{"id":"https://openalex.org/W4408353302","doi":"https://doi.org/10.1109/icassp49660.2025.10888243","title":"An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis","display_name":"An Attentive Dual-Encoder Framework Leveraging Multimodal Visual and Semantic Information for Automatic OSAHS Diagnosis","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353302","doi":"https://doi.org/10.1109/icassp49660.2025.10888243"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5018160615","display_name":"Yingchen Wei","orcid":"https://orcid.org/0009-0007-2089-3239"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchen Wei","raw_affiliation_strings":["Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007950680","display_name":"Xihe Qiu","orcid":"https://orcid.org/0000-0003-4024-925X"},"institutions":[{"id":"https://openalex.org/I141962983","display_name":"Shanghai University of Engineering Science","ror":"https://ror.org/0557b9y08","country_code":"CN","type":"education","lineage":["https://openalex.org/I141962983"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihe Qiu","raw_affiliation_strings":["Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai University of Engineering Science,School of Electronic and Electrical Engineering,Shanghai,China","institution_ids":["https://openalex.org/I141962983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869238","display_name":"Xiaoyu Tan","orcid":"https://orcid.org/0000-0003-3555-7143"},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Tan","raw_affiliation_strings":["INFLY TECH (Shanghai) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INFLY TECH (Shanghai) Co., Ltd","institution_ids":["https://openalex.org/I110675161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108270699","display_name":"Jingjing Huang","orcid":"https://orcid.org/0000-0002-3009-8681"},"institutions":[{"id":"https://openalex.org/I4210112065","display_name":"Eye & ENT Hospital of Fudan University","ror":"https://ror.org/02wc1yz29","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210112065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingjing Huang","raw_affiliation_strings":["Fudan University,Eye & ENT Hospital,ENT Institute and Department of Otorhinolaryngology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Eye & ENT Hospital,ENT Institute and Department of Otorhinolaryngology,Shanghai,China","institution_ids":["https://openalex.org/I4210112065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906116","display_name":"Wei Chu","orcid":"https://orcid.org/0000-0002-4595-388X"},"institutions":[{"id":"https://openalex.org/I110675161","display_name":"Infosys (India)","ror":"https://ror.org/03bs18y54","country_code":"IN","type":"company","lineage":["https://openalex.org/I110675161"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Wei Chu","raw_affiliation_strings":["INFLY TECH (Shanghai) Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INFLY TECH (Shanghai) Co., Ltd","institution_ids":["https://openalex.org/I110675161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100579456","display_name":"Yinghui Xu","orcid":"https://orcid.org/0009-0002-7346-2794"},"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":"Yinghui Xu","raw_affiliation_strings":["Fudan University,Artificial Intelligence Innovation and Incubation Institute,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Artificial Intelligence Innovation and Incubation Institute,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101493262","display_name":"Yuan Qi","orcid":"https://orcid.org/0000-0002-3206-4776"},"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":"Yuan Qi","raw_affiliation_strings":["Fudan University,Artificial Intelligence Innovation and Incubation Institute,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University,Artificial Intelligence Innovation and Incubation Institute,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11579","display_name":"Cardiovascular and Diving-Related Complications","score":0.29739999771118164,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11579","display_name":"Cardiovascular and Diving-Related Complications","score":0.29739999771118164,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7787783145904541},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6173531413078308},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6021685004234314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47674500942230225},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40651798248291016},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36166858673095703}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787783145904541},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6173531413078308},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6021685004234314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47674500942230225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40651798248291016},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36166858673095703},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888243","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888243","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1543410833","https://openalex.org/W1976526581","https://openalex.org/W2420887096","https://openalex.org/W2592857683","https://openalex.org/W2754276438","https://openalex.org/W2782755471","https://openalex.org/W2886046288","https://openalex.org/W2949208911","https://openalex.org/W2963716420","https://openalex.org/W3004298088","https://openalex.org/W3015351929","https://openalex.org/W3157699413","https://openalex.org/W3168825659","https://openalex.org/W4231438709","https://openalex.org/W4283732245","https://openalex.org/W4312443924","https://openalex.org/W4382560317","https://openalex.org/W4384827460","https://openalex.org/W4389454115","https://openalex.org/W4390873225","https://openalex.org/W4399522030","https://openalex.org/W4399533140","https://openalex.org/W4402660140","https://openalex.org/W6631190155","https://openalex.org/W6780140667","https://openalex.org/W6780593937","https://openalex.org/W6791353385","https://openalex.org/W6795140394"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Obstructive":[0],"sleep":[1,8],"apnea-hypopnea":[2],"syndrome":[3],"(OS-AHS)":[4],"is":[5,27,137],"a":[6,57,124],"common":[7],"disorder":[9],"caused":[10],"by":[11],"upper":[12],"airway":[13],"blockage,":[14],"leading":[15],"to":[16,43],"oxygen":[17],"deprivation":[18],"and":[19,30,48,65,86,98,105,117],"disrupted":[20],"sleep.":[21],"Traditional":[22],"diagnosis":[23],"using":[24,36,76],"polysomnography":[25],"(PSG)":[26],"expensive,":[28],"time-consuming,":[29],"uncomfortable.":[31],"Existing":[32],"deep":[33],"learning":[34],"methods":[35],"facial":[37,45,81],"image":[38,97],"analysis":[39],"lack":[40],"accuracy":[41,122],"due":[42],"poor":[44],"feature":[46,103],"capture":[47],"limited":[49],"sample":[50],"sizes.":[51],"To":[52],"address":[53],"this,":[54],"we":[55],"propose":[56],"multimodal":[58],"dual":[59],"encoder":[60],"model":[61,73],"that":[62],"integrates":[63],"visual":[64],"language":[66],"inputs":[67],"for":[68,101],"automated":[69],"OSAHS":[70],"diagnosis.":[71],"The":[72],"balances":[74],"data":[75,90,100],"randomOverSampler":[77],"(ROS),":[78],"extracts":[79],"key":[80],"features":[82],"with":[83],"attention":[84,95],"grids,":[85],"converts":[87],"basic":[88],"physiological":[89],"into":[91],"meaningful":[92],"text.":[93],"Cross":[94],"combines":[96],"text":[99],"better":[102],"extraction,":[104],"ordered":[106],"regression":[107],"loss":[108],"ensures":[109],"stable":[110],"learning.":[111],"Our":[112],"approach":[113],"improves":[114],"diagnostic":[115],"efficiency":[116],"accuracy,":[118],"achieving":[119],"91.3%":[120],"top-1":[121],"in":[123],"four":[125],"class":[126],"severity":[127],"classification":[128],"task,":[129],"demonstrating":[130],"state":[131],"of":[132],"the":[133],"art":[134],"performance.":[135],"Code":[136],"available":[138],"at":[139],"https://github.com/luboyan6/VTA-OSAHS.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}