancer Center","ror":"https://ror.org/01xf75524","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I3019308854"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ghulam Rasool","raw_affiliation_strings":["Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL, United States","institution_ids":["https://openalex.org/I3019308854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082579603"],"corresponding_institution_ids":["https://openalex.org/I3019308854"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":35.5301,"has_fulltext":true,"cited_by_count":161,"citation_normalized_percentile":{"value":0.99889153,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":null,"first_page":"1430984","last_page":"1430984"},"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":0.9980999827384949,"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":0.9962999820709229,"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":0.7335707545280457},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.547347366809845},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5056636333465576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45869535207748413},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42004379630088806},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3265201151371002},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32600337266921997},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10966011881828308}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335707545280457},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.547347366809845},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5056636333465576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45869535207748413},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42004379630088806},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3265201151371002},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32600337266921997},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10966011881828308}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2024.1430984","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1430984","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1430984/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:39628839","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39628839","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":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11611889","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11611889","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11611889/pdf/frai-07-1430984.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Artif Intell","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:ab60768cda6049ffaa1d0f8efe9456c5","is_oa":true,"landing_page_url":"https://doaj.org/article/ab60768cda6049ffaa1d0f8efe9456c5","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Artificial Intelligence, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frai.2024.1430984","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2024.1430984","pdf_url":"https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2024.1430984/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3026169261","display_name":null,"funder_award_id":"1903466","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4893101906","display_name":null,"funder_award_id":"2234468","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6162870944","display_name":null,"funder_award_id":"2234836","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404509535.pdf"},"referenced_works_count":220,"referenced_works":["https://openalex.org/W1614298861","https://openalex.org/W1994616650","https://openalex.org/W2064675550","https://openalex.org/W2108598243","https://openalex.org/W2123301721","https://openalex.org/W2152772232","https://openalex.org/W2157331557","https://openalex.org/W2169818249","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2270070752","https://openalex.org/W2493916176","https://openalex.org/W2525778437","https://openalex.org/W2549139847","https://openalex.org/W2558592895","https://openalex.org/W2803259101","https://openalex.org/W2809254203","https://openalex.org/W2897980926","https://openalex.org/W2901466771","https://openalex.org/W2911978475","https://openalex.org/W2919115771","https://openalex.org/W2936695845","https://openalex.org/W2944400536","https://openalex.org/W2945472816","https://openalex.org/W2955425717","https://openalex.org/W2962764817","https://openalex.org/W2962766617","https://openalex.org/W2962784628","https://openalex.org/W2963115613","https://openalex.org/W2963373823","https://openalex.org/W2963466845","https://openalex.org/W2963521239","https://openalex.org/W2966715458","https://openalex.org/W2967957126","https://openalex.org/W2968124245","https://openalex.org/W2970482702","https://openalex.org/W2970986790","https://openalex.org/W2973379954","https://openalex.org/W2995082892","https://openalex.org/W2995225687","https://openalex.org/W2997522493","https://openalex.org/W2998353611","https://openalex.org/W3003209274","https://openalex.org/W3005680577","https://openalex.org/W3012608737","https://openalex.org/W3017330637","https://openalex.org/W3024545783","https://openalex.org/W3027879771","https://openalex.org/W3030691360","https://openalex.org/W3046375318","https://openalex.org/W3047555776","https://openalex.org/W3090832565","https://openalex.org/W3094950914","https://openalex.org/W3100748148","https://openalex.org/W3101223450","https://openalex.org/W3104050923","https://openalex.org/W3119438769","https://openalex.org/W3123459983","https://openalex.org/W3123742938","https://openalex.org/W3126337491","https://openalex.org/W3144208177","https://openalex.org/W3157598734","https://openalex.org/W3162922479","https://openalex.org/W3164654615","https://openalex.org/W3165058054","https://openalex.org/W3166396011","https://openalex.org/W3166845084","https://openalex.org/W3180355996","https://openalex.org/W3184735396","https://openalex.org/W3186209406","https://openalex.org/W3193402170","https://openalex.org/W3195577433","https://openalex.org/W3199965269","https://openalex.org/W3204755840","https://openalex.org/W3207576362","https://openalex.org/W4205539453","https://openalex.org/W4212774754","https://openalex.org/W4214708455","https://openalex.org/W4214717370","https://openalex.org/W4224308101","https://openalex.org/W4225323055","https://openalex.org/W4225832925","https://openalex.org/W4226278401","https://openalex.org/W4229036808","https://openalex.org/W4235803738","https://openalex.org/W4251247712","https://openalex.org/W4255889725","https://openalex.org/W4283368635","https://openalex.org/W4287027469","https://openalex.org/W4287208373","https://openalex.org/W4287813795","https://openalex.org/W4288574670","https://openalex.org/W4288860568","https://openalex.org/W4292779060","https://openalex.org/W4293030607","https://openalex.org/W4294170691","https://openalex.org/W4295916547","https://openalex.org/W4295938038","https://openalex.org/W4295951577","https://openalex.org/W4297808394","https://openalex.org/W4298331175","https://openalex.org/W4306809100","https://openalex.org/W4307006119","https://openalex.org/W4312091811","https://openalex.org/W4312091890","https://openalex.org/W4312220150","https://openalex.org/W4312549535","https://openalex.org/W4312576773","https://openalex.org/W4312804044","https://openalex.org/W4312982094","https://openalex.org/W4315925340","https://openalex.org/W4317542939","https://openalex.org/W4319049883","https://openalex.org/W4320458302","https://openalex.org/W4320495974","https://openalex.org/W4320514069","https://openalex.org/W4320858981","https://openalex.org/W4321855097","https://openalex.org/W4322718191","https://openalex.org/W4322761295","https://openalex.org/W4323030240","https://openalex.org/W4323066559","https://openalex.org/W4324144441","https://openalex.org/W4324299475","https://openalex.org/W4328120750","https://openalex.org/W4353007118","https://openalex.org/W4361866053","https://openalex.org/W4366327625","https://openalex.org/W4366330503","https://openalex.org/W4366459807","https://openalex.org/W4375870219","https://openalex.org/W4376312115","https://openalex.org/W4377047569","https://openalex.org/W4378945744","https://openalex.org/W4379259189","https://openalex.org/W4379879090","https://openalex.org/W4380715596","https://openalex.org/W4381930847","https://openalex.org/W4384071683","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4385262478","https://openalex.org/W4385436420","https://openalex.org/W4385546024","https://openalex.org/W4386059972","https://openalex.org/W4386185600","https://openalex.org/W4386211615","https://openalex.org/W4386566421","https://openalex.org/W4386907423","https://openalex.org/W4387026748","https://openalex.org/W4387113775","https://openalex.org/W4387211307","https://openalex.org/W4387560284","https://openalex.org/W4387561528","https://openalex.org/W4388584897","https://openalex.org/W4389072945","https://openalex.org/W4389261383","https://openalex.org/W4389363751","https://openalex.org/W4389599534","https://openalex.org/W4389707992","https://openalex.org/W4391416725","https://openalex.org/W4391505377","https://openalex.org/W4392340525","https://openalex.org/W4392486097","https://openalex.org/W4392851477","https://openalex.org/W4392947521","https://openalex.org/W4392947532","https://openalex.org/W4394659038","https://openalex.org/W4395444183","https://openalex.org/W4396913741","https://openalex.org/W4399567248","https://openalex.org/W4399695052","https://openalex.org/W4399838024","https://openalex.org/W4400455978","https://openalex.org/W4400981456","https://openalex.org/W4402432789","https://openalex.org/W4403789028","https://openalex.org/W6631190155","https://openalex.org/W6640773114","https://openalex.org/W6678262379","https://openalex.org/W6679997575","https://openalex.org/W6682631176","https://openalex.org/W6683258052","https://openalex.org/W6687483927","https://openalex.org/W6729342207","https://openalex.org/W6747316385","https://openalex.org/W6754096985","https://openalex.org/W6755207826","https://openalex.org/W6757081750","https://openalex.org/W6761205521","https://openalex.org/W6764024669","https://openalex.org/W6766819354","https://openalex.org/W6766904570","https://openalex.org/W6766912723","https://openalex.org/W6767102903","https://openalex.org/W6775750170","https://openalex.org/W6776721752","https://openalex.org/W6778485988","https://openalex.org/W6784333009","https://openalex.org/W6784492723","https://openalex.org/W6785277102","https://openalex.org/W6785642512","https://openalex.org/W6789909235","https://openalex.org/W6790019176","https://openalex.org/W6791479011","https://openalex.org/W6791613716","https://openalex.org/W6792155083","https://openalex.org/W6793825583","https://openalex.org/W6796149595","https://openalex.org/W6796581206","https://openalex.org/W6800139874","https://openalex.org/W6803621926","https://openalex.org/W6803924480","https://openalex.org/W6806281474","https://openalex.org/W6838675997","https://openalex.org/W6839304758","https://openalex.org/W6842949855","https://openalex.org/W6854254364","https://openalex.org/W6854357704","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359","https://openalex.org/W2115758952"],"abstract_inverted_index":{"Medical":[0],"vision-language":[1,91],"models":[2,35],"(VLMs)":[3],"combine":[4],"computer":[5],"vision":[6],"(CV)":[7],"and":[8,16,41,51,65,98,107,121,140],"natural":[9],"language":[10,66],"processing":[11],"(NLP)":[12],"to":[13,73,153,167],"analyze":[14],"visual":[15,42,64],"textual":[17],"medical":[18,38,90,105,118,129,170],"data.":[19,79],"Our":[20],"paper":[21],"reviews":[22],"recent":[23,103,162],"advancements":[24],"in":[25,117,164],"developing":[26,165],"VLMs":[27,166],"specialized":[28],"for":[29,37,113,172],"healthcare,":[30],"focusing":[31],"on":[32,49,110],"publicly":[33],"available":[34],"designed":[36],"report":[39,119],"generation":[40,120],"question":[43],"answering":[44],"(VQA).":[45],"We":[46,123],"provide":[47],"background":[48],"NLP":[50],"CV,":[52],"explaining":[53],"how":[54],"techniques":[55],"from":[56,77],"both":[57],"fields":[58],"are":[59],"integrated":[60],"into":[61],"VLMs,":[62,106],"with":[63,137],"data":[67,134,138,171],"often":[68],"fused":[69],"using":[70],"Transformer-based":[71],"architectures":[72,97],"enable":[74],"effective":[75],"learning":[76],"multimodal":[78,169],"Key":[80],"areas":[81],"we":[82],"address":[83,154],"include":[84],"the":[85,96,161],"exploration":[86],"of":[87,95,101,142],"18":[88],"public":[89],"datasets,":[92],"in-depth":[93],"analyses":[94],"pre-training":[99],"strategies":[100],"16":[102],"noteworthy":[104],"comprehensive":[108],"discussion":[109],"evaluation":[111,144],"metrics":[112],"assessing":[114],"VLMs'":[115],"performance":[116],"VQA.":[122],"also":[124,149],"highlight":[125],"current":[126],"challenges":[127],"facing":[128],"VLM":[130],"development,":[131],"including":[132],"limited":[133],"availability,":[135],"concerns":[136],"privacy,":[139],"lack":[141],"proper":[143],"metrics,":[145],"among":[146],"others,":[147],"while":[148],"proposing":[150],"future":[151],"directions":[152],"these":[155],"obstacles.":[156],"Overall,":[157],"our":[158],"review":[159],"summarizes":[160],"progress":[163],"harness":[168],"improved":[173],"healthcare":[174],"applications.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":47},{"year":2025,"cited_by_count":101},{"year":2024,"cited_by_count":13}],"updated_date":"2026-06-05T09:01:59.212387","created_date":"2025-10-10T00:00:00"}