{"id":"https://openalex.org/W4416191178","doi":"https://doi.org/10.1109/wacv61042.2026.00278","title":"Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation","display_name":"Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4416191178","doi":"https://doi.org/10.1109/wacv61042.2026.00278"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.08402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113010931","display_name":"Difei Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Difei Gu","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061627386","display_name":"Yunhe Gao","orcid":"https://orcid.org/0000-0002-1559-5532"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yunhe Gao","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102944058","display_name":"Mu Zhou","orcid":"https://orcid.org/0000-0001-5072-5630"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mu Zhou","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064437234","display_name":"Dimitris Metaxas","orcid":"https://orcid.org/0000-0001-7142-7640"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dimitris Metaxas","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210096112"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2838","last_page":"2847"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.47589999437332153,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.47589999437332153,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.10140000283718109,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.0763000026345253,"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/interpretation","display_name":"Interpretation (philosophy)","score":0.6365000009536743},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.6136000156402588},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5669000148773193},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4959999918937683},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.46630001068115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676800012588501},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.6136000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702999830245972},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4959999918937683},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4058000147342682},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.40470001101493835},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2985722590","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical knowledge","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C206497026","wikidata":"https://www.wikidata.org/wiki/Q1753883","display_name":"SNOMED CT","level":3,"score":0.25589999556541443}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00278","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.08402","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08402","pdf_url":"https://arxiv.org/pdf/2511.08402","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,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.08402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.08402","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,"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2511.08402","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.08402","pdf_url":"https://arxiv.org/pdf/2511.08402","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,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4416191178.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"disease":[1,43,117],"interpretation":[2,164],"from":[3,65,91],"radiology":[4],"remains":[5],"challenging":[6],"due":[7],"to":[8,86,114],"imaging":[9],"heterogeneity.":[10],"Achieving":[11],"expert-level":[12,162],"diagnostic":[13],"decisions":[14],"requires":[15],"integration":[16],"of":[17,61,134],"subtle":[18],"image":[19,37,138],"features":[20,90],"with":[21,100],"clinical":[22,163],"knowledge.":[23,150],"Yet":[24],"major":[25],"vision-language":[26,74],"models":[27],"(VLMs)":[28],"treat":[29],"images":[30,47],"as":[31,58],"holistic":[32],"entities":[33],"and":[34,54,126,148],"overlook":[35],"fine-grained":[36,144],"details":[38],"that":[39,76,142],"are":[40,98],"vital":[41],"for":[42,103],"diagnosis.":[44],"Clinicians":[45],"analyze":[46],"by":[48],"utilizing":[49],"their":[50],"prior":[51],"medical":[52,93,112],"knowledge":[53,102],"identify":[55],"anatomical":[56,89,147],"structures":[57],"important":[59],"region":[60],"interests":[62],"(ROIs).":[63],"Inspired":[64],"this":[66],"human-centric":[67],"workflow,":[68],"we":[69,81],"introduce":[70],"Anatomy-VLM,":[71],"a":[72,83],"fine-grained,":[73],"model":[75,84,108],"incorporates":[77],"multi-scale":[78,111],"information.":[79],"First,":[80],"design":[82],"encoder":[85,109,154],"localize":[87],"key":[88],"entire":[92],"images.":[94],"Second,":[95],"these":[96],"regions":[97],"enriched":[99],"structured":[101],"contextually-aware":[104],"interpretation.":[105],"Finally,":[106],"the":[107,132,152],"aligns":[110],"information":[113],"generate":[115],"clinically-interpretable":[116],"prediction.":[118],"Anatomy-VLM":[119,135],"achieves":[120],"outstanding":[121],"performance":[122,133],"on":[123,136],"both":[124],"in-":[125],"out-of-distribution":[127],"datasets.":[128],"We":[129],"also":[130],"validate":[131],"downstream":[137],"segmentation":[139],"tasks,":[140],"suggesting":[141],"its":[143,160],"alignment":[145],"captures":[146],"pathology-related":[149],"Furthermore,":[151],"Anatomy-VLM\u2019s":[153],"facilitates":[155],"zero-shot":[156],"anatomy-wise":[157],"interpretation,":[158],"providing":[159],"strong":[161],"capabilities.":[165]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-11-13T00:00:00"}