{"id":"https://openalex.org/W4387171875","doi":"https://doi.org/10.3233/faia230389","title":"Multi-Modal Fusion with Semantic Supervision for Radiology Report Generation","display_name":"Multi-Modal Fusion with Semantic Supervision for Radiology Report Generation","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171875","doi":"https://doi.org/10.3233/faia230389"},"language":"en","primary_location":{"id":"doi:10.3233/faia230389","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230389","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230389","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230389","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102441247","display_name":"Xing Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing Jia","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001877137","display_name":"Yun Xiong","orcid":"https://orcid.org/0000-0002-8575-5415"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Xiong","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447010","display_name":"Yao Zhang","orcid":"https://orcid.org/0000-0003-2789-6962"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhang","raw_affiliation_strings":["Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100779209","display_name":"Li Luo","orcid":"https://orcid.org/0000-0003-3605-9904"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Luo","raw_affiliation_strings":["School of Public Health, Fudan University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Public Health, Fudan University, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001877137"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":0.7546,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78028141,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9941999912261963,"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":0.9941999912261963,"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":0.9901000261306763,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9767000079154968,"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":0.7479650974273682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5556097030639648},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5545163750648499},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.519263505935669},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5175116062164307},{"id":"https://openalex.org/keywords/image-fusion","display_name":"Image fusion","score":0.48292991518974304},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4672417938709259},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.458936870098114},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4499635398387909},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.44484102725982666},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42346689105033875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3508743643760681},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08102497458457947},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06676942110061646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479650974273682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5556097030639648},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5545163750648499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.519263505935669},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5175116062164307},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.48292991518974304},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4672417938709259},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.458936870098114},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4499635398387909},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.44484102725982666},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42346689105033875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3508743643760681},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08102497458457947},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06676942110061646},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230389","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230389","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230389","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230389","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230389","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230389","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5340839507","display_name":null,"funder_award_id":"U1936213","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":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171875.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1895577753","https://openalex.org/W2152772232","https://openalex.org/W2302086703","https://openalex.org/W2511730936","https://openalex.org/W2549599535","https://openalex.org/W2770165365","https://openalex.org/W2803411968","https://openalex.org/W2890888035","https://openalex.org/W2902243109","https://openalex.org/W2903721568","https://openalex.org/W2929309437","https://openalex.org/W2938603906","https://openalex.org/W2942396292","https://openalex.org/W2963101956","https://openalex.org/W2963282262","https://openalex.org/W2963446712","https://openalex.org/W2964359091","https://openalex.org/W2964546107","https://openalex.org/W2966554469","https://openalex.org/W2979861699","https://openalex.org/W2980483218","https://openalex.org/W2990818246","https://openalex.org/W2995753487","https://openalex.org/W2997704374","https://openalex.org/W3003817677","https://openalex.org/W3030163527","https://openalex.org/W3034655362","https://openalex.org/W3036968235","https://openalex.org/W3094307802","https://openalex.org/W3096799362","https://openalex.org/W3098325931","https://openalex.org/W3104609094","https://openalex.org/W3118571973","https://openalex.org/W3128439646","https://openalex.org/W3132450979","https://openalex.org/W3135367836","https://openalex.org/W3166142651","https://openalex.org/W3166396011","https://openalex.org/W3166845084","https://openalex.org/W3168117093","https://openalex.org/W3174714208","https://openalex.org/W3177048142","https://openalex.org/W3197531068","https://openalex.org/W3204326462","https://openalex.org/W3211037369","https://openalex.org/W3212101459","https://openalex.org/W4206050569","https://openalex.org/W4285108627","https://openalex.org/W4285531589","https://openalex.org/W4287120153","https://openalex.org/W4287325132","https://openalex.org/W4287755086","https://openalex.org/W4292779060","https://openalex.org/W4307006119","https://openalex.org/W4307073150","https://openalex.org/W4313525635","https://openalex.org/W4321018175","https://openalex.org/W4385245566","https://openalex.org/W4385573131","https://openalex.org/W4394659038"],"related_works":["https://openalex.org/W2564015900","https://openalex.org/W2963829519","https://openalex.org/W2147243590","https://openalex.org/W2252005665","https://openalex.org/W3078371441","https://openalex.org/W2922382144","https://openalex.org/W271538509","https://openalex.org/W3182591145","https://openalex.org/W118347290","https://openalex.org/W1020482675"],"abstract_inverted_index":{"Radiology":[0],"report":[1,14,36,76],"generation,":[2,52],"one":[3],"way":[4],"of":[5,23,33,50,54,89,108,117,179,187],"analyzing":[6],"radiology":[7,75],"images,":[8],"is":[9,22,113,151],"to":[10,26,114,153],"generate":[11],"a":[12,73,124,141],"textual":[13,58],"automatically":[15],"for":[16],"the":[17,31,48,55,94,99,105,109,118,131,135,146,155,165,185],"given":[18],"image,":[19],"and":[20,29,57,60,82,98,129,137,162,182],"it":[21],"great":[24],"significance":[25],"assist":[27],"diagnosis":[28],"alleviate":[30],"workload":[32],"radiologists.":[34],"Some":[35],"generation":[37,77],"methods":[38,45],"have":[39],"been":[40],"therefore":[41],"proposed.":[42],"However,":[43],"these":[44],"suffer":[46],"from":[47],"problem":[49],"low-quality":[51],"because":[53],"visual":[56],"bias":[59],"training":[61],"with":[62,79,158,168],"text":[63,138],"similarity":[64,160],"oriented":[65],"objective.":[66],"To":[67],"solve":[68],"this":[69],"problem,":[70],"we":[71],"propose":[72],"novel":[74,142],"model":[78,128],"multi-modal":[80],"fusion":[81,96,111],"semantic":[83,100,147,159],"supervision,":[84],"namely":[85],"MS-Gen.":[86,188],"MS-Gen":[87],"consists":[88],"two":[90,176],"main":[91,106],"components,":[92],"i.e.,":[93,145],"semantic-visual":[95,110],"module":[97,112],"weighted":[101,148],"contrastive":[102,149],"loss.":[103],"Specifically,":[104],"idea":[107],"make":[115],"use":[116],"domain-specific":[119],"prior":[120],"knowledge":[121],"contained":[122],"in":[123],"large":[125],"pre-trained":[126],"visual-language":[127],"also":[130],"complementary":[132],"nature":[133],"between":[134],"image":[136],"modalities.":[139],"Moreover,":[140],"optimization":[143,156],"term,":[144],"loss,":[150],"proposed":[152],"guide":[154],"process":[157],"objective,":[161],"further":[163],"enforce":[164],"generated":[166],"reports":[167],"higher":[169],"clinical":[170],"accuracy.":[171],"Extensive":[172],"experiments":[173],"conducted":[174],"on":[175],"real":[177],"datasets":[178],"IU":[180],"X-Ray":[181],"MIMIC-CXR":[183],"demonstrate":[184],"effectiveness":[186]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}