{"id":"https://openalex.org/W4409367232","doi":"https://doi.org/10.1609/aaai.v39i8.32848","title":"Autoregressive Sequence Modeling for 3D Medical Image Representation","display_name":"Autoregressive Sequence Modeling for 3D Medical Image Representation","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409367232","doi":"https://doi.org/10.1609/aaai.v39i8.32848"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i8.32848","doi":"https://doi.org/10.1609/aaai.v39i8.32848","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i8.32848","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32848/35003","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"parent_works":[],"lineage":["https://openalex.org/W4409367232"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32848/35003","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103171478","display_name":"Siwen Wang","orcid":"https://orcid.org/0009-0004-0808-0559","observed_orcids":["https://orcid.org/0009-0004-0808-0559","https://orcid.org/0000-0002-9908-9724"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siwen Wang","raw_affiliation_strings":["Deepwise AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deepwise AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011041316","display_name":"Churan Wang","orcid":"https://orcid.org/0000-0002-7699-0894","observed_orcids":["https://orcid.org/0000-0002-7699-0894","https://orcid.org/0000-0001-9242-1627"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Churan Wang","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Nat\u2019l Eng. Research Center of Visual Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Nat\u2019l Eng. Research Center of Visual Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101688555","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0001-9020-6720","observed_orcids":["https://orcid.org/0000-0001-9020-6720"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Nat\u2019l Eng. Research Center of Visual Technology, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Nat\u2019l Eng. Research Center of Visual Technology, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111422321","display_name":"Lixian Su","orcid":"https://orcid.org/0009-0008-2195-2074","observed_orcids":["https://orcid.org/0009-0008-2195-2074"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lixian Su","raw_affiliation_strings":["Deepwise AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deepwise AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022828476","display_name":"Fandong Zhang","orcid":"https://orcid.org/0000-0003-0655-1180","observed_orcids":["https://orcid.org/0000-0003-0655-1180"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fandong Zhang","raw_affiliation_strings":["Deepwise AI Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deepwise AI Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100602395","display_name":"Yizhou Wang","orcid":"https://orcid.org/0000-0001-9888-6409","observed_orcids":["https://orcid.org/0000-0001-9888-6409"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Wang","raw_affiliation_strings":["Center on Frontiers of Computing Studies, School of Computer Science, Nat\u2019l Eng. Research Center of Visual Technology, Peking University\nState Key Lab of General Artificial Intelligence, Inst. for Artificial Intelligence, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, School of Computer Science, Nat\u2019l Eng. Research Center of Visual Technology, Peking University\nState Key Lab of General Artificial Intelligence, Inst. for Artificial Intelligence, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108557359","display_name":"Yizhou Yu","orcid":"https://orcid.org/0000-0002-0470-5548","observed_orcids":["https://orcid.org/0000-0002-0470-5548"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yizhou Yu","raw_affiliation_strings":["School of Computing and Data Science, The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3649,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8558378,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"39","issue":"8","first_page":"7871","last_page":"7879"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38499999046325684,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.38499999046325684,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.2705000042915344,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.08860000222921371,"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/self-supervised-pretraining","display_name":"self-supervised pre-training","score":0.8320000171661377},{"id":"https://openalex.org/keywords/next-token-prediction","display_name":"next-token prediction","score":0.5929999947547913},{"id":"https://openalex.org/keywords/visual-tokenization","display_name":"visual tokenization","score":0.6069999933242798},{"id":"https://openalex.org/keywords/ct-and-mri-images","display_name":"CT and MRI images","score":0.6869999766349792},{"id":"https://openalex.org/keywords/contextual-information","display_name":"contextual information","score":0.4830000102519989},{"id":"https://openalex.org/keywords/multimodal-medical-images","display_name":"multimodal medical images","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6773183345794678},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.599744975566864},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5868324637413025},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49755576252937317},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4873574376106262},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44398602843284607},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.4417513310909271},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.337188184261322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2720761299133301},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.1575322151184082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.143978089094162},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12036359310150146},{"id":"https://openalex.org/C24338571","wikidata":"https://www.wikidata.org/wiki/Q2566298","display_name":"Autoregressive integrated moving average","level":3,"score":0.11376684904098511},{"id":"https://openalex.org/C151406439","wikidata":"https://www.wikidata.org/wiki/Q186588","display_name":"Time series","level":2,"score":0.07888445258140564},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.06936874985694885},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v39i8.32848","doi":"https://doi.org/10.1609/aaai.v39i8.32848","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i8.32848","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32848/35003","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2409.08691","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.08691","pdf_url":"https://arxiv.org/pdf/2409.08691","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ojs.aaai.org:article/32848","doi":null,"is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/32848","pdf_url":null,"source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.2409.08691","doi":"https://doi.org/10.48550/arxiv.2409.08691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2409.08691","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,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i8.32848","doi":"https://doi.org/10.1609/aaai.v39i8.32848","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i8.32848","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/32848/35003","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409367232.pdf","grobid_xml":"https://content.openalex.org/works/W4409367232.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W3094502228","https://openalex.org/W3178989684","https://openalex.org/W4366208220","https://openalex.org/W4376864677","https://openalex.org/W4390963175","https://openalex.org/W4403666775","https://openalex.org/W4405663061","https://openalex.org/W6940613197","https://openalex.org/W7103299521","https://openalex.org/W7148259318"],"related_works":["https://openalex.org/W7148519297","https://openalex.org/W3100622512","https://openalex.org/W4393294707","https://openalex.org/W4414198625","https://openalex.org/W4317626608","https://openalex.org/W4385474648","https://openalex.org/W4415054872","https://openalex.org/W7213394268","https://openalex.org/W4408355745","https://openalex.org/W7135086524"],"abstract_inverted_index":{"Three-dimensional":[0],"(3D)":[1],"medical":[2,105,118,168],"images,":[3],"such":[4],"as":[5,77,129],"Computed":[6],"Tomography":[7],"(CT)":[8],"and":[9,24,39,50,124,160,182],"Magnetic":[10],"Resonance":[11],"Imaging":[12],"(MRI),":[13],"are":[14],"essential":[15],"for":[16,22,102],"clinical":[17],"applications.":[18],"However,":[19],"the":[20,32,46,62,82,146,151,162,185,197],"need":[21],"diverse":[23],"comprehensive":[25],"representations":[26,107],"is":[27,194],"particularly":[28],"pronounced":[29],"when":[30],"considering":[31],"variability":[33],"across":[34],"different":[35],"organs,":[36],"diagnostic":[37],"tasks,":[38],"imaging":[40],"modalities.":[41],"How":[42],"to":[43,61,157,177,183],"effectively":[44],"interpret":[45],"intricate":[47],"contextual":[48,163],"information":[49,164],"extract":[51],"meaningful":[52],"insights":[53],"from":[54,89],"these":[55],"images":[56,119],"remains":[57],"an":[58,75,109,139],"open":[59],"challenge":[60],"community.":[63],"While":[64],"current":[65],"self-supervised":[66],"learning":[67,103],"methods":[68],"have":[69],"shown":[70],"potential,":[71],"they":[72],"often":[73],"consider":[74],"image":[76,106],"a":[78,99,134,173],"whole":[79],"thereby":[80],"overlooking":[81],"extensive,":[83],"complex":[84],"relationships":[85,181],"among":[86],"local":[87],"regions":[88],"one":[90],"or":[91],"multiple":[92],"images.":[93,169],"In":[94],"this":[95],"work,":[96],"we":[97,144,171],"introduce":[98],"pioneering":[100],"method":[101],"3D":[104,117,167],"through":[108],"autoregressive":[110,140],"pre-training":[111],"framework.":[112],"Our":[113],"approach":[114,193],"sequences":[115],"various":[116],"based":[120],"on":[121,202],"spatial,":[122],"contrast,":[123],"semantic":[125],"correlations,":[126],"treating":[127],"them":[128],"interconnected":[130],"visual":[131,148],"tokens":[132],"within":[133],"token":[135,149,180],"sequence.":[136],"By":[137],"employing":[138],"sequence":[141],"modeling":[142],"task,":[143],"predict":[145],"next":[147],"in":[150,166,206],"sequence,":[152],"which":[153],"allows":[154],"our":[155,192],"model":[156],"deeply":[158],"understand":[159],"integrate":[161],"inherent":[165],"Additionally,":[170],"implement":[172],"random":[174],"startup":[175],"strategy":[176],"avoid":[178],"overestimating":[179],"enhance":[184],"robustness":[186],"of":[187,191],"learning.":[188],"The":[189],"effectiveness":[190],"demonstrated":[195],"by":[196],"superior":[198],"performance":[199],"over":[200],"others":[201],"nine":[203],"downstream":[204],"tasks":[205],"public":[207],"datasets.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2025-04-12T00:00:00"}