{"id":"https://openalex.org/W7131061776","doi":"https://doi.org/10.1109/iccvw69036.2025.00127","title":"Dual-LVT: A Dual Attention Language-Vision Transformer for Tumor Segmentation","display_name":"Dual-LVT: A Dual Attention Language-Vision Transformer for Tumor Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131061776","doi":"https://doi.org/10.1109/iccvw69036.2025.00127"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5103411114","display_name":"S F Zhang","orcid":"https://orcid.org/0009-0006-3576-5240"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Shiman Zhang","raw_affiliation_strings":["Yeshiva University,Department of Graduate Computer Science and Engineering,USA"],"affiliations":[{"raw_affiliation_string":"Yeshiva University,Department of Graduate Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I19772626"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073393494","display_name":"Songzhu Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I2802755631","display_name":"Morgan Stanley (United States)","ror":"https://ror.org/00aphdz18","country_code":"US","type":"company","lineage":["https://openalex.org/I2802755631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songzhu Zheng","raw_affiliation_strings":["Morgan Stanley,USA"],"affiliations":[{"raw_affiliation_string":"Morgan Stanley,USA","institution_ids":["https://openalex.org/I2802755631"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101409314","display_name":"Ming Ma","orcid":"https://orcid.org/0000-0002-2666-6295"},"institutions":[{"id":"https://openalex.org/I19772626","display_name":"Yeshiva University","ror":"https://ror.org/045x93337","country_code":"US","type":"education","lineage":["https://openalex.org/I19772626"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Ma","raw_affiliation_strings":["Yeshiva University,Department of Graduate Computer Science and Engineering,USA"],"affiliations":[{"raw_affiliation_string":"Yeshiva University,Department of Graduate Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I19772626"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103411114"],"corresponding_institution_ids":["https://openalex.org/I19772626"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74561574,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1183","last_page":"1192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.38659998774528503,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.38659998774528503,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.18320000171661377,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.1551000028848648,"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/segmentation","display_name":"Segmentation","score":0.652899980545044},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5440999865531921},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5102999806404114},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35989999771118164},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.35749998688697815},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3531000018119812},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.35089999437332153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6538000106811523},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.652899980545044},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5440999865531921},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5102999806404114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.35089999437332153},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00127","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1984703219","https://openalex.org/W2093457492","https://openalex.org/W2562469482","https://openalex.org/W2911489562","https://openalex.org/W3046375318","https://openalex.org/W3155171916","https://openalex.org/W4200631575","https://openalex.org/W4212875960","https://openalex.org/W4221163766","https://openalex.org/W4234920706","https://openalex.org/W4362636656","https://openalex.org/W4382998948","https://openalex.org/W4385307867","https://openalex.org/W4391109864","https://openalex.org/W4396614772","https://openalex.org/W4403649704","https://openalex.org/W4403649753","https://openalex.org/W4409367393","https://openalex.org/W4413146579"],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"target":[1],"volume":[2,139],"delineation":[3,140,163],"is":[4,167],"critical":[5],"for":[6,134],"successful":[7],"cancer":[8],"treatment.":[9],"Deep":[10],"learning":[11],"(DL)":[12],"has":[13],"driven":[14],"significant":[15],"advances":[16],"in":[17,56,161],"automatic":[18,162],"delineation,":[19],"and":[20,53,91,137,147],"the":[21,29,66,153],"emergence":[22],"of":[23,31,79,155],"large":[24],"language":[25,48,74,93],"models":[26],"(LLMs)":[27],"enables":[28,92],"use":[30],"multimodal":[32,44],"data,":[33],"such":[34],"as":[35,49,157],"clinical":[36,81],"notes,":[37],"to":[38,51,95,125],"assist":[39],"these":[40],"algorithms.":[41],"However,":[42],"existing":[43],"approaches":[45],"often":[46],"treat":[47],"secondary":[50],"vision":[52,89],"fuse":[54],"modalities":[55],"a":[57,122],"coarse":[58,98],"manner,":[59],"underutilizing":[60],"valuable":[61],"textual":[62],"information.":[63],"We":[64,106],"propose":[65],"Dual":[67],"Attention":[68],"Language\u2013Vision":[69],"Transformer":[70],"(Dual-LVT),":[71],"which":[72,116],"incorporates":[73],"em-beddings":[75],"from":[76,87],"LLM-generated":[77],"summaries":[78],"doctors'":[80],"notes.":[82],"Dual-LVT":[83,143],"separates":[84],"modality-fused":[85],"features":[86,94],"pure":[88],"information":[90],"directly":[96],"generate":[97],"segmentation":[99,136],"maps,":[100],"guiding":[101],"downstream":[102],"tasks":[103],"more":[104],"effectively.":[105],"further":[107],"introduce":[108],"an":[109],"Adaptive":[110],"Hounsfield":[111],"Unit":[112],"Clipping":[113],"(AdaHU)":[114],"module,":[115],"dynamically":[117],"adjusts":[118],"HU":[119],"ranges":[120],"via":[121],"gating":[123],"mechanism":[124],"handle":[126],"scanner-induced":[127],"heterogeneity.":[128],"Evaluations":[129],"on":[130],"multiple":[131],"public":[132],"datasets":[133],"2D":[135],"3D":[138],"show":[141],"that":[142],"achieves":[144],"superior":[145],"accuracy":[146],"robustness":[148],"over":[149],"state-of-the-art":[150],"models,":[151],"highlighting":[152],"potential":[154],"LLMs":[156],"primary":[158],"feature":[159],"extractors":[160],"systems.":[164],"The":[165],"code":[166],"available":[168],"at":[169],"https://github.com/Shira7z/Dual-LVT.git.":[170]},"counts_by_year":[],"updated_date":"2026-02-25T06:17:34.324206","created_date":"2026-02-24T00:00:00"}