{"id":"https://openalex.org/W7125966055","doi":"https://doi.org/10.1109/smc58881.2025.11343384","title":"Multi-scale based cross-modal semantic alignment network for radiology report generation","display_name":"Multi-scale based cross-modal semantic alignment network for radiology report generation","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125966055","doi":"https://doi.org/10.1109/smc58881.2025.11343384"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5100361547","display_name":"Zhihao Zhang","orcid":"https://orcid.org/0000-0003-3900-2305"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihao Zhang","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124067706","display_name":"Long Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Zhao","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124091443","display_name":"Dun Lan","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dun Lan","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124085059","display_name":"Yuyao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyao Wang","raw_affiliation_strings":["Boston University,Department of Mathematics and Statistics,Boston,MA,USA"],"affiliations":[{"raw_affiliation_string":"Boston University,Department of Mathematics and Statistics,Boston,MA,USA","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124075127","display_name":"Linfeng Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linfeng Jiang","raw_affiliation_strings":["Qilu University of Technology (Shandong Academy of Sciences),Faculty of Economics and Management,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Qilu University of Technology (Shandong Academy of Sciences),Faculty of Economics and Management,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113985813","display_name":"Xiangjun Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangjun Dong","raw_affiliation_strings":["Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China"],"affiliations":[{"raw_affiliation_string":"Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences),Key Laboratory of Computing Power Network and Information Security, Ministry of Education,Jinan,China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100361547"],"corresponding_institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68829283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1538","last_page":"1543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.754800021648407,"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":0.754800021648407,"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":0.03840000182390213,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.036400001496076584,"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/image-registration","display_name":"Image registration","score":0.49900001287460327},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.49480000138282776},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45080000162124634},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44859999418258667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41530001163482666},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.3831999897956848},{"id":"https://openalex.org/keywords/semantic-network","display_name":"Semantic network","score":0.3734999895095825},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.3531999886035919}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784500002861023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5504999756813049},{"id":"https://openalex.org/C166704113","wikidata":"https://www.wikidata.org/wiki/Q861092","display_name":"Image registration","level":3,"score":0.49900001287460327},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45080000162124634},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41530001163482666},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C85407183","wikidata":"https://www.wikidata.org/wiki/Q1045785","display_name":"Semantic network","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.3531999886035919},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30379998683929443},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2858000099658966},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328720","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2101105183","https://openalex.org/W2152772232","https://openalex.org/W2549599535","https://openalex.org/W2575842049","https://openalex.org/W2605045867","https://openalex.org/W2745461083","https://openalex.org/W2770165365","https://openalex.org/W2949167374","https://openalex.org/W2963084599","https://openalex.org/W2963446712","https://openalex.org/W2963466845","https://openalex.org/W2995225687","https://openalex.org/W2997704374","https://openalex.org/W3104609094","https://openalex.org/W3173688449","https://openalex.org/W3174714208","https://openalex.org/W4312420429","https://openalex.org/W4319663728","https://openalex.org/W4385245566","https://openalex.org/W4386076536","https://openalex.org/W4390187353","https://openalex.org/W4390905318","https://openalex.org/W4400314951","https://openalex.org/W4404443084"],"related_works":[],"abstract_inverted_index":{"The":[0],"automatic":[1],"generation":[2],"of":[3,41,61,97],"radiology":[4,65,125],"reports":[5,126],"draws":[6],"attention":[7],"for":[8,23,53],"easing":[9],"radiologists\u2019":[10],"workload":[11],"and":[12,19,55,118,142],"aiding":[13],"diagnosis.":[14],"Cross-modal":[15,76],"alignment":[16,28,45,54,103,107],"between":[17,108],"images":[18],"text":[20],"is":[21],"critical":[22],"high-quality":[24],"reporting,":[25],"but":[26],"cross-modal":[27,101],"has":[29],"not":[30],"been":[31],"fully":[32],"explored":[33],"at":[34],"this":[35],"time":[36],"due":[37],"to":[38],"a":[39,73,85,100,119],"lack":[40],"annotation.":[42],"Meanwhile,":[43],"existing":[44],"methods":[46],"utilize":[47],"single":[48],"scale":[49],"image":[50,93],"region":[51],"features":[52],"cannot":[56],"accommodate":[57],"the":[58,109,140],"different":[59,98],"sizes":[60],"anatomical":[62],"structures":[63],"in":[64,95],"images.":[66],"To":[67],"address":[68],"these":[69],"problems,":[70],"we":[71],"propose":[72],"Multi-scale":[74],"based":[75],"Semantic":[77],"Alignment":[78],"Network":[79],"(MCSANet).":[80],"It":[81],"includes":[82],"three":[83],"modules:":[84],"multi-scale":[86],"visual":[87],"feature":[88],"extraction":[89],"module,":[90,104],"capturing":[91],"key":[92],"information":[94],"windows":[96],"sizes;":[99],"semantic":[102,106],"achieving":[105],"two":[110],"modalities":[111],"without":[112],"relying":[113],"on":[114,139],"additional":[115],"auxiliary":[116],"information;":[117],"transformer":[120],"report":[121],"generator,":[122],"which":[123],"generates":[124],"using":[127],"final":[128],"features.":[129],"Experimental":[130],"results":[131],"show":[132],"that":[133],"MCSANet":[134],"surpasses":[135],"other":[136],"leading":[137],"approaches":[138],"IU-Xray":[141],"MIMIC-CXR":[143],"datasets.":[144]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-29T00:00:00"}
