{"id":"https://openalex.org/W7221480229","doi":"https://doi.org/10.64898/2026.10.08.26365053","title":"Data-efficient machine learning for the detection of duodenal neoplasia: a multi-centre study","display_name":"Data-efficient machine learning for the detection of duodenal neoplasia: a multi-centre study","publication_year":2026,"publication_date":"2026-10-11","ids":{"openalex":"https://openalex.org/W7221480229","doi":"https://doi.org/10.64898/2026.10.08.26365053"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.08.26365053","doi":"https://doi.org/10.64898/2026.10.08.26365053","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.08.26365053","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/11/2026.10.08.26365053.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/11/2026.10.08.26365053.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119772472","display_name":"Flavio Di Lisio","orcid":"https://orcid.org/0009-0009-8136-7851","observed_orcids":["https://orcid.org/0009-0009-8136-7851"]},"institutions":[{"id":"https://openalex.org/I162290304","display_name":"Scuola Superiore Sant'Anna","ror":"https://ror.org/025602r80","country_code":"IT","type":"education","lineage":["https://openalex.org/I162290304"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","IT"],"is_corresponding":true,"raw_author_name":"Flavio Di Lisio","raw_affiliation_strings":["Department of Pathology, University of Cambridge, Cambridge, UK","Interdisciplinary Center for Health Sciences, Scuola Superiore Sant\u2019Anna, Italy"],"raw_orcid":"https://orcid.org/0009-0009-8136-7851","affiliations":[{"raw_affiliation_string":"Department of Pathology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Interdisciplinary Center for Health Sciences, Scuola Superiore Sant\u2019Anna, Italy","institution_ids":["https://openalex.org/I162290304"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062739895","display_name":"Elizabeth J. Soilleux","orcid":"https://orcid.org/0000-0002-4032-7249","observed_orcids":["https://orcid.org/0000-0002-4032-7249"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elizabeth J. Soilleux","raw_affiliation_strings":["Department of Pathology, University of Cambridge, Cambridge, UK","Lyzeum Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Lyzeum Ltd, Cambridge, UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033700527","display_name":"Florian Jaeckle","orcid":"https://orcid.org/0009-0002-4607-6476","observed_orcids":["https://orcid.org/0009-0002-4607-6476"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florian Jaeckle","raw_affiliation_strings":["Department of Pathology, University of Cambridge, Cambridge, UK","Lyzeum Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Pathology, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Lyzeum Ltd, Cambridge, UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5119772472"],"corresponding_institution_ids":["https://openalex.org/I162290304","https://openalex.org/I241749"],"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":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":1.0,"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":1.0,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.0,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0,"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/duodenal-neoplasms","display_name":"duodenal neoplasms","score":0.9620000123977661},{"id":"https://openalex.org/keywords/duodenal-adenoma","display_name":"duodenal adenoma","score":0.8679999709129333},{"id":"https://openalex.org/keywords/duodenal-cancer","display_name":"duodenal cancer","score":0.9940000176429749},{"id":"https://openalex.org/keywords/duodenal-neuroendocrine-tumor","display_name":"duodenal neuroendocrine tumor","score":0.9340000152587891},{"id":"https://openalex.org/keywords/whole-slide-images","display_name":"whole slide images","score":0.8690000176429749},{"id":"https://openalex.org/keywords/histopathological-diagnosis","display_name":"histopathological diagnosis","score":0.8949999809265137},{"id":"https://openalex.org/keywords/data-efficient-machine-learning","display_name":"data-efficient machine learning","score":0.847000002861023},{"id":"https://openalex.org/keywords/foundation-models","display_name":"foundation models","score":0.6690000295639038},{"id":"https://openalex.org/keywords/patch-embedding","display_name":"patch embedding","score":0.8109999895095825},{"id":"https://openalex.org/keywords/gaussian-mixture-model","display_name":"Gaussian mixture model","score":0.8399999737739563},{"id":"https://openalex.org/keywords/rare-tumor","display_name":"rare tumor","score":0.7699999809265137}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7584999799728394},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6704999804496765},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5605000257492065},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48919999599456787},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.45559999346733093},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.454800009727478},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C2775934546","wikidata":"https://www.wikidata.org/wiki/Q179991","display_name":"Biopsy","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C203616005","wikidata":"https://www.wikidata.org/wiki/Q620495","display_name":"Hessian matrix","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3046000003814697},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.30329999327659607},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2897999882698059},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.08.26365053","doi":"https://doi.org/10.64898/2026.10.08.26365053","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.08.26365053","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/11/2026.10.08.26365053.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.08.26365053","doi":"https://doi.org/10.64898/2026.10.08.26365053","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.08.26365053","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/10/11/2026.10.08.26365053.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"score":0.9537000060081482,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7221480229.pdf","grobid_xml":"https://content.openalex.org/works/W7221480229.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2594258169","https://openalex.org/W4399511651"],"related_works":["https://openalex.org/W4225616443","https://openalex.org/W4402220065","https://openalex.org/W2920527701","https://openalex.org/W3004016611","https://openalex.org/W7008230062","https://openalex.org/W2957792382","https://openalex.org/W4361275822","https://openalex.org/W4312156722","https://openalex.org/W4307725214","https://openalex.org/W7127986743"],"abstract_inverted_index":{"Background":[0],"Machine":[1],"Learning":[2],"(ML)":[3],"has":[4],"shown":[5],"promise":[6],"in":[7,38],"histopathological":[8,245],"diagnosis,":[9],"but":[10],"rare":[11,244],"tumours,":[12],"like":[13],"duodenal":[14,35,51,211],"epithelial":[15,36,212],"neoplasms,":[16],"are":[17,23],"challenging":[18],"because":[19],"large,":[20],"labelled":[21],"datasets":[22],"difficult":[24],"to":[25],"assemble.":[26],"We":[27,42,85,111,203],"propose":[28],"a":[29,44,102,107,127,137,205],"data-efficient":[30,206],"ML":[31,207],"pipeline":[32,97,135,188],"for":[33,209,243],"detecting":[34,210],"neoplasia":[37,213],"whole-slide":[39],"images.":[40],"Methods":[41],"assembled":[43],"five-hospital":[45],"dataset":[46],"of":[47,93,140,143,146,151,168,199,233,240],"haematoxylin":[48],"and":[49,63,70,78,106,120,148,166,222],"eosin\u2013stained":[50],"biopsy":[52],"whole":[53],"slide":[54],"images":[55],"(WSIs)":[56],"at":[57],"10x":[58],"magnification,":[59],"comprising":[60],"8,027":[61],"normal":[62],"401":[64],"neoplastic":[65,234],"biopsies,":[66],"including":[67],"adenomas,":[68],"carcinomas":[69],"neuroendocrine":[71],"tumours.":[72],"WSIs":[73],"were":[74],"divided":[75],"into":[76],"patches":[77],"encoded":[79],"using":[80,114],"the":[81,134,154,185,230,238],"Hibou-B":[82],"foundation":[83],"model.":[84],"compared":[86,180,195],"global":[87,182],"standardisation":[88,92,171],"with":[89,181,196],"unsupervised":[90],"site-specific":[91],"patch":[94,200],"embeddings.":[95,201],"Our":[96],"combined":[98],"principal":[99],"component":[100],"analysis,":[101],"Gaussian":[103,186],"mixture":[104,187],"model":[105],"Random":[108],"Forest":[109],"classifier.":[110],"assessed":[112],"generalisability":[113],"leave-one-hospital-out":[115,132],"cross-validation":[116,174],"across":[117,220],"four":[118],"hospitals":[119,221],"on":[121,223],"an":[122,149,224],"independent":[123,225],"test":[124,156,227],"set":[125],"from":[126,214],"fifth":[128],"hospital.":[129],"Results":[130],"In":[131],"cross-validation,":[133],"achieved":[136,159],"mean":[138,173,197],"accuracy":[139,175,190],"90%,":[141],"sensitivity":[142],"96%,":[144],"specificity":[145],"83%":[147],"AUC":[150,167],"0.96.":[152],"On":[153],"external":[155,226],"hospital,":[157],"it":[158],"94%":[160],"accuracy,":[161],"93%":[162],"sensitivity,":[163],"95%":[164],"specificity,":[165],"0.97.":[169],"Site-specific":[170],"improved":[172,189],"by":[176,191],"20":[177],"percentage":[178,193],"points":[179,194],"standardisation,":[183],"while":[184],"12":[192],"pooling":[198],"Conclusions":[202],"present":[204],"approach":[208],"WSIs.":[215],"Strong":[216],"performance":[217],"was":[218],"maintained":[219],"cohort":[228],"despite":[229],"limited":[231],"number":[232],"training":[235],"cases,":[236],"supporting":[237],"feasibility":[239],"foundation-model-based":[241],"approaches":[242],"diagnoses.":[246]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-12T00:00:00"}