{"id":"https://openalex.org/W7160842752","doi":"https://doi.org/10.48550/arxiv.2605.07749","title":"Benchmarking Foundation Models for Renal Lesion Stratification in CT","display_name":"Benchmarking Foundation Models for Renal Lesion Stratification in CT","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160842752","doi":"https://doi.org/10.48550/arxiv.2605.07749"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07749","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.07749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135834299","display_name":"Hartmut H\u00e4ntze","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e4ntze, Hartmut","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057300818","display_name":"Sarah de Boer","orcid":"https://orcid.org/0000-0001-5184-4340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"de Boer, Sarah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042663865","display_name":"Myrthe Buser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buser, Myrthe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135905690","display_name":"Alessa Hering","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hering, Alessa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135866893","display_name":"Bram van Ginneken","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van Ginneken, Bram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074955220","display_name":"M Prokop","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prokop, Mathias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051273513","display_name":"Jawed Nawabi","orcid":"https://orcid.org/0000-0002-1137-0643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nawabi, Jawed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135831274","display_name":"Sebastian Ziegelmayer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziegelmayer, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125652985","display_name":"Lisa Adams","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adams, Lisa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135889548","display_name":"Keno Bressem","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bressem, Keno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10449","display_name":"Renal cell carcinoma treatment","score":0.782800018787384,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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/T10449","display_name":"Renal cell carcinoma treatment","score":0.782800018787384,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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":0.05480000004172325,"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":0.030400000512599945,"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/radiomics","display_name":"Radiomics","score":0.6956999897956848},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6169000267982483},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4927000105381012},{"id":"https://openalex.org/keywords/lesion","display_name":"Lesion","score":0.48500001430511475},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4691999852657318},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.42890000343322754},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.35749998688697815},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.3499999940395355}],"concepts":[{"id":"https://openalex.org/C2778559731","wikidata":"https://www.wikidata.org/wiki/Q23808793","display_name":"Radiomics","level":2,"score":0.6956999897956848},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.597599983215332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5329999923706055},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C2781156865","wikidata":"https://www.wikidata.org/wiki/Q827023","display_name":"Lesion","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4343000054359436},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.42890000343322754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36079999804496765},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C2777472916","wikidata":"https://www.wikidata.org/wiki/Q1164529","display_name":"Renal cell carcinoma","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C194051981","wikidata":"https://www.wikidata.org/wiki/Q1337691","display_name":"Economic shortage","level":3,"score":0.29010000824928284},{"id":"https://openalex.org/C3020404979","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk stratification","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C190892606","wikidata":"https://www.wikidata.org/wiki/Q3512464","display_name":"Radiological weapon","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07749","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07749","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07749","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5486984848976135,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/16","score":0.42451223731040955,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,124],"rapid":[1],"proliferation":[2],"of":[3,57,110,120,173],"open-source":[4],"medical":[5,59,206],"foundation":[6],"models":[7,212],"(FMs)":[8],"raises":[9],"a":[10,33,55,83,92,97,107,154],"practical":[11],"question:":[12],"how":[13],"well":[14],"do":[15,186],"their":[16,201],"pre-trained":[17],"representations":[18],"transfer":[19],"to":[20],"clinically":[21],"relevant":[22],"but":[23],"data-scarce":[24,204],"classification":[25],"tasks?":[26],"Particularly":[27],"in":[28,203],"CT-based":[29],"renal":[30,76,214],"lesion":[31,215],"classification,":[32],"push":[34],"toward":[35],"greater":[36],"generalizability":[37],"would":[38],"be":[39],"meaningful,":[40],"as":[41,219],"the":[42,140,160,190,220],"field":[43],"is":[44],"constrained":[45],"by":[46],"inherently":[47],"limited":[48],"training":[49],"data.":[50],"We":[51],"addressed":[52],"this":[53,62],"through":[54],"benchmark":[56],"three":[58],"FMs":[60,207],"on":[61,106,115,153],"specific":[63],"task.":[64],"This":[65,179],"six-class":[66],"problem":[67],"spans":[68],"common":[69],"entities":[70],"like":[71],"cysts":[72],"and":[73,96,113,193],"clear":[74],"cell":[75,77],"carcinoma,":[78],"alongside":[79],"rare":[80],"subtypes.":[81],"Using":[82],"frozen":[84],"feature-probing":[85],"protocol,":[86],"we":[87],"compared":[88],"FM":[89,135,184],"embeddings":[90,185],"against":[91],"handcrafted":[93],"radiomics":[94,162,218],"classifier":[95],"3D":[98],"ResNet-50":[99],"trained":[100,105],"from":[101,123],"scratch.":[102],"Models":[103],"were":[104],"composite":[108],"dataset":[109],"2,854":[111],"lesions":[112,122],"evaluated":[114],"an":[116,171],"external":[117],"test":[118],"set":[119],"234":[121],"Cancer":[125],"Imaging":[126],"Archive.":[127],"Our":[128],"results":[129],"reveal":[130],"two":[131],"key":[132],"findings.":[133],"First,":[134],"performance":[136],"(AUC":[137,143],"0.70-0.77)":[138],"matched":[139],"from-scratch":[141],"ResNet":[142],"0.72)":[144],"while":[145],"drastically":[146],"reducing":[147],"hardware":[148],"demand,":[149],"requiring":[150],"only":[151],"seconds":[152],"CPU":[155],"after":[156],"feature":[157],"extraction.":[158],"However,":[159],"conventional":[161],"baseline":[163],"significantly":[164],"outperformed":[165],"all":[166],"deep":[167],"learning":[168],"approaches,":[169],"achieving":[170],"AUC":[172],"0.88":[174],"(all":[175],"p":[176],"$\\leq$":[177],"0.002).":[178],"suggests":[180],"that":[181],"current":[182,221],"generalist":[183],"not":[187,209],"yet":[188],"capture":[189],"fine-grained":[191],"texture":[192],"shape":[194],"heterogeneity":[195],"driving":[196],"histological":[197],"subtype":[198],"discrimination.":[199],"Despite":[200],"potential":[202],"settings,":[205],"did":[208],"surpass":[210],"established":[211],"for":[213],"stratification,":[216],"leaving":[217],"state-of-the-art.":[222]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}