{"id":"https://openalex.org/W7128399390","doi":"https://doi.org/10.1145/3787120.3787131","title":"RoTransMIL: Rotary Positional Embedding for Transformer-based Multiple Instance Learning","display_name":"RoTransMIL: Rotary Positional Embedding for Transformer-based Multiple Instance Learning","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W7128399390","doi":"https://doi.org/10.1145/3787120.3787131"},"language":null,"primary_location":{"id":"doi:10.1145/3787120.3787131","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787120.3787131","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 5th International Conference on Artificial Intelligence and Application Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787120.3787131","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125381712","display_name":"Taro Nitta","orcid":null},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taro Nitta","raw_affiliation_strings":["Department of Pathology, University of Yamanashi, Chuo, Yamanashi, Japan"],"raw_orcid":"https://orcid.org/0009-0004-9873-8907","affiliations":[{"raw_affiliation_string":"Department of Pathology, University of Yamanashi, Chuo, Yamanashi, Japan","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125393538","display_name":"Masataka Kawai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145079","display_name":"National Cancer Center Hospital East","ror":"https://ror.org/03rm3gk43","country_code":"JP","type":"healthcare","lineage":["https://openalex.org/I4210145079"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masataka Kawai","raw_affiliation_strings":["Department of Pathology and Clinical Laboratories, National Cancer Center Hospital East, Kashiwa, Chiba, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1106-239X","affiliations":[{"raw_affiliation_string":"Department of Pathology and Clinical Laboratories, National Cancer Center Hospital East, Kashiwa, Chiba, Japan","institution_ids":["https://openalex.org/I4210145079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81231174,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9861999750137329,"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":0.9861999750137329,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"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/T12874","display_name":"Digital Imaging for Blood Diseases","score":0.001500000013038516,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6536999940872192},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5522000193595886},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.531000018119812},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4226999878883362},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38960000872612},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3456999957561493},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.32019999623298645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6536999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358000040054321},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.531000018119812},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37130001187324524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.32019999623298645},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.31790000200271606},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.2727999985218048},{"id":"https://openalex.org/C2777609662","wikidata":"https://www.wikidata.org/wiki/Q416356","display_name":"PTEN","level":4,"score":0.26649999618530273},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787120.3787131","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787120.3787131","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 5th International Conference on Artificial Intelligence and Application Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3787120.3787131","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787120.3787131","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 5th International Conference on Artificial Intelligence and Application Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.45099058747291565,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G6725152017","display_name":null,"funder_award_id":"JPNP20006","funder_id":"https://openalex.org/F4320321034","funder_display_name":"New Energy and Industrial Technology Development Organization"}],"funders":[{"id":"https://openalex.org/F4320321034","display_name":"New Energy and Industrial Technology Development Organization","ror":"https://ror.org/0055k7a87"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2785934082","https://openalex.org/W2963341956","https://openalex.org/W3135547872","https://openalex.org/W3159481202","https://openalex.org/W3173365702","https://openalex.org/W3201041614","https://openalex.org/W3202214962","https://openalex.org/W3202476840","https://openalex.org/W3210690434","https://openalex.org/W4312468136","https://openalex.org/W4382561738","https://openalex.org/W4387422491","https://openalex.org/W4388979610"],"related_works":[],"abstract_inverted_index":{"Whole-slide":[0],"images":[1],"(WSIs)":[2],"are":[3,10,27],"widely":[4],"used":[5],"in":[6,66,127,158],"digital":[7],"pathology":[8],"but":[9],"often":[11],"too":[12],"large":[13],"for":[14,88,95,155],"efficient":[15],"processing.":[16],"While":[17,102],"Hadamard-product":[18],"attention-based":[19],"multiple":[20],"instance":[21],"learning":[22],"(MIL)":[23],"methods":[24,106,169],"like":[25],"ABMIL":[26,135],"effective,":[28,152],"they":[29],"do":[30],"not":[31],"capture":[32],"correlations":[33],"between":[34],"image":[35],"patches":[36],"or":[37,163],"incorporate":[38],"positional":[39,53,104,156],"information.":[40],"To":[41,76],"address":[42],"this,":[43],"we":[44,80],"introduce":[45],"RoTransMIL,":[46],"a":[47],"parameter-free":[48,153],"approach":[49],"that":[50],"integrates":[51],"rotary":[52],"embeddings":[54],"(1D":[55],"and":[56,91,97,136],"2D)":[57],"into":[58],"dot-product":[59],"attention/transformer-based":[60],"MIL":[61,68,131],"models.":[62],"A":[63],"major":[64],"challenge":[65],"pathological":[67],"research":[69],"is":[70],"the":[71,121],"lack":[72],"of":[73,124],"high-quality":[74],"datasets.":[75],"facilitate":[77],"further":[78],"advancements,":[79],"curated":[81],"two":[82],"new":[83],"datasets:":[84],"SegPANDA-MIL":[85],"(1K":[86],"images)":[87,94],"tumor":[89],"detection":[90],"UCEC-4K":[92,115],"(4K":[93],"TP53":[96],"PTEN":[98],"gene":[99],"mutation":[100],"prediction.":[101],"various":[103],"encoding":[105,157],"improved":[107],"model":[108],"performance,":[109],"RoTransMIL":[110,149],"demonstrated":[111],"strong":[112],"results.":[113],"Although":[114],"exhibited":[116],"some":[117],"instability":[118],"due":[119],"to":[120,146,167],"small":[122],"number":[123],"test":[125],"cases":[126],"5-fold":[128],"cross-validation,":[129],"transformer-based":[130,159],"models":[132],"consistently":[133],"outperformed":[134],"CLAM,":[137],"maintaining":[138],"robustness":[139],"even":[140],"under":[141],"extreme":[142],"token":[143],"masking":[144],"up":[145],"90\u201399%.":[147],"Overall,":[148],"offers":[150],"an":[151],"solution":[154],"MIL,":[160],"achieving":[161],"competitive":[162],"superior":[164],"performance":[165],"compared":[166],"existing":[168],"with":[170],"minimal":[171],"computational":[172],"cost.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-10T00:00:00"}