{"id":"https://openalex.org/W4417247887","doi":"https://doi.org/10.1109/iccv51701.2025.01999","title":"MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs","display_name":"MedSegFactory: Text-Guided Generation of Medical Image-Mask Pairs","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417247887","doi":"https://doi.org/10.1109/iccv51701.2025.01999"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01999","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 (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.06897","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101860156","display_name":"Jiawei Mao","orcid":"https://orcid.org/0000-0002-6741-7033"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiawei Mao","raw_affiliation_strings":["UC Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101361893","display_name":"Yuhan Wang","orcid":"https://orcid.org/0009-0006-0401-4516"},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhan Wang","raw_affiliation_strings":["UC Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101653641","display_name":"Yucheng Tang","orcid":"https://orcid.org/0000-0003-0110-2466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yucheng Tang","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052339079","display_name":"Daguang Xu","orcid":"https://orcid.org/0000-0002-4621-881X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daguang Xu","raw_affiliation_strings":["NVIDIA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081849715","display_name":"Kang Wang","orcid":"https://orcid.org/0000-0002-6666-5641"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kang Wang","raw_affiliation_strings":["UC San Francisco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Francisco","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096293763","display_name":"Yang Yang","orcid":"https://orcid.org/0009-0001-5103-4361"},"institutions":[{"id":"https://openalex.org/I180670191","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54","country_code":"US","type":"education","lineage":["https://openalex.org/I180670191"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["UC San Francisco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC San Francisco","institution_ids":["https://openalex.org/I180670191"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084104975","display_name":"Zongwei Zhou","orcid":"https://orcid.org/0000-0002-3154-9851"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zongwei Zhou","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067640436","display_name":"Yuyin Zhou","orcid":"https://orcid.org/0000-0003-2232-9563"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuyin Zhou","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101860156"],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37646404,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21525","last_page":"21535"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7200000286102295,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.7200000286102295,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.05860000103712082,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.035999998450279236,"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":0.7968999743461609},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.583299994468689},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5163999795913696},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.48820000886917114},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.48669999837875366},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4090000092983246},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.40720000863075256},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.38960000872612},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3734999895095825}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7968999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505000233650208},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.583299994468689},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626999735832214},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5367000102996826},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.48820000886917114},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.48669999837875366},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.40720000863075256},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.36250001192092896},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3012000024318695},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.29260000586509705},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01999","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 (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.06897","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.06897","pdf_url":"https://arxiv.org/pdf/2504.06897","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.06897","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.06897","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.06897","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.06897","pdf_url":"https://arxiv.org/pdf/2504.06897","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417247887.pdf","grobid_xml":"https://content.openalex.org/works/W4417247887.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,83,131],"paper":[1],"presents":[2],"MedSegFactory,":[3],"a":[4,44,74],"versatile":[5],"medical":[6,13,52,105,135,143],"synthesis":[7,137],"framework":[8],"that":[9,113,154],"generates":[10,57,156],"high-quality":[11,128],"paired":[12,104],"images":[14,53,106],"and":[15,20,54,107,122,127,149,161,170,178],"segmentation":[16,37,59,108,172],"masks":[17,109],"across":[18],"modalities":[19],"tasks.":[21],"It":[22],"aims":[23],"to":[24,34,89],"serve":[25],"as":[26],"an":[27],"unlimited":[28],"data":[29,129,157,176],"repository,":[30],"supplying":[31],"image-mask":[32,66],"pairs":[33],"enhance":[35],"existing":[36],"tools.":[38],"The":[39],"core":[40],"of":[41,103,134,158],"MedSegFactory":[42,99,155],"is":[43],"dual-stream":[45],"diffusion":[46],"model,":[47],"where":[48],"one":[49],"stream":[50],"synthesizes":[51],"the":[55,115],"other":[56],"corresponding":[58],"masks.":[60],"To":[61],"ensure":[62],"precise":[63],"alignment":[64],"between":[65,81,96],"pairs,":[67],"we":[68],"introduce":[69],"Joint":[70],"Cross-Attention":[71],"(JCA),":[72],"enabling":[73],"collaborative":[75],"denoising":[76],"paradigm":[77,133],"by":[78],"dynamic":[79],"cross-conditioning":[80],"streams.":[82],"bidirectional":[84],"interaction":[85],"allows":[86],"both":[87,147],"representations":[88],"guide":[90],"each":[91],"other's":[92],"generation,":[93],"enhancing":[94,146],"consistency":[95],"generated":[97],"pairs.":[98],"unlocks":[100],"on-demand":[101],"generation":[102],"through":[110],"user-defined":[111],"prompts":[112],"specify":[114],"target":[116],"labels,":[117],"imaging":[118,144],"modalities,":[119],"anatomical":[120],"regions,":[121],"pathological":[123],"conditions,":[124],"facilitating":[125],"scalable":[126],"generation.":[130],"new":[132],"image":[136],"enables":[138],"seamless":[139],"integration":[140],"into":[141],"diverse":[142],"workflows,":[145],"efficiency":[148],"accuracy.":[150],"Extensive":[151],"experiments":[152],"show":[153],"superior":[159],"quality":[160],"usability,":[162],"achieving":[163],"competitive":[164],"or":[165],"state-of-the-art":[166],"performance":[167],"in":[168],"2D":[169],"3D":[171],"tasks":[173],"while":[174],"addressing":[175],"scarcity":[177],"regulatory":[179],"constraints.":[180]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}