{"id":"https://openalex.org/W4304701343","doi":"https://doi.org/10.48550/arxiv.2210.04133","title":"Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains","display_name":"Adapting Pretrained Vision-Language Foundational Models to Medical Imaging Domains","publication_year":2022,"publication_date":"2022-10-09","ids":{"openalex":"https://openalex.org/W4304701343","doi":"https://doi.org/10.48550/arxiv.2210.04133"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.04133","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04133","pdf_url":"https://arxiv.org/pdf/2210.04133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.04133","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137275383","display_name":"Pierre Chambon","orcid":"https://orcid.org/0000-0001-7394-3729","observed_orcids":["https://orcid.org/0000-0001-7394-3729"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chambon, Pierre","raw_affiliation_strings":["Center for Artificial Intelligence in Medicine and Imaging Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence in Medicine and Imaging Stanford University","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089676369","display_name":"Christian Bl\u00fcthgen","orcid":"https://orcid.org/0000-0001-7321-5676","observed_orcids":["https://orcid.org/0000-0001-7321-5676"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bluethgen, Christian","raw_affiliation_strings":["Center for Artificial Intelligence in Medicine and Imaging Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence in Medicine and Imaging Stanford University","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087710258","display_name":"Curtis P. Langlotz","orcid":"https://orcid.org/0000-0002-8972-8051","observed_orcids":["https://orcid.org/0000-0002-8972-8051"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Langlotz, Curtis P.","raw_affiliation_strings":["Center for Artificial Intelligence in Medicine and Imaging Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence in Medicine and Imaging Stanford University","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064829377","display_name":"Akshay Sanjay Chaudhari","orcid":"https://orcid.org/0000-0002-3667-6796","observed_orcids":["https://orcid.org/0000-0002-3667-6796"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chaudhari, Akshay","raw_affiliation_strings":["Center for Artificial Intelligence in Medicine and Imaging Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Artificial Intelligence in Medicine and Imaging Stanford University","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":78,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9286999702453613,"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":0.9286999702453613,"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":0.050200000405311584,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.018799999728798866,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/medical-image-synthesis","display_name":"medical image synthesis","score":0.6740000247955322},{"id":"https://openalex.org/keywords/stable-diffusion","display_name":"Stable Diffusion","score":0.8740000128746033},{"id":"https://openalex.org/keywords/vision-language-foundation-models","display_name":"vision-language foundation models","score":0.8460000157356262},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"domain adaptation","score":0.8220000267028809},{"id":"https://openalex.org/keywords/diagnostic-imaging","display_name":"diagnostic imaging","score":0.4309999942779541},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"anomaly detection","score":0.5450000166893005},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.6399999856948853},{"id":"https://openalex.org/keywords/variational-autoencoder","display_name":"variational autoencoder","score":0.9279999732971191},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597595453262329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6897943615913391},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.670341968536377},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5738778114318848},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5730469226837158},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5364291071891785},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5173296332359314},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.451369971036911},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4301733076572418},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3925062417984009},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3849724531173706},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34409210085868835},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.04133","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04133","pdf_url":"https://arxiv.org/pdf/2210.04133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.04133","doi":"https://doi.org/10.48550/arxiv.2210.04133","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.04133","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.04133","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.04133","pdf_url":"https://arxiv.org/pdf/2210.04133","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.46810001134872437,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3018715022","display_name":null,"funder_award_id":"75N92020C00021","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"},{"id":"https://openalex.org/G8842961228","display_name":null,"funder_award_id":"75N92020C00008","funder_id":"https://openalex.org/F4320337363","funder_display_name":"National Institute of Biomedical Imaging and Bioengineering"}],"funders":[{"id":"https://openalex.org/F4320324346","display_name":"Schweizerische Gesellschaft f\u00fcr Radiologie","ror":"https://ror.org/01w0j5472"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337363","display_name":"National Institute of Biomedical Imaging and Bioengineering","ror":"https://ror.org/00372qc85"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304701343.pdf","grobid_xml":"https://content.openalex.org/works/W4304701343.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4309953923","https://openalex.org/W7167722134","https://openalex.org/W4390115208","https://openalex.org/W4401888965","https://openalex.org/W7165479507","https://openalex.org/W7161124286","https://openalex.org/W4360891532","https://openalex.org/W4414055181","https://openalex.org/W4416046300","https://openalex.org/W4386829267"],"abstract_inverted_index":{"Multi-modal":[0],"foundation":[1,85],"models":[2,23,52,86],"are":[3],"typically":[4,31],"trained":[5,188],"on":[6,175,185],"millions":[7],"of":[8,10,66,82,110,135,153],"pairs":[9],"natural":[11,48],"images":[12,40,55,101],"and":[13,77,120,143,166],"text":[14,155],"captions,":[15],"frequently":[16],"obtained":[17],"through":[18],"web-crawling":[19],"approaches.":[20],"Although":[21],"such":[22,37],"depict":[24,58],"excellent":[25],"generative":[26,51],"capabilities,":[27],"they":[28],"do":[29],"not":[30],"generalize":[32],"well":[33],"to":[34,47,75,87,97,123,127,170,189],"specific":[35,100],"domains":[36],"as":[38],"medical":[39,54,88,104,129],"that":[41,56,147],"have":[42],"fundamentally":[43],"shifted":[44],"distributions":[45],"compared":[46],"images.":[49,130],"Building":[50],"for":[53,91],"faithfully":[57],"clinical":[59,151],"context":[60],"may":[61],"help":[62],"alleviate":[63],"the":[64,79,93,108,111,118,121,125,133,150,162,191],"paucity":[65],"healthcare":[67],"datasets.":[68],"Thus,":[69],"in":[70,103],"this":[71],"study,":[72],"we":[73],"seek":[74],"research":[76],"expand":[78],"representational":[80],"capabilities":[81],"large":[83],"pretrained":[84],"concepts,":[89],"specifically":[90],"leveraging":[92],"Stable":[94,112],"Diffusion":[95,113],"model":[96,126,159],"generate":[98,128],"domain":[99],"found":[102],"imaging.":[105],"We":[106,131],"explore":[107],"sub-components":[109],"pipeline":[114],"(the":[115],"variational":[116],"autoencoder,":[117],"U-Net":[119],"text-encoder)":[122],"fine-tune":[124],"benchmark":[132],"efficacy":[134],"these":[136],"efforts":[137],"using":[138],"quantitative":[139],"image":[140],"quality":[141],"metrics":[142],"qualitative":[144],"radiologist-driven":[145],"evaluations":[146],"accurately":[148],"represent":[149],"content":[152],"conditional":[154],"prompts.":[156],"Our":[157],"best-performing":[158],"improves":[160],"upon":[161],"stable":[163],"diffusion":[164],"baseline":[165],"can":[167],"be":[168],"conditioned":[169],"insert":[171],"a":[172,176,182,186],"realistic-looking":[173],"abnormality":[174],"synthetic":[177],"radiology":[178],"image,":[179],"while":[180],"maintaining":[181],"95%":[183],"accuracy":[184],"classifier":[187],"detect":[190],"abnormality.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":24},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":23}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2022-10-12T00:00:00"}