{"id":"https://openalex.org/W4309953923","doi":"https://doi.org/10.48550/arxiv.2211.12737","title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","display_name":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","publication_year":2022,"publication_date":"2022-11-23","ids":{"openalex":"https://openalex.org/W4309953923","doi":"https://doi.org/10.48550/arxiv.2211.12737"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.12737","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.12737","pdf_url":"https://arxiv.org/pdf/2211.12737","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2211.12737","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085761422","display_name":"Pierre Chambon","orcid":"https://orcid.org/0000-0002-7861-6046"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chambon, Pierre","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111185084","display_name":"Christian Bluethgen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bluethgen, Christian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016013231","display_name":"Jean-Benoit Delbrouck","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Delbrouck, Jean-Benoit","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078961422","display_name":"Rogier Van der Sluijs","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Van der Sluijs, Rogier","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003001142","display_name":"Ma\u0142gorzata Po\u0142acin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Po\u0142acin, Ma\u0142gorzata","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019424010","display_name":"Juan Manuel Zambrano Chaves","orcid":"https://orcid.org/0000-0002-7274-8072"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaves, Juan Manuel Zambrano","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028004251","display_name":"Tanishq Mathew Abraham","orcid":"https://orcid.org/0000-0002-9590-391X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abraham, Tanishq Mathew","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051278552","display_name":"Shivanshu Purohit","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Purohit, Shivanshu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087710258","display_name":"Curtis P. Langlotz","orcid":"https://orcid.org/0000-0002-8972-8051"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Langlotz, Curtis P.","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064829377","display_name":"Akshay Chaudhari","orcid":"https://orcid.org/0000-0002-3667-6796"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaudhari, Akshay","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5085761422"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":56,"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/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9847999811172485,"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/T10862","display_name":"AI in cancer detection","score":0.9768000245094299,"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/computer-science","display_name":"Computer science","score":0.7598932981491089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5724884271621704},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5378363132476807},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.5209111571311951},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5055265426635742},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47427424788475037},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.4558088481426239},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4555971622467041},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.39743152260780334},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.396567165851593},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32487475872039795},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.30744311213493347},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07910484075546265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598932981491089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5724884271621704},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5378363132476807},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5209111571311951},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5055265426635742},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47427424788475037},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.4558088481426239},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4555971622467041},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39743152260780334},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.396567165851593},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32487475872039795},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30744311213493347},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07910484075546265},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.12737","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.12737","pdf_url":"https://arxiv.org/pdf/2211.12737","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2211.12737","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.12737","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:2211.12737","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.12737","pdf_url":"https://arxiv.org/pdf/2211.12737","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Multimodal":[0],"models":[1,50,69],"trained":[2,51,222,234],"on":[3,52,110,137,201,224,235],"large":[4,99],"natural":[5,24,53],"image-text":[6,54],"pair":[7],"datasets":[8],"have":[9],"exhibited":[10],"astounding":[11],"abilities":[12],"in":[13,35,252],"generating":[14],"high-quality":[15],"images.":[16],"Medical":[17],"imaging":[18,68,87],"data":[19,37,211],"is":[20,169],"fundamentally":[21],"different":[22],"to":[23,30,59,62,96,130,171,186],"images,":[25,178,228],"and":[26,119,150,154,179,206,226,229,255],"the":[27,63,80,98,127,142,165,181,253],"language":[28],"used":[29],"succinctly":[31],"capture":[32],"relevant":[33],"details":[34],"medical":[36,64,72,86],"uses":[38],"a":[39,94,105,111,187,202,210,216,220,230,236],"different,":[40],"narrow":[41],"but":[42,238],"semantically":[43],"rich,":[44],"domain-specific":[45],"vocabulary.":[46],"Not":[47],"surprisingly,":[48],"multi-modal":[49],"pairs":[55],"do":[56],"not":[57],"tend":[58],"generalize":[60],"well":[61],"domain.":[65],"Developing":[66],"generative":[67],"faithfully":[70],"representing":[71],"concepts":[73],"while":[74],"providing":[75],"compositional":[76],"diversity":[77],"could":[78],"mitigate":[79],"existing":[81],"paucity":[82],"of":[83,113,219,261],"high-quality,":[84],"annotated":[85],"datasets.":[88],"In":[89],"this":[90,199,247],"work,":[91],"we":[92,214,244],"develop":[93],"strategy":[95],"overcome":[97],"natural-medical":[100],"distributional":[101],"shift":[102],"by":[103,157,190,266],"adapting":[104],"pre-trained":[106],"latent":[107],"diffusion":[108],"model":[109,143,167,200],"corpus":[112],"publicly":[114],"available":[115],"chest":[116],"x-rays":[117],"(CXR)":[118],"their":[120],"corresponding":[121],"radiology":[122],"(text)":[123],"reports.":[124],"We":[125,140,161],"investigate":[126],"model's":[128],"ability":[129],"generate":[131],"high-fidelity,":[132],"diverse":[133,175],"synthetic":[134,176,225,240],"CXR":[135,177],"conditioned":[136],"text":[138,193],"prompts.":[139],"assess":[141],"outputs":[144],"quantitatively":[145],"using":[146,191,207],"image":[147,152],"quality":[148,153],"metrics,":[149],"evaluate":[151],"text-image":[155],"alignment":[156],"human":[158],"domain":[159],"experts.":[160],"present":[162],"evidence":[163],"that":[164,180,246],"resulting":[166],"(RoentGen)":[168],"able":[170],"create":[172],"visually":[173],"convincing,":[174],"output":[182],"can":[183,256],"be":[184],"controlled":[185],"new":[188],"extent":[189],"free-form":[192],"prompts":[194],"including":[195],"radiology-specific":[196],"language.":[197],"Fine-tuning":[198],"fixed":[203],"training":[204,241],"set":[205],"it":[208],"as":[209],"augmentation":[212],"method,":[213],"measure":[215],"5%":[217],"improvement":[218,232],"classifier":[221],"jointly":[223],"real":[227],"3%":[231],"when":[233],"larger":[237],"purely":[239],"set.":[242],"Finally,":[243],"observe":[245],"fine-tuning":[248],"distills":[249],"in-domain":[250],"knowledge":[251],"text-encoder":[254],"improve":[257],"its":[258],"representation":[259],"capabilities":[260],"certain":[262],"diseases":[263],"like":[264],"pneumothorax":[265],"25%.":[267]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":16}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}