{"id":"https://openalex.org/W4411359061","doi":"https://doi.org/10.1109/tmi.2025.3580561","title":"Bridging the Semantic Gap in Medical Visual Question Answering With Prompt Learning","display_name":"Bridging the Semantic Gap in Medical Visual Question Answering With Prompt Learning","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W4411359061","doi":"https://doi.org/10.1109/tmi.2025.3580561","pmid":"https://pubmed.ncbi.nlm.nih.gov/40526558"},"language":"en","primary_location":{"id":"doi:10.1109/tmi.2025.3580561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2025.3580561","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/A5100647576","display_name":"Zilin Lu","orcid":"https://orcid.org/0000-0003-2437-283X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zilin Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091379515","display_name":"Qingjie Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingjie Zeng","raw_affiliation_strings":["School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029300511","display_name":"Mengkang Lu","orcid":"https://orcid.org/0009-0003-5679-1761"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengkang Lu","raw_affiliation_strings":["School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100765638","display_name":"Geng Chen","orcid":"https://orcid.org/0000-0001-8350-6581"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Geng Chen","raw_affiliation_strings":["School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100670074","display_name":"Yong Xia","orcid":"https://orcid.org/0000-0001-9273-2847"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xia","raw_affiliation_strings":["National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100647576"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":2.5568,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89824472,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"44","issue":"11","first_page":"4605","last_page":"4616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9973000288009644,"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":0.9973000288009644,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9639999866485596,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9538999795913696,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.9362212419509888},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.627918004989624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6196656823158264},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4944291114807129},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4779346287250519},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4007495939731598},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3489839434623718},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17101532220840454},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.1572759747505188}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9362212419509888},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.627918004989624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6196656823158264},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4944291114807129},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4779346287250519},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4007495939731598},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3489839434623718},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17101532220840454},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.1572759747505188},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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":"D003952","descriptor_name":"Diagnostic Imaging","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003952","descriptor_name":"Diagnostic Imaging","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003952","descriptor_name":"Diagnostic Imaging","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"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":"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":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"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}],"locations_count":2,"locations":[{"id":"doi:10.1109/tmi.2025.3580561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmi.2025.3580561","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:40526558","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40526558","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":[],"awards":[{"id":"https://openalex.org/G984875820","display_name":null,"funder_award_id":"62171377","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2411377185","https://openalex.org/W2560730294","https://openalex.org/W2897980926","https://openalex.org/W2901466771","https://openalex.org/W2963150162","https://openalex.org/W2963954913","https://openalex.org/W2965373594","https://openalex.org/W2966683369","https://openalex.org/W2970231061","https://openalex.org/W2970476646","https://openalex.org/W2979525559","https://openalex.org/W3004349648","https://openalex.org/W3090449556","https://openalex.org/W3098267758","https://openalex.org/W3104050923","https://openalex.org/W3164670515","https://openalex.org/W3165058054","https://openalex.org/W3173220247","https://openalex.org/W3174148569","https://openalex.org/W3174770825","https://openalex.org/W3198377975","https://openalex.org/W3203255640","https://openalex.org/W3203635737","https://openalex.org/W4283258232","https://openalex.org/W4304092130","https://openalex.org/W4307823382","https://openalex.org/W4312310776","https://openalex.org/W4312582757","https://openalex.org/W4312982094","https://openalex.org/W4379879090","https://openalex.org/W4385573131","https://openalex.org/W4386076293","https://openalex.org/W4386352883","https://openalex.org/W4386566421","https://openalex.org/W4387789891","https://openalex.org/W4388336515","https://openalex.org/W4388543952","https://openalex.org/W4403089452","https://openalex.org/W4406075583","https://openalex.org/W4406388205","https://openalex.org/W4409014564"],"related_works":["https://openalex.org/W4408719353","https://openalex.org/W4388870064","https://openalex.org/W2384605597","https://openalex.org/W2210139803","https://openalex.org/W2128807628","https://openalex.org/W4234264766","https://openalex.org/W2415426693","https://openalex.org/W2310544549","https://openalex.org/W2575246084","https://openalex.org/W3135226307"],"abstract_inverted_index":{"Medical":[0],"Visual":[1],"Question":[2],"Answering":[3],"(Med-VQA)":[4],"aims":[5],"to":[6,34,50,80],"answer":[7,123],"questions":[8,130],"regarding":[9],"the":[10,35,55,71,110],"content":[11],"of":[12,38],"medical":[13,39,201],"images,":[14],"crucial":[15],"for":[16,197],"enhancing":[17],"diagnostics":[18],"and":[19,61,98,131,136,147,162,193],"education":[20],"in":[21,25,84,177,187,191,200],"healthcare.":[22],"However,":[23],"progress":[24],"this":[26,52,87],"field":[27],"is":[28],"hindered":[29],"by":[30,113,125],"data":[31,40],"scarcity":[32],"due":[33],"resource-intensive":[36],"nature":[37],"annotation.":[41],"While":[42],"existing":[43,153],"Med-VQA":[44,154,192],"approaches":[45],"often":[46],"rely":[47],"on":[48,143,156],"pre-training":[49],"mitigate":[51],"issue,":[53],"bridging":[54],"semantic":[56,111],"gap":[57,112],"between":[58,129],"pre-trained":[59,142],"models":[60,155],"specific":[62],"tasks":[63],"remains":[64],"a":[65,167,174],"significant":[66],"challenge.":[67],"This":[68],"paper":[69],"presents":[70],"Dynamic":[72,99],"Semantic-Adaptive":[73],"Prompting":[74,96,101],"(DSAP)":[75],"framework,":[76],"leveraging":[77,126],"prompt":[78],"learning":[79],"enhance":[81],"model":[82,115],"performance":[83,169],"Med-VQA.":[85],"To":[86],"end,":[88],"we":[89],"introduce":[90],"two":[91],"prompting":[92],"strategies:":[93],"Semantic":[94],"Alignment":[95],"(SAP)":[97],"Question-Aware":[100],"(DQAP).":[102],"SAP":[103],"prompts":[104],"multi-modal":[105],"inputs":[106],"during":[107],"fine-tuning,":[108],"reducing":[109],"aligning":[114],"outputs":[116],"with":[117,171],"domain-specific":[118],"contexts.":[119],"Simultaneously,":[120],"DQAP":[121],"enhances":[122],"selection":[124],"grammatical":[127],"relationships":[128],"answers,":[132],"thereby":[133],"improving":[134],"accuracy":[135],"relevance.":[137],"The":[138],"DSAP":[139,172],"framework":[140],"was":[141],"three":[144,157],"datasets-ROCO,":[145],"MedICaT,":[146],"MIMIC-CXR-and":[148],"comprehensively":[149],"evaluated":[150],"against":[151],"15":[152],"public":[158],"datasets:":[159],"VQA-RAD,":[160],"SLAKE,":[161],"PathVQA.":[163],"Our":[164],"results":[165,179],"demonstrate":[166],"substantial":[168],"improvement,":[170],"achieving":[173],"1.9%":[175],"enhancement":[176],"average":[178],"across":[180],"benchmarks.":[181],"These":[182],"findings":[183],"underscore":[184],"DSAP's":[185],"effectiveness":[186],"addressing":[188],"critical":[189],"challenges":[190],"suggest":[194],"promising":[195],"avenues":[196],"future":[198],"developments":[199],"AI.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}