{"id":"https://openalex.org/W4405754135","doi":"https://doi.org/10.1109/tmm.2024.3521728","title":"Knowledge-Guided Cross-Modal Alignment and Progressive Fusion for Chest X-Ray Report Generation","display_name":"Knowledge-Guided Cross-Modal Alignment and Progressive Fusion for Chest X-Ray Report Generation","publication_year":2024,"publication_date":"2024-12-24","ids":{"openalex":"https://openalex.org/W4405754135","doi":"https://doi.org/10.1109/tmm.2024.3521728"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2024.3521728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521728","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5100729418","display_name":"Lili Huang","orcid":"https://orcid.org/0000-0002-8753-3170"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lili Huang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-8753-3170","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073718157","display_name":"Yiming Cao","orcid":"https://orcid.org/0000-0002-8481-5762"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Cao","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053341136","display_name":"Pengcheng Jia","orcid":"https://orcid.org/0000-0001-5166-4921"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Jia","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398932","display_name":"Chenglong Li","orcid":"https://orcid.org/0000-0002-7233-2739"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I253932293","display_name":"Anhui University of Traditional Chinese Medicine","ror":"https://ror.org/0139j4p80","country_code":"CN","type":"education","lineage":["https://openalex.org/I253932293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Li","raw_affiliation_strings":["First Affiliated Hospital, Anhui University of Chinese Medicine, Hefei, China","Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7233-2739","affiliations":[{"raw_affiliation_string":"First Affiliated Hospital, Anhui University of Chinese Medicine, Hefei, China","institution_ids":["https://openalex.org/I253932293"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030720334","display_name":"Jin Tang","orcid":"https://orcid.org/0000-0001-8375-3590"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Tang","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8375-3590","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060053395","display_name":"Chuanfu Li","orcid":"https://orcid.org/0000-0002-4021-8034"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]},{"id":"https://openalex.org/I253932293","display_name":"Anhui University of Traditional Chinese Medicine","ror":"https://ror.org/0139j4p80","country_code":"CN","type":"education","lineage":["https://openalex.org/I253932293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanfu Li","raw_affiliation_strings":["First Affiliated Hospital, Anhui University of Chinese Medicine, Hefei, China","Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China","First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"First Affiliated Hospital, Anhui University of Chinese Medicine, Hefei, China","institution_ids":["https://openalex.org/I253932293"]},{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui Provincial Key Laboratory of Security Artificial Intelligence, School of Artificial Intelligence, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"First Affiliated Hospital of Anhui University of Chinese Medicine, Hefei, China","institution_ids":["https://openalex.org/I253932293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.78851982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"27","issue":null,"first_page":"557","last_page":"567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.988099992275238,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.988099992275238,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9373000264167786,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778196334838867},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5277719497680664},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.47372332215309143},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4308048188686371},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10131829977035522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778196334838867},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5277719497680664},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.47372332215309143},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4308048188686371},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10131829977035522},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2024.3521728","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2024.3521728","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1244492877","display_name":null,"funder_award_id":"62106006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G845944294","display_name":null,"funder_award_id":"62376004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G849060900","display_name":null,"funder_award_id":"2208085J18","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2152772232","https://openalex.org/W2194775991","https://openalex.org/W2549599535","https://openalex.org/W2575842049","https://openalex.org/W2745461083","https://openalex.org/W2888321701","https://openalex.org/W2890781596","https://openalex.org/W2903721568","https://openalex.org/W2906314281","https://openalex.org/W2949167374","https://openalex.org/W2962990649","https://openalex.org/W2963084599","https://openalex.org/W2963466845","https://openalex.org/W2981165461","https://openalex.org/W2995225687","https://openalex.org/W2997704374","https://openalex.org/W3034655362","https://openalex.org/W3035160838","https://openalex.org/W3035284526","https://openalex.org/W3093272873","https://openalex.org/W3096809860","https://openalex.org/W3103694015","https://openalex.org/W3104609094","https://openalex.org/W3173460036","https://openalex.org/W3173688449","https://openalex.org/W3174714208","https://openalex.org/W3175824375","https://openalex.org/W3181252431","https://openalex.org/W3183226462","https://openalex.org/W3213610319","https://openalex.org/W4229027955","https://openalex.org/W4285108627","https://openalex.org/W4285531589","https://openalex.org/W4312420429","https://openalex.org/W4312941295","https://openalex.org/W4375802394","https://openalex.org/W4385245566","https://openalex.org/W4387171500","https://openalex.org/W4395096791","https://openalex.org/W6631190155","https://openalex.org/W6677328238","https://openalex.org/W6682631176"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,278],"task":[1],"of":[2,14,44,53,96,101,109,197,223,226,252,266,289],"chest":[3,26,49,162],"X-ray":[4,27,50,163],"report":[5,28,164],"generation,":[6],"which":[7,138],"aims":[8],"to":[9,36,59,152,237,262,273],"simulate":[10],"the":[11,22,76,99,116,140,150,154,170,179,201,205,209,221,224,231,239,249,253,264,287,290],"diagnosis":[12],"process":[13],"doctors,":[15],"has":[16],"received":[17],"widespread":[18],"attention.":[19],"Compared":[20],"with":[21,90,187],"image":[23],"caption":[24],"task,":[25],"generation":[29],"is":[30,235],"more":[31,41,65],"challenging":[32],"since":[33],"it":[34],"needs":[35],"generate":[37,274],"a":[38,127,144,217,258],"longer":[39],"and":[40,80,83,103,134,158,182,211,229,244,270,283],"accurate":[42,66,161],"description":[43],"each":[45],"diagnostic":[46],"part":[47,95],"in":[48,88],"images.":[51],"Most":[52],"existing":[54,71],"works":[55,97],"focus":[56],"on":[57,70,194,200,281],"how":[58],"extract":[60],"better":[61,275],"visual":[62,79,102,210,243],"features":[63,225,272],"or":[64],"text":[67,81,104,212,245],"expression":[68],"based":[69,193],"reports.":[72,277],"However,":[73],"they":[74],"ignore":[75],"interactions":[77,100],"between":[78,119,242],"modalities":[82,213],"are":[84,214],"thus":[85],"obviously":[86],"not":[87,114],"line":[89],"human":[91],"thinking.":[92],"A":[93],"small":[94],"explore":[98],"modalities,":[105,228],"but":[106],"data-driven":[107],"learning":[108],"cross-modal":[110,155],"information":[111],"mapping":[112,218],"can":[113],"break":[115],"semantic":[117,240],"gap":[118,241],"different":[120],"modalities.":[121,246],"In":[122,166],"this":[123],"work,":[124],"we":[125,168,256],"propose":[126],"novel":[128],"approach":[129],"called":[130],"Knowledge-guided":[131],"Cross-modal":[132],"Alignment":[133],"Progressive":[135],"fusion":[136,233,260],"(KCAP),":[137],"takes":[139],"knowledge":[141,147,172,191,202,207],"words":[142,192,203],"from":[143,178,204],"created":[145],"medical":[146,171,176,206,276],"dictionary":[148,173],"as":[149,190],"bridge":[151],"guide":[153],"feature":[156],"alignment":[157,232],"fusion,":[159],"for":[160,220],"generation.":[165],"particular,":[167],"create":[169],"by":[174,216],"extracting":[175],"phrases":[177,186],"training":[180],"set":[181],"then":[183,230],"selecting":[184],"some":[185],"substantive":[188],"meanings":[189],"their":[195],"frequency":[196],"occurrence.":[198],"Based":[199],"dictionary,":[208],"interacted":[215],"layer":[219],"enhancement":[222],"two":[227],"module":[234],"introduced":[236],"mitigate":[238],"To":[247],"retain":[248],"important":[250],"details":[251],"original":[254,271],"information,":[255],"design":[257],"progressive":[259],"scheme":[261],"integrate":[263],"advantages":[265],"both":[267],"salient":[268],"fused":[269],"experimental":[279],"results":[280],"IU-Xray":[282],"MIMIC":[284],"datasets":[285],"demonstrate":[286],"effectiveness":[288],"proposed":[291],"KCAP.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}