{"id":"https://openalex.org/W7138055736","doi":"https://doi.org/10.1609/aaai.v40i9.37649","title":"PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology","display_name":"PathFLIP: Fine-grained Language-Image Pretraining for Versatile Computational Pathology","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138055736","doi":"https://doi.org/10.1609/aaai.v40i9.37649"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i9.37649","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37649","pdf_url":null,"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,"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"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i9.37649","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121050872","display_name":"Fengchun Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengchun Liu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102250093","display_name":"Songhan Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Songhan Jiang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087479926","display_name":"Linghan Cai","orcid":"https://orcid.org/0000-0002-7931-7697"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghan Cai","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129652874","display_name":"Ziyue Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziyue Wang","raw_affiliation_strings":["National University of Singapore, Department of Electronic and Computer Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Department of Electronic and Computer Engineering","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129673765","display_name":"Yongbing Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbing Zhang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, School of Computer Science and Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.30626781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"9","first_page":"7132","last_page":"7140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5995000004768372,"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":0.5995000004768372,"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/T10862","display_name":"AI in cancer detection","score":0.14489999413490295,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.07919999957084656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.506600022315979},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.4578999876976013},{"id":"https://openalex.org/keywords/digital-pathology","display_name":"Digital pathology","score":0.4336000084877014},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.38190001249313354},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3425999879837036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.337799996137619}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7587000131607056},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612500011920929},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.4578999876976013},{"id":"https://openalex.org/C2777522853","wikidata":"https://www.wikidata.org/wiki/Q5276128","display_name":"Digital pathology","level":2,"score":0.4336000084877014},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.39989998936653137},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i9.37649","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37649","pdf_url":null,"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,"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:ojs.aaai.org:article/37649","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37649","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i9.37649","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i9.37649","pdf_url":null,"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,"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":[{"score":0.8163942098617554,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Vision-Language":[1],"Models":[2,95],"(VLMs)":[3],"have":[4],"achieved":[5],"notable":[6],"progress":[7],"in":[8,158],"computational":[9],"pathology":[10],"(CPath),":[11],"the":[12,151],"gigapixel":[13],"scale":[14],"and":[15,41,81,104,122,127,160],"spatial":[16],"heterogeneity":[17],"of":[18,46],"Whole":[19],"Slide":[20],"Images":[21],"(WSIs)":[22],"continue":[23],"to":[24,34,86,106],"pose":[25],"challenges":[26],"for":[27,70,153],"multimodal":[28],"understanding.":[29],"Existing":[30],"alignment":[31],"methods":[32],"struggle":[33],"capture":[35],"fine-grained":[36,124],"correspondences":[37],"between":[38],"textual":[39],"descriptions":[40],"visual":[42],"cues":[43],"across":[44,115],"thousands":[45],"patches":[47],"from":[48],"a":[49,67],"slide,":[50],"compromising":[51],"their":[52],"performance":[53],"on":[54,140],"downstream":[55],"tasks.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"PathFLIP":[62,74,97,134],"(Pathology":[63],"Fine-grained":[64],"Language-Image":[65],"Pretraining),":[66],"novel":[68],"framework":[69],"holistic":[71],"WSI":[72,156],"interpretation.":[73],"decomposes":[75],"slide-level":[76,120],"captions":[77],"into":[78],"region-level":[79],"sub-captions":[80],"generates":[82],"text-conditioned":[83],"region":[84],"embeddings":[85],"facilitate":[87],"precise":[88],"visual-language":[89],"grounding.":[90],"By":[91],"harnessing":[92],"Large":[93],"Language":[94],"(LLMs),":[96],"can":[98],"seamlessly":[99],"follow":[100],"diverse":[101],"clinical":[102,161],"instructions":[103],"adapt":[105],"varied":[107],"diagnostic":[108],"contexts.":[109],"Furthermore,":[110],"it":[111],"exhibits":[112],"versatile":[113],"capabilities":[114],"multiple":[116],"paradigms,":[117],"efficiently":[118],"handling":[119],"classification":[121],"retrieval,":[123],"lesion":[125],"localization,":[126],"instruction":[128],"following.":[129],"Extensive":[130],"experiments":[131],"demonstrate":[132],"that":[133],"outperforms":[135],"existing":[136],"large-scale":[137],"pathological":[138],"VLMs":[139],"four":[141],"representative":[142],"benchmarks":[143],"while":[144],"requiring":[145],"significantly":[146],"less":[147],"training":[148],"data,":[149],"paving":[150],"way":[152],"fine-grained,":[154],"instruction-aware":[155],"interpretation":[157],"research":[159],"practice.":[162]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}