{"id":"https://openalex.org/W7137836903","doi":"https://doi.org/10.1609/aaai.v40i11.37835","title":"DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities","display_name":"DiA-gnostic VLVAE: Disentangled Alignment-Constrained Vision Language Variational AutoEncoder for Robust Radiology Reporting with Missing Modalities","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137836903","doi":"https://doi.org/10.1609/aaai.v40i11.37835"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37835","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37835","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37835","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027212073","display_name":"Nagur Shareef Shaik","orcid":"https://orcid.org/0000-0002-2432-7409"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nagur Shareef Shaik","raw_affiliation_strings":["Georgia State University"],"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015473698","display_name":"Teja Krishna Cherukuri","orcid":"https://orcid.org/0000-0002-4952-728X"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teja Krishna Cherukuri","raw_affiliation_strings":["Georgia State University"],"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650603","display_name":"Adnan Masood","orcid":null},"institutions":[{"id":"https://openalex.org/I4210140100","display_name":"Universitatea de Stat din Tiraspol","ror":"https://ror.org/04wd4rg36","country_code":"MD","type":"education","lineage":["https://openalex.org/I4210140100"]}],"countries":["MD"],"is_corresponding":false,"raw_author_name":"Adnan Masood","raw_affiliation_strings":["UST"],"affiliations":[{"raw_affiliation_string":"UST","institution_ids":["https://openalex.org/I4210140100"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068927047","display_name":"Dong Hye Ye","orcid":"https://orcid.org/0000-0002-9186-4095"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Hye Ye","raw_affiliation_strings":["Georgia State University"],"affiliations":[{"raw_affiliation_string":"Georgia State University","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027212073"],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05671642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"8814","last_page":"8823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3391000032424927,"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":0.3391000032424927,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.17659999430179596,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.12630000710487366,"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/modalities","display_name":"Modalities","score":0.6265000104904175},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6194000244140625},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6010000109672546},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5453000068664551},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.47279998660087585},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.4602000117301941},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44029998779296875}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6309999823570251},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6265000104904175},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6226999759674072},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6010000109672546},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.47279998660087585},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.4602000117301941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4528999924659729},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37220001220703125},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C69505689","wikidata":"https://www.wikidata.org/wiki/Q455338","display_name":"Unified Medical Language System","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2874999940395355},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.250900000333786},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37835","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37835","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37835","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37835","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"integration":[1],"of":[2,157],"medical":[3],"images":[4],"with":[5,36],"clinical":[6,42,50],"context":[7,51],"is":[8,91],"essential":[9],"for":[10],"generating":[11],"accurate":[12],"and":[13,34,53,60,67,102,120,147,159],"clinically":[14,68],"interpretable":[15],"radiology":[16,84],"reports.":[17],"However,":[18],"current":[19],"automated":[20],"methods":[21],"often":[22],"rely":[23],"on":[24],"resource-heavy":[25],"Large":[26],"Language":[27],"Models":[28],"(LLMs)":[29],"or":[30],"static":[31],"knowledge":[32],"graphs":[33],"struggle":[35],"two":[37],"fundamental":[38],"challenges":[39],"in":[40],"real-world":[41],"data:":[43],"(1)":[44],"missing":[45,97],"modalities,":[46],"such":[47],"as":[48],"incomplete":[49],",":[52],"(2)":[54],"feature":[55],"entanglement,":[56],"where":[57],"mixed":[58],"modality-specific":[59,103],"shared":[61,101],"information":[62],"leads":[63],"to":[64,93,96,126,139],"suboptimal":[65,128],"fusion":[66],"unfaithful":[69],"hallucinated":[70],"findings.":[71],"To":[72],"address":[73],"these":[74,123,136],"challenges,":[75],"we":[76],"propose":[77],"the":[78,144,166],"DiA-gnostic":[79],"VLVAE,":[80],"which":[81],"achieves":[82],"robust":[83],"reporting":[85],"through":[86],"Disentangled":[87],"Alignment.":[88],"Our":[89],"framework":[90],"designed":[92],"be":[94],"resilient":[95],"modalities":[98],"by":[99],"disentangling":[100],"features":[104],"using":[105],"a":[106],"Mixture-of-Experts":[107],"(MoE)":[108],"based":[109],"Vision-Language":[110],"Variational":[111],"Autoencoder":[112],"(VLVAE).":[113],"A":[114,130],"constrained":[115],"optimization":[116],"objective":[117],"enforces":[118],"orthogonality":[119],"alignment":[121],"between":[122],"latent":[124],"representations":[125,138],"prevent":[127],"fusion.":[129],"compact":[131],"LLaMA-X":[132],"decoder":[133],"then":[134],"uses":[135],"disentangled":[137],"generate":[140],"reports":[141],"efficiently.":[142],"On":[143],"IU":[145],"X-Ray":[146],"MIMIC-CXR":[148],"datasets,":[149],"DiA":[150],"has":[151],"set":[152],"new":[153],"state-of-the-art":[154,171],"BLEU@4":[155],"scores":[156],"0.266":[158],"0.134,":[160],"respectively.":[161],"Experimental":[162],"results":[163],"show":[164],"that":[165],"proposed":[167],"method":[168],"significantly":[169],"outperforms":[170],"models.":[172]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}