{"id":"https://openalex.org/W7161174001","doi":"https://doi.org/10.48550/arxiv.2605.13544","title":"CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image Understanding","display_name":"CA-GCL: Cross-Anatomy Global-Local Contrastive Learning for Robust 3D Medical Image Understanding","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161174001","doi":"https://doi.org/10.48550/arxiv.2605.13544"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.13544","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13544","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.2605.13544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136163377","display_name":"Hanwen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hanwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136183972","display_name":"Yao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078465133","display_name":"Die Dai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Die","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136128804","display_name":"Jiaye Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiaye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136116569","display_name":"Qiao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136108780","display_name":"Yutong Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136153891","display_name":"Peng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3107999861240387,"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":0.3107999861240387,"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":0.17190000414848328,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.12200000137090683,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"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/robustness","display_name":"Robustness (evolution)","score":0.6967999935150146},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5375000238418579},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43380001187324524},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4293000102043152},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.41659998893737793},{"id":"https://openalex.org/keywords/completeness","display_name":"Completeness (order theory)","score":0.4009999930858612},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.39719998836517334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078999876976013},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6967999935150146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6815999746322632},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4422000050544739},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43380001187324524},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3862000107765198},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34060001373291016},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3402999937534332},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C50965678","wikidata":"https://www.wikidata.org/wiki/Q2724302","display_name":"Abnormality","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.26100000739097595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.13544","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13544","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.2605.13544","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.13544","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":[{"score":0.7239115834236145,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-grained":[0],"Vision-Language":[1],"Pre-training":[2],"(FVLP)":[3],"demonstrates":[4],"significant":[5],"potential":[6],"in":[7,31,88,138],"3D":[8,179],"medical":[9,180],"image":[10,181],"understanding":[11],"by":[12,98],"aligning":[13],"anatomy-level":[14],"visual":[15],"representations":[16],"with":[17],"corresponding":[18],"textual":[19,33,162],"descriptions.":[20],"However,":[21],"existing":[22,135],"FVLP":[23],"paradigms":[24,137],"often":[25],"suffer":[26],"from":[27],"severe":[28],"representation":[29],"collapse":[30],"the":[32,52,89,94,125,160],"embedding":[34],"space,":[35,91],"where":[36],"text":[37,106],"embeddings":[38],"of":[39],"distinct":[40],"anatomical":[41,86],"structures":[42],"become":[43],"highly":[44],"clustered":[45],"and":[46,113,127],"indistinguishable.":[47],"This":[48],"distributional":[49],"degeneracy":[50],"renders":[51],"model":[53],"hypersensitive":[54],"to":[55,116],"prompt":[56,157],"variations,":[57],"hindering":[58],"reliable":[59],"clinical":[60],"deployment.":[61],"To":[62],"address":[63],"these":[64],"challenges,":[65],"we":[66,102],"propose":[67],"a":[68,78,104,166],"novel":[69],"Cross-Anatomy":[70],"Global-Local":[71],"Contrastive":[72],"Learning":[73],"framework":[74,176],"(CA-GCL).":[75],"CA-GCL":[76,132,151,172],"introduces":[77],"global":[79],"contrastive":[80],"objective":[81],"that":[82,131],"enforces":[83],"separation":[84],"between":[85],"categories":[87],"latent":[90],"effectively":[92],"counteracting":[93],"aggregation":[95],"tendency":[96],"induced":[97],"local":[99],"alignment.":[100],"Furthermore,":[101],"incorporate":[103],"clinical-aware":[105],"augmentation":[107],"strategy":[108],"based":[109],"on":[110,124],"permutation":[111],"invariance":[112],"partial":[114],"completeness":[115],"enhance":[117],"robustness":[118],"against":[119],"descriptive":[120],"incompleteness.":[121],"Extensive":[122],"evaluations":[123],"CT-RATE":[126],"Rad-ChestCT":[128],"datasets":[129],"demonstrate":[130],"consistently":[133],"outperforms":[134],"VLP":[136],"zero-shot":[139],"abnormality":[140],"detection,":[141],"achieving":[142],"superior":[143],"performance":[144,153],"while":[145],"exhibiting":[146],"strong":[147],"cross-dataset":[148],"generalization.":[149],"Crucially,":[150],"reduces":[152],"variance":[154],"across":[155],"diverse":[156],"templates,":[158],"transforming":[159],"collapsed":[161],"similarity":[163],"distribution":[164],"into":[165],"bell-shaped":[167],"distribution.":[168],"These":[169],"results":[170],"validate":[171],"as":[173],"an":[174],"effective":[175],"for":[177],"robust":[178],"understanding.":[182]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-15T00:00:00"}