{"id":"https://openalex.org/W7158672764","doi":"https://doi.org/10.1038/s41746-026-02676-5","title":"Key concept learning for medical vision language model with reasoning capabilities","display_name":"Key concept learning for medical vision language model with reasoning capabilities","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7158672764","doi":"https://doi.org/10.1038/s41746-026-02676-5","pmid":"https://pubmed.ncbi.nlm.nih.gov/42056236"},"language":"en","primary_location":{"id":"doi:10.1038/s41746-026-02676-5","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-026-02676-5","pdf_url":"https://www.nature.com/articles/s41746-026-02676-5_reference.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"npj Digital Medicine","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.nature.com/articles/s41746-026-02676-5_reference.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108048691","display_name":"Wei Lou","orcid":"https://orcid.org/0000-0001-6538-2407"},"institutions":[{"id":"https://openalex.org/I135237710","display_name":"Zhejiang Normal University","ror":"https://ror.org/01vevwk45","country_code":"CN","type":"education","lineage":["https://openalex.org/I135237710"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lou","raw_affiliation_strings":["College of Mathematical Medicine, Zhejiang Normal University, Jinhua, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mathematical Medicine, Zhejiang Normal University, Jinhua, China","institution_ids":["https://openalex.org/I135237710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134922080","display_name":"Yue Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yue Wu","raw_affiliation_strings":["School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134876215","display_name":"Pusheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pusheng Xu","raw_affiliation_strings":["School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134882573","display_name":"Weiyi Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Weiyi Zhang","raw_affiliation_strings":["School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134881684","display_name":"Xiaolan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaolan Chen","raw_affiliation_strings":["School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020501435","display_name":"Jiancheng Yang","orcid":"https://orcid.org/0000-0003-4455-7145"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jiancheng Yang","raw_affiliation_strings":["Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134891056","display_name":"Mingguang He","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I2799346673","display_name":"Hong Kong Eye Hospital","ror":"https://ror.org/03fttgk04","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I1294586568","https://openalex.org/I2799346673"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Mingguang He","raw_affiliation_strings":["Centre for Eye and Vision Research (CEVR), Hong Kong, China. mingguang.he@polyu.edu.hk","Research Centre for SHARP Vision (RCSV), The Hong Kong Polytechnic University, Hong Kong, China. mingguang.he@polyu.edu.hk","School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China. mingguang.he@polyu.edu.hk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Eye and Vision Research (CEVR), Hong Kong, China. mingguang.he@polyu.edu.hk","institution_ids":["https://openalex.org/I2799346673"]},{"raw_affiliation_string":"Research Centre for SHARP Vision (RCSV), The Hong Kong Polytechnic University, Hong Kong, China. mingguang.he@polyu.edu.hk","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China. mingguang.he@polyu.edu.hk","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134888357","display_name":"Danli Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]},{"id":"https://openalex.org/I4210096587","display_name":"Vision Eye Institute","ror":"https://ror.org/00b0t9z66","country_code":"AU","type":"education","lineage":["https://openalex.org/I4210096587"]}],"countries":["AU","HK"],"is_corresponding":true,"raw_author_name":"Danli Shi","raw_affiliation_strings":["Centre for Eye and Vision Research (CEVR), Hong Kong, China. danli.shi@polyu.edu.hk","Research Centre for SHARP Vision (RCSV), The Hong Kong Polytechnic University, Hong Kong, China. danli.shi@polyu.edu.hk","School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China. danli.shi@polyu.edu.hk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Eye and Vision Research (CEVR), Hong Kong, China. danli.shi@polyu.edu.hk","institution_ids":["https://openalex.org/I4210096587"]},{"raw_affiliation_string":"Research Centre for SHARP Vision (RCSV), The Hong Kong Polytechnic University, Hong Kong, China. danli.shi@polyu.edu.hk","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"School of Optometry, The Hong Kong Polytechnic University, Hong Kong, China. danli.shi@polyu.edu.hk","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5134888357","https://openalex.org/A5134891056"],"corresponding_institution_ids":["https://openalex.org/I14243506","https://openalex.org/I2799346673","https://openalex.org/I4210096587"],"apc_list":{"value":3590,"currency":"USD","value_usd":3590},"apc_paid":{"value":3590,"currency":"USD","value_usd":3590},"fwci":7.1155,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97006145,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"9","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9458000063896179,"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":0.9458000063896179,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.011699999682605267,"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"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.006200000178068876,"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/key","display_name":"Key (lock)","score":0.7045000195503235},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.6358000040054321},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.447299987077713},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.40459999442100525},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3377000093460083},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.32190001010894775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138000130653381},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7045000195503235},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5472000241279602},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32710000872612},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C48164120","wikidata":"https://www.wikidata.org/wiki/Q4491893","display_name":"Concept learning","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1038/s41746-026-02676-5","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-026-02676-5","pdf_url":"https://www.nature.com/articles/s41746-026-02676-5_reference.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"npj Digital Medicine","raw_type":"journal-article"},{"id":"pmid:42056236","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42056236","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"NPJ digital medicine","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:8fdb86d312e54571a56db485013ed149","is_oa":false,"landing_page_url":"https://doaj.org/article/8fdb86d312e54571a56db485013ed149","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"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":"npj Digital Medicine, Vol 9, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13338256","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13338256/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"NPJ Digit Med","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1038/s41746-026-02676-5","is_oa":true,"landing_page_url":"https://doi.org/10.1038/s41746-026-02676-5","pdf_url":"https://www.nature.com/articles/s41746-026-02676-5_reference.pdf","source":{"id":"https://openalex.org/S4210195431","display_name":"npj Digital Medicine","issn_l":"2398-6352","issn":["2398-6352"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319908","host_organization_name":"Nature Portfolio","host_organization_lineage":["https://openalex.org/P4310319908","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Nature Portfolio","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"npj Digital Medicine","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4226875603199005,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7158672764.pdf","grobid_xml":"https://content.openalex.org/works/W7158672764.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"medical":[1,36,43,65,99,144],"vision-language":[2],"models":[3],"(VLMs)":[4],"typically":[5],"demands":[6],"millions":[7],"of":[8,109],"image-text":[9],"pairs":[10],"to":[11,53,72,140],"achieve":[12],"versatility":[13],"and":[14,68,93],"reasoning,":[15],"posing":[16],"significant":[17],"challenges":[18],"in":[19],"data":[20],"acquisition.":[21],"We":[22],"propose":[23],"ConceptVLM,":[24],"a":[25,57,63,137],"novel":[26],"data-efficient":[27],"fine-tuning":[28,83],"paradigm":[29],"that":[30],"transforms":[31],"general-domain":[32],"VLMs":[33],"into":[34],"specialized":[35],"ones":[37],"with":[38],"minimal":[39],"labeled":[40],"data,":[41,113],"integrating":[42],"knowledge":[44],"without":[45],"disrupting":[46],"the":[47,74,89,110,125],"model's":[48,75,90],"existing":[49],"general":[50],"capabilities.":[51],"Central":[52],"our":[54],"approach":[55],"is":[56],"key":[58,133],"concept-aware":[59],"training":[60,112],"strategy,":[61],"building":[62],"structured":[64],"concept":[66],"dictionary":[67],"employing":[69],"masked":[70],"attention":[71],"guide":[73],"focus":[76],"toward":[77],"essential":[78],"clinical":[79],"concepts.":[80],"This":[81],"focused":[82],"enhances":[84],"domain-specific":[85],"comprehension":[86],"while":[87],"preserving":[88],"reasoning":[91],"abilities":[92],"response":[94],"diversity.":[95],"Experiments":[96],"across":[97],"multimodal":[98],"benchmarks":[100],"show":[101],"ConceptVLM":[102],"achieves":[103],"state-of-the-art":[104],"results":[105],"using":[106],"only":[107],"1%":[108],"original":[111],"outperforming":[114],"traditional":[115],"methods":[116],"reliant":[117],"on":[118,128],"large-scale":[119],"QA":[120],"datasets.":[121],"These":[122],"findings":[123],"challenge":[124],"prevailing":[126],"reliance":[127],"extensive":[129],"annotated":[130],"corpora,":[131],"demonstrating":[132],"concept-guided":[134],"tuning":[135],"as":[136],"viable":[138],"path":[139],"developing":[141],"cognitively":[142],"capable":[143],"VLMs.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2026-05-01T00:00:00"}
