{"id":"https://openalex.org/W7164766496","doi":"https://doi.org/10.3390/make8060164","title":"Do Foundation Models Truly Outperform Domain-Specific Models? Evidence from Digital Pathology","display_name":"Do Foundation Models Truly Outperform Domain-Specific Models? Evidence from Digital Pathology","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164766496","doi":"https://doi.org/10.3390/make8060164"},"language":"en","primary_location":{"id":"doi:10.3390/make8060164","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8060164","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/make8060164","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045733261","display_name":"Chaima Ben Rabah","orcid":"https://orcid.org/0000-0003-4153-3287"},"institutions":[{"id":"https://openalex.org/I4210152471","display_name":"Weill Cornell Medical College in Qatar","ror":"https://ror.org/05v5hg569","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210152471"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Chaima Ben Rabah","raw_affiliation_strings":["AI Innovation Lab, Weill Cornell Medicine, Doha P.O. Box 24144, Qatar"],"raw_orcid":"https://orcid.org/0000-0003-4153-3287","affiliations":[{"raw_affiliation_string":"AI Innovation Lab, Weill Cornell Medicine, Doha P.O. Box 24144, Qatar","institution_ids":["https://openalex.org/I4210152471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086475627","display_name":"Ahmed Serag","orcid":"https://orcid.org/0000-0002-4145-5509"},"institutions":[{"id":"https://openalex.org/I4210152471","display_name":"Weill Cornell Medical College in Qatar","ror":"https://ror.org/05v5hg569","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210152471"]}],"countries":["QA"],"is_corresponding":true,"raw_author_name":"Ahmed Serag","raw_affiliation_strings":["AI Innovation Lab, Weill Cornell Medicine, Doha P.O. Box 24144, Qatar"],"raw_orcid":"https://orcid.org/0000-0002-4145-5509","affiliations":[{"raw_affiliation_string":"AI Innovation Lab, Weill Cornell Medicine, Doha P.O. Box 24144, Qatar","institution_ids":["https://openalex.org/I4210152471"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045733261","https://openalex.org/A5086475627"],"corresponding_institution_ids":["https://openalex.org/I4210152471"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1559},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1559},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75661843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"6","first_page":"164","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.8300999999046326,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.8300999999046326,"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":0.019899999722838402,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.01600000075995922,"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/prostate-cancer","display_name":"Prostate cancer","score":0.5552999973297119},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5224000215530396},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.45339998602867126},{"id":"https://openalex.org/keywords/generalist-and-specialist-species","display_name":"Generalist and specialist species","score":0.438400000333786},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5881999731063843},{"id":"https://openalex.org/C2780192828","wikidata":"https://www.wikidata.org/wiki/Q181257","display_name":"Prostate cancer","level":3,"score":0.5552999973297119},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5250999927520752},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116000175476074},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48179998993873596},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C45371612","wikidata":"https://www.wikidata.org/wiki/Q3058587","display_name":"Generalist and specialist species","level":3,"score":0.438400000333786},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C530470458","wikidata":"https://www.wikidata.org/wiki/Q128581","display_name":"Breast cancer","level":3,"score":0.37229999899864197},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.36629998683929443},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.3587000072002411},{"id":"https://openalex.org/C2776235491","wikidata":"https://www.wikidata.org/wiki/Q9625","display_name":"Prostate","level":3,"score":0.34389999508857727},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.33799999952316284},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26669999957084656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make8060164","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8060164","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:297e5752d2544ed28d812a3e4f771754","is_oa":false,"landing_page_url":"https://doaj.org/article/297e5752d2544ed28d812a3e4f771754","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":"Machine Learning and Knowledge Extraction, Vol 8, Iss 6, p 164 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make8060164","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8060164","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"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":{"Foundation":[0],"models":[1,134],"(FMs)":[2],"are":[3,218,262],"increasingly":[4],"proposed":[5],"as":[6,236],"general-purpose":[7,49],"solutions":[8],"for":[9,25,142,183,223,239],"computational":[10],"pathology,":[11],"with":[12,34],"the":[13,23,99,121,151,157,169,231,246],"potential":[14],"to":[15,96,101,266],"simplify":[16],"clinical":[17,44,226,255],"artificial":[18],"intelligence":[19],"deployment":[20],"by":[21],"reducing":[22],"need":[24],"task-specific":[26],"architectures.":[27],"However,":[28],"their":[29],"reliability":[30],"across":[31,56,107,173],"cancer":[32,111,149,188],"domains":[33],"distinct":[35],"morphological":[36],"characteristics":[37],"remains":[38],"unclear,":[39],"limiting":[40],"confidence":[41],"in":[42,127,208],"real-world":[43],"use.":[45,227],"We":[46],"benchmarked":[47],"seven":[48],"pathology":[50,260],"FMs":[51,55,217,235,261],"and":[52,69,76,89,109,211,257],"three":[53,61],"domain-specific":[54],"eleven":[57],"patch-level":[58,242],"datasets":[59],"spanning":[60],"clinically":[62],"relevant":[63],"domains:":[64],"pediatric":[65,84],"hematology,":[66,120],"prostate":[67,87,148,210],"cancer,":[68,71,88,92,166,213],"breast":[70,91,165,187,212],"using":[72],"both":[73,209],"linear":[74],"probing":[75],"last-layer":[77],"fine-tuning":[78],"adaptation":[79],"strategies.":[80],"By":[81],"jointly":[82],"evaluating":[83],"leukemia,":[85],"male-predominant":[86],"female-predominant":[90],"this":[93],"study":[94],"is,":[95],"our":[97],"knowledge,":[98],"first":[100],"explicitly":[102],"examine":[103],"specialist-versus-generalist":[104,196],"FM":[105,123,153,180,192],"behavior":[106],"age-":[108],"sex-stratified":[110],"populations.":[112],"Performance":[113],"differences":[114],"were":[115],"strongly":[116],"domain":[117],"dependent.":[118],"In":[119,147,164],"specialist":[122,158,267],"DINOBloom":[124],"matched":[125],"and,":[126],"several":[128],"datasets,":[129],"marginally":[130],"exceeded":[131],"leading":[132],"generalist":[133,152,234],"(AUC":[135,160],"0.990\u20130.999":[136],"vs.":[137,162],"GigaPath":[138],"0.981\u20131.000),":[139],"suggesting":[140],"advantages":[141],"highly":[143],"distinctive":[144],"cellular":[145],"morphology.":[146],"grading,":[150],"UNI2-h":[154,167],"consistently":[155],"outperformed":[156],"HistoEncoder":[159],"0.956\u20130.977":[161],"0.908\u20130.964).":[163],"achieved":[168],"best":[170],"overall":[171],"performance":[172,203,251],"all":[174],"tasks.":[175],"No":[176],"publicly":[177],"available":[178],"breast-cancer-specific":[179],"currently":[181],"exists":[182],"direct":[184],"comparison;":[185],"therefore,":[186],"results":[189],"characterize":[190],"general":[191],"transferability":[193],"rather":[194],"than":[195],"differences.":[197],"Importantly,":[198],"cross-dataset":[199],"experiments":[200],"revealed":[201],"substantial":[202],"degradation":[204],"under":[205],"dataset":[206],"shift":[207],"indicating":[214],"that":[215,248,259],"current":[216],"not":[219,263],"yet":[220],"robust":[221],"enough":[222],"heterogeneous":[224],"multi-site":[225],"These":[228],"findings":[229],"support":[230],"use":[232],"of":[233],"efficient":[237],"backbones":[238],"well-characterized":[240],"single-site,":[241],"tasks,":[243],"while":[244],"challenging":[245],"assumption":[247],"high":[249],"benchmark":[250],"necessarily":[252],"reflects":[253],"true":[254],"readiness":[256],"demonstrating":[258],"uniformly":[264],"superior":[265],"models.":[268]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-06-15T00:00:00"}