{"id":"https://openalex.org/W4415193043","doi":"https://doi.org/10.48550/arxiv.2508.06182","title":"Clinically-guided Data Synthesis for Laryngeal Lesion Detection","display_name":"Clinically-guided Data Synthesis for Laryngeal Lesion Detection","publication_year":2025,"publication_date":"2025-08-08","ids":{"openalex":"https://openalex.org/W4415193043","doi":"https://doi.org/10.48550/arxiv.2508.06182"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.06182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06182","pdf_url":"https://arxiv.org/pdf/2508.06182","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.06182","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111187200","display_name":"Chiara Baldini","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Baldini, Chiara","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008578692","display_name":"Kaisar Kushibar","orcid":"https://orcid.org/0000-0001-7507-5208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kushibar, Kaisar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014725683","display_name":"Richard Osuala","orcid":"https://orcid.org/0000-0003-1835-8564"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Osuala, Richard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049150711","display_name":"Simone Balocco","orcid":"https://orcid.org/0000-0002-7149-7806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balocco, Simone","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015469645","display_name":"Oliver D\u00edaz","orcid":"https://orcid.org/0000-0001-8259-8381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Diaz, Oliver","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078391768","display_name":"Karim Lekadir","orcid":"https://orcid.org/0000-0002-9456-1612"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lekadir, Karim","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066219856","display_name":"Leonardo S. Mattos","orcid":"https://orcid.org/0000-0002-8511-9144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mattos, Leonardo S.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5111187200"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9276999831199646,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/T10863","display_name":"Voice and Speech Disorders","score":0.9276999831199646,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"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/T10307","display_name":"Head and Neck Cancer Studies","score":0.9035000205039978,"subfield":{"id":"https://openalex.org/subfields/2733","display_name":"Otorhinolaryngology"},"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/bottleneck","display_name":"Bottleneck","score":0.5139999985694885},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.43630000948905945},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4032999873161316},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.3546999990940094},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.3424000144004822},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.34049999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6104000210762024},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5139999985694885},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3912999927997589},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34049999713897705},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.337799996137619},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.2842000126838684},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.06182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06182","pdf_url":"https://arxiv.org/pdf/2508.06182","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.2508.06182","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.06182","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:2508.06182","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.06182","pdf_url":"https://arxiv.org/pdf/2508.06182","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"computer-aided":[1],"diagnosis":[2],"(CADx)":[3],"and":[4,38,57,121,179,234],"detection":[5,166],"(CADe)":[6],"systems":[7,66],"have":[8],"made":[9],"significant":[10],"progress":[11],"in":[12,21,148,206,241],"various":[13],"medical":[14],"domains,":[15],"their":[16,204],"application":[17],"is":[18,67],"still":[19],"limited":[20],"specialized":[22,63],"fields":[23],"such":[24],"as":[25,49],"otorhinolaryngology.":[26],"In":[27],"the":[28,39,50,68,114,145,157,165,174,186,189,215,219,236],"latter,":[29],"current":[30],"assessment":[31,146],"methods":[32],"heavily":[33],"depend":[34],"on":[35,181],"operator":[36],"expertise,":[37],"high":[40],"heterogeneity":[41],"of":[42,70,155,159,168,188,221,238],"lesions":[43,170],"complicates":[44],"diagnosis,":[45,227],"with":[46,73,93,199],"biopsy":[47],"persisting":[48],"gold":[51],"standard":[52],"despite":[53],"its":[54],"substantial":[55],"costs":[56],"risks.":[58],"A":[59],"critical":[60],"bottleneck":[61],"for":[62,76,141,224],"endoscopic":[64,100],"CADx/e":[65,142],"lack":[69],"well-annotated":[71],"datasets":[72,140],"sufficient":[74],"variability":[75],"real-world":[77,242],"generalization.":[78],"This":[79,212],"study":[80],"introduces":[81],"a":[82,87,94,152,229],"novel":[83],"approach":[84,133],"that":[85,126],"exploits":[86],"Latent":[88],"Diffusion":[89],"Model":[90],"(LDM)":[91],"coupled":[92],"ControlNet":[95],"adapter":[96],"to":[97,117,137,202,217,231],"generate":[98],"laryngeal":[99,169,225],"image-annotation":[101],"pairs,":[102],"guided":[103],"by":[104,112,171,194],"clinical":[105],"observations.":[106],"The":[107,131],"method":[108],"addresses":[109],"data":[110,163,232,240],"scarcity":[111,233],"conditioning":[113],"diffusion":[115],"process":[116,147],"produce":[118],"realistic,":[119],"high-quality,":[120],"clinically":[122],"relevant":[123],"image":[124],"features":[125],"capture":[127],"diverse":[128],"anatomical":[129],"conditions.":[130],"proposed":[132],"can":[134],"be":[135],"leveraged":[136],"expand":[138],"training":[139],"models,":[143],"empowering":[144],"laryngology.":[149],"Indeed,":[150],"during":[151],"downstream":[153],"task":[154],"detection,":[156],"addition":[158],"only":[160],"10%":[161],"synthetic":[162,208,239],"improved":[164],"rate":[167,203],"9%":[172],"when":[173],"model":[175],"was":[176,192],"internally":[177],"tested":[178],"22.1%":[180],"out-of-domain":[182],"external":[183],"data.":[184],"Additionally,":[185],"realism":[187],"generated":[190],"images":[191],"evaluated":[193],"asking":[195],"5":[196],"expert":[197],"otorhinolaryngologists":[198],"varying":[200],"expertise":[201],"confidence":[205],"distinguishing":[207],"from":[209],"real":[210],"images.":[211],"work":[213],"has":[214],"potential":[216],"accelerate":[218],"development":[220],"automated":[222],"tools":[223],"disease":[226],"offering":[228],"solution":[230],"demonstrating":[235],"applicability":[237],"scenarios.":[243]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-15T00:00:00"}
