{"id":"https://openalex.org/W7158475607","doi":"https://doi.org/10.48550/arxiv.2604.26807","title":"A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification","display_name":"A Multi-Dataset Benchmark of Multiple Instance Learning for 3D Neuroimage Classification","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7158475607","doi":"https://doi.org/10.48550/arxiv.2604.26807"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.26807","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.26807","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111213546","display_name":"Ethan Harvey","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harvey, Ethan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068452415","display_name":"Dennis Johan Loevlie","orcid":"https://orcid.org/0000-0002-2822-7763"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loevlie, Dennis Johan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134917423","display_name":"Amir Ali Satani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Satani, Amir Ali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009114007","display_name":"Wansu Chen","orcid":"https://orcid.org/0000-0002-3486-7468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wansu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006559598","display_name":"David M. Kent","orcid":"https://orcid.org/0000-0002-9205-5070"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kent, David M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058890009","display_name":"Michael C. Hughes","orcid":"https://orcid.org/0000-0003-4859-7400"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hughes, Michael C.","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/T10036","display_name":"Advanced Neural Network Applications","score":0.4584999978542328,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.4584999978542328,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.13930000364780426,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.035999998450279236,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.8174999952316284},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5529000163078308},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5512999892234802},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4875999987125397},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.450300008058548},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4359000027179718}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8174999952316284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7682999968528748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7253999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5616000294685364},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5529000163078308},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5512999892234802},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.2939000129699707},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.28999999165534973},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.26019999384880066}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.26807","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.26807","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26807","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"},"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":{"Despite":[0],"being":[1,166],"resource-intensive":[2],"to":[3,15,47,100,169],"train,":[4],"3D":[5,37,76,79,111,148],"convolutional":[6],"neural":[7,106],"networks":[8,107],"(CNNs)":[9],"have":[10],"been":[11],"the":[12,42,56,189,200],"standard":[13],"approach":[14],"classify":[16],"CT":[17,83],"and":[18,54,59,78,84,113,128,181,206],"MRI":[19,86],"scans.":[20,96],"Recent":[21],"work":[22,108],"suggests":[23,207],"that":[24,133],"deep":[25],"multiple":[26],"instance":[27],"learning":[28],"(MIL)":[29],"may":[30],"be":[31],"a":[32,68,182,194],"more":[33],"efficient":[34],"alternative":[35],"for":[36,110,120,209],"brain":[38],"scans,":[39],"especially":[40],"when":[41],"pre-trained":[43],"image":[44],"encoder":[45],"used":[46],"embed":[48],"each":[49],"2D":[50],"slice":[51],"is":[52,99],"frozen":[53],"only":[55],"pooling":[57,126,136],"operation":[58],"classifier":[60,192],"are":[61],"trained.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,176,186],"provide":[67],"systematic":[69],"comparison":[70],"of":[71,92,153,202],"simple":[72,134],"MIL,":[73,75,122,137],"attention-based":[74,121],"CNNs,":[77],"ViTs":[80],"across":[81],"three":[82],"four":[85],"datasets,":[87],"including":[88,123],"two":[89,162],"large":[90,163],"datasets":[91,164],"at":[93],"least":[94],"10,000":[95],"Our":[97],"goal":[98],"help":[101],"resource-constrained":[102],"practitioners":[103],"understand":[104],"which":[105],"well":[109],"neuroimages":[112],"why.":[114],"We":[115,131],"further":[116],"compare":[117],"design":[118],"choices":[119],"different":[124],"encoders,":[125],"operations,":[127],"architectural":[129],"orderings.":[130],"find":[132],"mean":[135,173],"without":[138],"any":[139],"learnable":[140],"attention,":[141],"matches":[142],"or":[143,147],"outperforms":[144],"recent":[145],"MIL":[146,204],"CNN":[149],"alternatives":[150],"on":[151,161],"4":[152],"6":[154],"moderate-sized":[155],"tasks.":[156],"This":[157,197],"baseline":[158],"remains":[159],"competitive":[160],"while":[165],"25x":[167],"faster":[168],"train.":[170],"To":[171],"explain":[172],"pooling's":[174],"success,":[175],"examine":[177],"per-slice":[178],"attention":[179],"quality":[180],"semi-synthetic":[183],"dataset":[184],"where":[185],"can":[187],"derive":[188],"best":[190],"possible":[191],"via":[193],"Bayes":[195],"estimator.":[196],"analysis":[198],"reveals":[199],"limits":[201],"existing":[203],"approaches":[205],"routes":[208],"future":[210],"improvements.":[211]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-01T00:00:00"}