{"id":"https://openalex.org/W4410636773","doi":"https://doi.org/10.1145/3701716.3717549","title":"Explainable Medical Image Captioning","display_name":"Explainable Medical Image Captioning","publication_year":2025,"publication_date":"2025-05-08","ids":{"openalex":"https://openalex.org/W4410636773","doi":"https://doi.org/10.1145/3701716.3717549"},"language":"en","primary_location":{"id":"doi:10.1145/3701716.3717549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717549","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717549","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717549","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062177671","display_name":"Md. Sarwar Kamal","orcid":"https://orcid.org/0000-0002-1945-821X"},"institutions":[{"id":"https://openalex.org/I153230381","display_name":"Charles Sturt University","ror":"https://ror.org/00wfvh315","country_code":"AU","type":"education","lineage":["https://openalex.org/I153230381"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Md Sarwar Kamal","raw_affiliation_strings":["Charles Sturt University, Albury, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-1945-821X","affiliations":[{"raw_affiliation_string":"Charles Sturt University, Albury, NSW, Australia","institution_ids":["https://openalex.org/I153230381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009554749","display_name":"Sonia Farhana Nimmy","orcid":"https://orcid.org/0000-0003-1788-1329"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sonia Farhana Nimmy","raw_affiliation_strings":["UNSW, Canberra, Canberra, ACT, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1788-1329","affiliations":[{"raw_affiliation_string":"UNSW, Canberra, Canberra, ACT, Australia","institution_ids":["https://openalex.org/I188329596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065820146","display_name":"Rafiqul Islam","orcid":"https://orcid.org/0000-0001-8317-5727"},"institutions":[{"id":"https://openalex.org/I153230381","display_name":"Charles Sturt University","ror":"https://ror.org/00wfvh315","country_code":"AU","type":"education","lineage":["https://openalex.org/I153230381"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Md Rafiqul Islam","raw_affiliation_strings":["Charles Sturt University, Albury, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8317-5727","affiliations":[{"raw_affiliation_string":"Charles Sturt University, Albury, NSW, Australia","institution_ids":["https://openalex.org/I153230381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077006200","display_name":"Usman Naseem","orcid":"https://orcid.org/0000-0003-0191-7171"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Usman Naseem","raw_affiliation_strings":["Macquarie University, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0191-7171","affiliations":[{"raw_affiliation_string":"Macquarie University, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062177671"],"corresponding_institution_ids":["https://openalex.org/I153230381"],"apc_list":null,"apc_paid":null,"fwci":2.2554,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8797197,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2253","last_page":"2261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9878000020980835,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9868000149726868,"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/closed-captioning","display_name":"Closed captioning","score":0.9408137202262878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6866225004196167},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5999253988265991},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5157065987586975},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46956634521484375}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9408137202262878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6866225004196167},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5999253988265991},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5157065987586975},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46956634521484375}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3701716.3717549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717549","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717549","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:publications/6a027104-6c6f-462f-89e9-e372e4c6dee7","is_oa":true,"landing_page_url":"https://researchoutput.csu.edu.au/en/publications/6a027104-6c6f-462f-89e9-e372e4c6dee7","pdf_url":null,"source":{"id":"https://openalex.org/S7407055442","display_name":"Charles Sturt University Research Output (CRO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamal, M S, Nimmy, S F, Islam, R & Naseem, U 2025, Explainable medical image captioning. in WWW Companion 2025 - Companion Proceedings of the ACM Web Conference 2025. WWW Companion 2025 - Companion Proceedings of the ACM Web Conference 2025, Association for Computing Machinery (ACM), pp. 2253-2261, 2025 ACM Web Conference , Sydney, New South Wales, Australia, 28/04/25. https://doi.org/10.1145/3701716.3717549","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3701716.3717549","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3701716.3717549","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3701716.3717549","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Companion Proceedings of the ACM on Web Conference 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410636773.pdf","grobid_xml":"https://content.openalex.org/works/W4410636773.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2611650229","https://openalex.org/W2770165365","https://openalex.org/W2963967185","https://openalex.org/W2995140071","https://openalex.org/W3033896008","https://openalex.org/W3096809860","https://openalex.org/W3098325931","https://openalex.org/W3101156210","https://openalex.org/W3119640832","https://openalex.org/W3164654615","https://openalex.org/W3175316843","https://openalex.org/W3216130706","https://openalex.org/W4220716465","https://openalex.org/W4285176735","https://openalex.org/W4310854123","https://openalex.org/W4312549535","https://openalex.org/W4315473444","https://openalex.org/W4315750691","https://openalex.org/W4317879851","https://openalex.org/W4321021687","https://openalex.org/W4323275954","https://openalex.org/W4366393884","https://openalex.org/W4375809566","https://openalex.org/W4382998707","https://openalex.org/W4385192740","https://openalex.org/W4385757471","https://openalex.org/W4385805130","https://openalex.org/W4386607626","https://openalex.org/W4387415104","https://openalex.org/W4389828756","https://openalex.org/W6959643953"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"the":[1,37,88,121,129,134,166,170,187,191,205,210,215,219,229,276,292],"age":[2],"of":[3,39,72,90,136,169,195,204,214],"current":[4],"information":[5],"superhighways,":[6],"it":[7,298],"is":[8,95,183,225,241],"essential":[9],"to":[10,25,35,78,132,227,287,303],"apply":[11,264],"Large":[12],"Language":[13],"Models":[14],"Using":[15],"Multi-modal":[16],"Data":[17],"for":[18,47,97,127,150,275],"User":[19],"Modeling":[20],"in":[21,60,102,153,243],"medical":[22,40,50,104,130,171,177,196,206,246,304],"data":[23,247],"analysis":[24],"enhance":[26,165],"accuracy,":[27,70],"contextual":[28,73,167],"understanding,":[29,74],"and":[30,55,75,100,141,160,212,235,250,261,269,278,301],"interpretability.":[31],"This":[32,181,198,239],"research":[33],"aims":[34],"transform":[36],"landscape":[38],"imaging":[41],"by":[42,185,190],"introducing":[43],"an":[44],"interpretable":[45],"approach":[46],"generating":[48],"precise":[49],"captions":[51],"from":[52],"X-ray":[53],"images":[54,131],"associated":[56],"data.":[57],"Current":[58],"methods":[59],"this":[61],"domain":[62],"often":[63],"have":[64],"some":[65],"limitations":[66],"such":[67],"as":[68],"insufficient":[69],"lack":[71],"limited":[76],"ability":[77],"provide":[79,288],"explainable":[80,91,118],"results.":[81],"Addressing":[82],"these":[83],"challenges,":[84],"our":[85,256],"work":[86],"emphasizes":[87],"importance":[89],"AI":[92],"(XAI),":[93],"which":[94],"crucial":[96],"enhancing":[98,142],"trust":[99],"reliability":[101],"automated":[103],"diagnostics.":[105],"We":[106],"propose":[107],"a":[108,124,175,201,222],"novel":[109],"framework":[110,122],"that":[111,255],"integrates":[112],"advanced":[113],"deep":[114],"learning":[115],"techniques":[116,284],"with":[117,193],"AI.":[119],"Initially,":[120],"employs":[123],"U-net":[125],"architecture":[126],"pre-processing":[128],"identify":[133],"regions":[135],"interests":[137],"(ROIs),":[138],"effectively":[139],"isolating":[140],"relevant":[143],"features.":[144],"The":[145],"Vision":[146],"Transformer":[147],"(ViT),":[148],"known":[149],"its":[151],"effectiveness":[152],"handling":[154],"image":[155,277],"data,":[156,280],"extracts":[157],"critical":[158],"features":[159,232],"generates":[161],"tokens.":[162,197],"To":[163,253],"further":[164],"understanding":[168,203],"images,":[172],"we":[173,263],"construct":[174],"comprehensive":[176],"language":[178,223],"graph":[179,182],"(MLG).":[180],"formed":[184],"integrating":[186],"tokens":[188],"generated":[189,216],"ViT":[192],"corpus":[194],"integration":[199],"enables":[200],"deeper":[202],"context,":[207],"significantly":[208],"improving":[209],"accuracy":[211],"relevance":[213],"captions.":[217,238],"For":[218],"final":[220],"step,":[221],"decoder":[224],"employed":[226],"translate":[228],"rich,":[230],"context-aware":[231],"into":[233,248,291],"coherent":[234],"medically":[236],"accurate":[237],"step":[240],"pivotal":[242],"transforming":[244],"complex":[245],"understandable":[249],"actionable":[251],"insights.":[252],"ensure":[254],"model's":[257,293],"decisions":[258],"are":[259],"transparent":[260],"interpretable,":[262],"Layer-wise":[265],"Relevance":[266],"Propagation":[267],"(LRP)":[268],"Local":[270],"Interpretable":[271],"Model-agnostic":[272],"Explanations":[273],"(LIME)":[274],"text":[279],"respectively.":[281],"These":[282],"explainability":[283],"enable":[285],"us":[286],"clear":[289],"insights":[290],"reasoning":[294],"process,":[295],"thereby":[296],"making":[297],"more":[299],"trustworthy":[300],"accessible":[302],"professionals.":[305]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2025-10-10T00:00:00"}