{"id":"https://openalex.org/W7162073525","doi":"https://doi.org/10.48550/arxiv.2605.22547","title":"Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement","display_name":"Case-Aware Medical Image Classification with Multimodal Knowledge Graphs and Reliability-Guided Refinement","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162073525","doi":"https://doi.org/10.48550/arxiv.2605.22547"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22547","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.22547","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136736316","display_name":"Yiming Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136779438","display_name":"Yixuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136811243","display_name":"Yuhang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136743218","display_name":"Ling Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136743719","display_name":"Yihan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136745181","display_name":"Qi Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Qi","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5338000059127808,"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":0.5338000059127808,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.061500001698732376,"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":0.06109999865293503,"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/leverage","display_name":"Leverage (statistics)","score":0.7315999865531921},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6079999804496765},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5587000250816345},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.4715000092983246},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4142000079154968},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4016000032424927},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4009000062942505},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.36809998750686646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584999799728394},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7315999865531921},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5587000250816345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5533999800682068},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4763000011444092},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.4715000092983246},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4016000032424927},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4009000062942505},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.2651999890804291}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22547","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.22547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22547","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7476134300231934,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"learning":[1],"has":[2],"brought":[3],"significant":[4],"progress":[5],"to":[6,176],"medical":[7,63,188],"image":[8,64],"classification,":[9],"yet":[10],"most":[11],"existing":[12],"methods":[13],"still":[14],"rely":[15],"on":[16,186],"isolated":[17],"visual":[18,140],"evidence":[19],"and":[20,40,82,100,112,169,172,201,207],"cannot":[21],"effectively":[22],"leverage":[23],"similar":[24,37,95],"cases":[25,39,96],"or":[26],"external":[27],"knowledge.":[28],"In":[29],"clinical":[30],"practice,":[31],"diagnosis":[32],"is":[33,211],"typically":[34],"supported":[35],"by":[36,58,129,164],"historical":[38],"their":[41,102],"associated":[42],"symptoms.":[43],"To":[44,145],"explicitly":[45],"model":[46],"this":[47,98],"evidence-based":[48],"diagnostic":[49,77],"process,":[50],"we":[51,67,149],"propose":[52],"a":[53,69,75,109,130,151],"case-aware":[54,70],"reasoning":[55],"framework":[56],"driven":[57],"multimodal":[59,71],"knowledge":[60,72,110],"graphs":[61],"for":[62,142],"classification.":[65],"Specifically,":[66],"construct":[68],"graph":[73],"as":[74],"structured":[76],"memory,":[78],"where":[79],"diseases,":[80],"images,":[81],"symptoms":[83],"are":[84],"hierarchically":[85],"organized.":[86],"Given":[87],"an":[88,117],"input":[89],"image,":[90],"our":[91,193],"method":[92],"adaptively":[93],"retrieves":[94],"from":[97],"memory":[99],"extracts":[101],"corresponding":[103],"case-centered":[104],"subgraphs.":[105],"We":[106],"further":[107],"introduce":[108],"propagation":[111],"injection":[113],"mechanism,":[114],"in":[115],"which":[116],"image-centric":[118],"Graph":[119],"Attention":[120],"Network":[121],"aggregates":[122],"heterogeneous":[123],"semantics":[124],"into":[125,139],"case-based":[126],"features,":[127],"followed":[128],"bidirectional":[131],"cross-modal":[132,143],"attention":[133],"mechanism":[134],"that":[135,156,192],"injects":[136],"these":[137],"features":[138],"representations":[141],"alignment.":[144],"mitigate":[146],"noisy":[147],"retrieval,":[148],"design":[150],"confidence-calibrated":[152],"decision":[153],"refinement":[154],"scheme":[155],"estimates":[157],"the":[158,177],"reliability":[159],"of":[160],"each":[161],"retrieved":[162],"case":[163],"jointly":[165],"considering":[166],"prediction":[167],"confidence":[168],"sample":[170],"similarity,":[171],"reweights":[173],"its":[174,205],"contribution":[175],"final":[178],"prediction,":[179],"providing":[180],"interpretable":[181],"case-level":[182],"evidence.":[183],"Extensive":[184],"experiments":[185],"multiple":[187],"imaging":[189],"datasets":[190],"demonstrate":[191],"approach":[194],"consistently":[195],"outperforms":[196],"strong":[197],"baselines,":[198],"while":[199],"ablation":[200],"qualitative":[202],"analyses":[203],"validate":[204],"effectiveness":[206],"interpretability.":[208],"The":[209],"code":[210],"available":[212],"at":[213],"https://anonymous.4open.science/r/MKG-CARE-8B7B.":[214]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}