{"id":"https://openalex.org/W4362664019","doi":"https://doi.org/10.1117/12.2654571","title":"Audio-visual feature fusion for improved thoracic disease classification","display_name":"Audio-visual feature fusion for improved thoracic disease classification","publication_year":2023,"publication_date":"2023-04-06","ids":{"openalex":"https://openalex.org/W4362664019","doi":"https://doi.org/10.1117/12.2654571"},"language":"en","primary_location":{"id":"doi:10.1117/12.2654571","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2654571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Imaging 2023: Computer-Aided Diagnosis","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/A5011778477","display_name":"Moinak Bhattacharya","orcid":"https://orcid.org/0000-0003-2378-5632"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moinak Bhattacharya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036343196","display_name":"Prateek Prasanna","orcid":"https://orcid.org/0000-0002-3068-3573"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prateek Prasanna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9811,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73538276,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.996399998664856,"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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9846000075340271,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13996","display_name":"Diverse Musicological Studies","score":0.9114999771118164,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7210205793380737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6732999086380005},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5584057569503784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5415480732917786},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.5189192295074463},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4280664622783661},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42347782850265503},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3917049467563629},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34889575839042664},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16379156708717346}],"concepts":[{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7210205793380737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6732999086380005},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5584057569503784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415480732917786},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.5189192295074463},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4280664622783661},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42347782850265503},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3917049467563629},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34889575839042664},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16379156708717346},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.2654571","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.2654571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Imaging 2023: Computer-Aided Diagnosis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.550000011920929,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2890952074","https://openalex.org/W3098751697","https://openalex.org/W4297841641","https://openalex.org/W4313134585","https://openalex.org/W6754392867","https://openalex.org/W6785025161","https://openalex.org/W6792155083","https://openalex.org/W6804186765","https://openalex.org/W6810176866","https://openalex.org/W6811054809","https://openalex.org/W6843199064"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2074916782","https://openalex.org/W2625296515","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2330333072","https://openalex.org/W2380912101"],"abstract_inverted_index":{"In":[0],"this":[1,50],"work,":[2],"we":[3],"fuse":[4,81],"imaging":[5,33,57,171],"features":[6,14],"from":[7,15,37],"Chest":[8],"X-Ray":[9],"(CXR)":[10],"scans":[11],"and":[12,58,76,79,127,137,144,159,165,167],"audio":[13,36,59,77,163],"dictations":[16],"of":[17,49,135],"a":[18,38,98],"radiologist":[19,39],"to":[20,97],"improve":[21],"thoracic":[22,120],"disease":[23,28,62,103,121],"classification.":[24,63,104],"Recent":[25],"deep":[26],"learning-based":[27],"classification":[29,99,122],"methods":[30],"mostly":[31],"use":[32,65],"modalities.":[34],"Dictation":[35],"contains":[40],"rich":[41],"auxiliary":[42],"diseaserelated":[43],"contextual":[44],"information.":[45],"The":[46],"main":[47],"hypothesis":[48],"proposed":[51,110],"work":[52],"is":[53,95],"that":[54,108,123],"leveraging":[55],"complementary":[56],"representations":[60,84],"improves":[61],"We":[64,105,132],"shifting":[66,140],"window":[67,141],"(Swin)":[68],"transformer":[69,142],"architectures":[70,146],"as":[71],"encoders":[72],"for":[73,101,118,139,148,161,169],"both":[74],"visual":[75],"modalities":[78],"finally":[80],"the":[82,109,114,152,162,170],"feature":[83,87,93],"using":[85],"cross-correlational":[86],"multiplication":[88],"fusion":[89],"strategy.":[90],"This":[91],"fused":[92,111,149],"representation":[94],"fed":[96],"head":[100],"downstream":[102],"experimentally":[106],"show":[107],"model":[112],"outperforms":[113],"individual":[115],"modality":[116,164],"models":[117],"multi-class":[119],"includes":[124],"normal,":[125],"pneumonia,":[126],"congestive":[128],"heart":[129],"failure":[130],"cases.":[131],"report":[133],"F1-score":[134],"0.5415":[136],"0.5353":[138],"base":[143],"small":[145],"respectively,":[147],"modalities,":[150],"while":[151],"corresponding":[153],"baselines":[154],"are":[155],"reported":[156],"at":[157],"0.5046":[158],"0.5076":[160],"0.4676":[166],"0.5261":[168],"modality,":[172],"respectively.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
