{"id":"https://openalex.org/W7119489214","doi":"https://doi.org/10.48550/arxiv.2601.03410","title":"Inferring Clinically Relevant Molecular Subtypes of Pancreatic Cancer from Routine Histopathology Using Deep Learning","display_name":"Inferring Clinically Relevant Molecular Subtypes of Pancreatic Cancer from Routine Histopathology Using Deep Learning","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7119489214","doi":"https://doi.org/10.48550/arxiv.2601.03410"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.03410","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03410","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.03410","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062903400","display_name":"Abdul Akbar","orcid":"https://orcid.org/0000-0002-8353-132X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Akbar, Abdul Rehman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022820025","display_name":"Alejandro H. Mar\u00edn Levya","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levya, Alejandro","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025576841","display_name":"Ashwini Esnakula","orcid":"https://orcid.org/0000-0001-6029-0124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Esnakula, Ashwini","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122361368","display_name":"Elshad Hasanov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hasanov, Elshad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009849305","display_name":"Anne M. Noonan","orcid":"https://orcid.org/0000-0001-8083-8492"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noonan, Anne","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Meng, Lingbin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng, Lingbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122390570","display_name":"Susan Tsai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsai, Susan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093054951","display_name":"Vaibhav Sahai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sahai, Vaibhav","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056209015","display_name":"Midhun Malla","orcid":"https://orcid.org/0000-0002-9969-588X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malla, Midhun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mukherjee, Sarbajit","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukherjee, Sarbajit","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087842474","display_name":"Upender Manne","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manne, Upender","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Parwani, Anil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parwani, Anil","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5096950690","display_name":"Ashish Manne","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manne, Ashish","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128872922","display_name":"Muhammad Khalid Khan Niazi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niazi, Muhammad Khalid Khan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5062903400"],"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/T10862","display_name":"AI in cancer detection","score":0.31299999356269836,"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":0.31299999356269836,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.27480000257492065,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10231","display_name":"Pancreatic and Hepatic Oncology Research","score":0.09350000321865082,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/subtyping","display_name":"Subtyping","score":0.7545999884605408},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.641700029373169},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5968000292778015},{"id":"https://openalex.org/keywords/pancreatic-cancer","display_name":"Pancreatic cancer","score":0.4851999878883362},{"id":"https://openalex.org/keywords/digital-pathology","display_name":"Digital pathology","score":0.4830000102519989},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.45879998803138733},{"id":"https://openalex.org/keywords/precision-medicine","display_name":"Precision medicine","score":0.42480000853538513},{"id":"https://openalex.org/keywords/clinical-practice","display_name":"Clinical Practice","score":0.4180999994277954},{"id":"https://openalex.org/keywords/prognostic-model","display_name":"Prognostic model","score":0.39419999718666077}],"concepts":[{"id":"https://openalex.org/C83852419","wikidata":"https://www.wikidata.org/wiki/Q2713292","display_name":"Subtyping","level":2,"score":0.7545999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6589000225067139},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.641700029373169},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.527400016784668},{"id":"https://openalex.org/C2780210213","wikidata":"https://www.wikidata.org/wiki/Q212961","display_name":"Pancreatic cancer","level":3,"score":0.4851999878883362},{"id":"https://openalex.org/C2777522853","wikidata":"https://www.wikidata.org/wiki/Q5276128","display_name":"Digital pathology","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.46959999203681946},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4359000027179718},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C143998085","wikidata":"https://www.wikidata.org/wiki/Q162555","display_name":"Oncology","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C2993277928","wikidata":"https://www.wikidata.org/wiki/Q7248370","display_name":"Prognostic model","level":3,"score":0.39419999718666077},{"id":"https://openalex.org/C3020404979","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk stratification","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.3727000057697296},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C544855455","wikidata":"https://www.wikidata.org/wiki/Q1070952","display_name":"Histopathology","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.3003000020980835},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.29350000619888306},{"id":"https://openalex.org/C2989179672","wikidata":"https://www.wikidata.org/wiki/Q6806500","display_name":"Clinical decision making","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.27570000290870667},{"id":"https://openalex.org/C176553487","wikidata":"https://www.wikidata.org/wiki/Q7855819","display_name":"Turnaround time","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C160798450","wikidata":"https://www.wikidata.org/wiki/Q4230870","display_name":"Concordance","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2779733811","wikidata":"https://www.wikidata.org/wiki/Q5531562","display_name":"Gene signature","level":4,"score":0.2648000121116638},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C18431079","wikidata":"https://www.wikidata.org/wiki/Q1502169","display_name":"Gene expression profiling","level":4,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.03410","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03410","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.03410","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03410","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"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":{"Molecular":[0],"subtyping":[1],"of":[2,36,127],"PDAC":[3],"into":[4,223],"basal-like":[5],"and":[6,11,26,75,111,132,182,202,217,227],"classical":[7],"has":[8],"established":[9,177],"prognostic":[10,155],"predictive":[12],"value.":[13],"However,":[14],"its":[15,31],"use":[16],"in":[17,33,151],"clinical":[18],"practice":[19],"is":[20],"limited":[21],"by":[22,89],"cost,":[23],"turnaround":[24],"time,":[25],"tissue":[27],"requirements,":[28],"thereby":[29],"restricting":[30],"application":[32],"the":[34,83,137],"management":[35],"PDAC.":[37,232],"We":[38,208],"introduce":[39],"PanSubNet,":[40],"an":[41],"interpretable":[42,203],"deep":[43],"learning":[44,110],"framework":[45],"that":[46,97],"predicts":[47],"therapy-relevant":[48],"molecular":[49,191],"subtypes":[50],"directly":[51],"from":[52,61,193,212],"standard":[53],"H&E-stained":[54,195],"WSIs.":[55],"PanSubNet":[56,123,148,197],"was":[57],"developed":[58],"using":[59,82,120],"data":[60,211],"1,055":[62],"patients":[63],"across":[64],"two":[65,213],"multi-institutional":[66],"cohorts":[67],"(PANCAN,":[68],"n=846;":[69],"TCGA,":[70],"n=209)":[71],"with":[72,101,129,176],"paired":[73],"histology":[74],"RNA-seq":[76,159],"data.":[77],"Ground-truth":[78],"labels":[79],"were":[80],"derived":[81],"validated":[84],"Moffitt":[85],"50-gene":[86],"signature":[87],"refined":[88],"GATA6":[90],"expression.":[91],"The":[92],"model":[93],"employs":[94],"dual-scale":[95],"architecture":[96],"fuses":[98],"cellular-level":[99],"morphology":[100],"tissue-level":[102],"architecture,":[103],"leveraging":[104],"attention":[105],"mechanisms":[106],"for":[107,205,231],"multi-scale":[108],"representation":[109],"transparent":[112],"feature":[113],"attribution.":[114],"On":[115],"internal":[116],"validation":[117,135],"within":[118],"PANCAN":[119],"five-fold":[121],"cross-validation,":[122],"achieved":[124],"mean":[125],"AUC":[126],"88.5%":[128],"balanced":[130],"sensitivity":[131],"specificity.":[133],"External":[134],"on":[136],"independent":[138],"TCGA":[139],"cohort":[140],"without":[141],"fine-tuning":[142],"demonstrated":[143],"robust":[144],"generalizability":[145],"(AUC":[146],"84.0%).":[147],"preserved":[149],"and,":[150],"metastatic":[152],"disease,":[153],"strengthened":[154],"stratification":[156,192],"compared":[157],"to":[158,165,215],"based":[160],"labels.":[161],"Prediction":[162],"uncertainty":[163],"linked":[164],"intermediate":[166],"transcriptional":[167],"states,":[168],"not":[169],"classification":[170],"noise.":[171],"Model":[172],"predictions":[173],"are":[174,209],"aligned":[175],"transcriptomic":[178],"programs,":[179],"differentiation":[180],"markers,":[181],"DNA":[183],"damage":[184],"repair":[185],"signatures.":[186],"By":[187],"enabling":[188],"rapid,":[189],"cost-effective":[190],"routine":[194],"slides,":[196],"offers":[198],"a":[199],"clinically":[200],"deployable":[201],"tool":[204],"genetic":[206],"subtyping.":[207],"gathering":[210],"institutions":[214],"validate":[216],"assess":[218],"real-world":[219],"performance,":[220],"supporting":[221],"integration":[222],"digital":[224],"pathology":[225],"workflows":[226],"advancing":[228],"precision":[229],"oncology":[230]},"counts_by_year":[],"updated_date":"2026-03-13T14:20:09.374765","created_date":"2026-01-09T00:00:00"}