{"id":"https://openalex.org/W4415537768","doi":"https://doi.org/10.1145/3746027.3754913","title":"Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation","display_name":"Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537768","doi":"https://doi.org/10.1145/3746027.3754913"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3754913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2509.25963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085584344","display_name":"Longzhen Yang","orcid":"https://orcid.org/0000-0002-5791-145X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Longzhen Yang","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5791-145X","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032273272","display_name":"Zhangkai Ni","orcid":"https://orcid.org/0000-0003-3682-6288"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangkai Ni","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3682-6288","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647485","display_name":"Ying Wen","orcid":"https://orcid.org/0000-0002-6974-5110"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wen","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6974-5110","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101847419","display_name":"Yihang Liu","orcid":"https://orcid.org/0000-0003-4257-2528"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihang Liu","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4257-2528","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091130234","display_name":"Lianghua He","orcid":"https://orcid.org/0000-0002-5250-170X"},"institutions":[{"id":"https://openalex.org/I4210092517","display_name":"Shanghai Eye Disease Prevention & Treatment Center","ror":"https://ror.org/0048a4976","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210092517"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianghua He","raw_affiliation_strings":["Tongji University, Shanghai, China and Shanghai Eye Disease Prevention and Treatment Center, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5250-170X","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China and Shanghai Eye Disease Prevention and Treatment Center, Shanghai, China","institution_ids":["https://openalex.org/I4210092517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052993469","display_name":"Heng Tao Shen","orcid":"https://orcid.org/0000-0002-2999-2088"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Tao Shen","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2999-2088","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5085584344"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28684703,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2958","last_page":"2967"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9987000226974487,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.967199981212616,"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/interpretability","display_name":"Interpretability","score":0.7904999852180481},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5145999789237976},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.41839998960494995},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.41260001063346863},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.40950000286102295},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3111000061035156}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7904999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6510999798774719},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5145999789237976},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4715000092983246},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3111000061035156},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.25369998812675476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3754913","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754913","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.25963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.25963","pdf_url":"https://arxiv.org/pdf/2509.25963","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2509.25963","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.25963","pdf_url":"https://arxiv.org/pdf/2509.25963","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3582019159","display_name":null,"funder_award_id":"62271155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4606321376","display_name":null,"funder_award_id":"2021SHZDZX0100","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7355213507","display_name":null,"funder_award_id":"62171323","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G897182718","display_name":null,"funder_award_id":"2021SHZDZX0100","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415537768.pdf","grobid_xml":"https://content.openalex.org/works/W4415537768.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1901129140","https://openalex.org/W2133459682","https://openalex.org/W2914203365","https://openalex.org/W2995225687","https://openalex.org/W3159481202","https://openalex.org/W3201906559","https://openalex.org/W3213233983","https://openalex.org/W4296295611","https://openalex.org/W4313156423","https://openalex.org/W4386065580","https://openalex.org/W4386076127","https://openalex.org/W4386076536","https://openalex.org/W4388713229","https://openalex.org/W4401971190","https://openalex.org/W4402134103","https://openalex.org/W4405268957"],"related_works":[],"abstract_inverted_index":{"Vision-grounded":[0],"medical":[1,11],"report":[2,152],"generation":[3],"aims":[4],"to":[5,18,50,110,157],"produce":[6],"clinically":[7],"accurate":[8,174],"descriptions":[9],"of":[10,96],"images,":[12],"anchored":[13],"in":[14,183,188,209],"explicit":[15],"visual":[16,160,199,204,211],"evidence":[17],"improve":[19],"interpretability":[20],"and":[21,46,68,175,186,191],"facilitate":[22],"integration":[23],"into":[24],"clinical":[25,189],"workflows.":[26],"However,":[27],"existing":[28],"methods":[29,180],"often":[30],"rely":[31],"on":[32,142,169,196],"separately":[33],"trained":[34],"detection":[35],"modules":[36],"that":[37,71,165],"require":[38],"extensive":[39],"expert":[40,170],"annotations,":[41,171],"introducing":[42],"high":[43],"labeling":[44],"costs":[45],"limiting":[47],"generalizability":[48],"due":[49],"pathology":[51],"distribution":[52],"bias":[53],"across":[54],"datasets.":[55],"To":[56,126],"address":[57],"these":[58],"challenges,":[59],"we":[60],"propose":[61],"Self-Supervised":[62],"Anatomical":[63],"Consistency":[64],"Learning":[65],"(SS-ACL)-a":[66],"novel":[67],"annotation-free":[69],"framework":[70],"aligns":[72],"generated":[73],"reports":[74],"with":[75],"corresponding":[76],"anatomical":[77,87,108,143],"regions":[78,109],"using":[79],"simple":[80],"textual":[81],"prompts.":[82],"SS-ACL":[83,135],"constructs":[84],"a":[85,137],"hierarchical":[86],"graph":[88],"inspired":[89],"by":[90,101,124,181,207],"the":[91],"invariant":[92],"top-down":[93],"inclusion":[94],"structure":[95],"human":[97],"anatomy,":[98],"organizing":[99],"entities":[100],"spatial":[102,113],"location.":[103],"It":[104],"recursively":[105],"reconstructs":[106],"fine-grained":[107],"enforce":[111],"intra-sample":[112],"alignment,":[114],"inherently":[115],"guiding":[116],"attention":[117,155],"maps":[118,156],"toward":[119],"visually":[120,176],"relevant":[121],"areas":[122],"prompted":[123],"text.":[125],"further":[127],"enhance":[128],"inter-sample":[129],"semantic":[130],"alignment":[131],"for":[132,151],"abnormality":[133],"recognition,":[134],"introduces":[136],"region-level":[138],"contrastive":[139],"learning":[140],"based":[141],"consistency.":[144],"These":[145],"aligned":[146],"embeddings":[147],"serve":[148],"as":[149],"priors":[150],"generation,":[153],"enabling":[154],"provide":[158],"interpretable":[159],"evidence.":[161],"Extensive":[162],"experiments":[163],"demonstrate":[164],"SS-ACL,":[166],"without":[167],"relying":[168],"(i)":[172],"generates":[173],"grounded":[177],"reports-outperforming":[178],"state-of-the-art":[179],"10%":[182],"lexical":[184],"accuracy":[185],"25%":[187],"efficacy,":[190],"(ii)":[192],"achieves":[193],"competitive":[194],"performance":[195],"various":[197],"downstream":[198],"tasks,":[200],"surpassing":[201],"current":[202],"leading":[203],"foundation":[205],"models":[206],"8%":[208],"zero-shot":[210],"grounding.":[212],"Our":[213],"code":[214],"is":[215],"available":[216],"at":[217],"https://github.com/kaelsunkiller/ssacl.":[218]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-25T00:00:00"}