{"id":"https://openalex.org/W4379056220","doi":"https://doi.org/10.1007/s11042-023-15884-y","title":"Enhanced descriptive captioning model for histopathological patches","display_name":"Enhanced descriptive captioning model for histopathological patches","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4379056220","doi":"https://doi.org/10.1007/s11042-023-15884-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11042-023-15884-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-023-15884-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-15884-y.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-15884-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040420095","display_name":"Samar Elbedwehy","orcid":"https://orcid.org/0000-0002-2187-0174"},"institutions":[{"id":"https://openalex.org/I130309236","display_name":"Kafrelsheikh University","ror":"https://ror.org/04a97mm30","country_code":"EG","type":"education","lineage":["https://openalex.org/I130309236"]},{"id":"https://openalex.org/I159247623","display_name":"Mansoura University","ror":"https://ror.org/01k8vtd75","country_code":"EG","type":"education","lineage":["https://openalex.org/I159247623"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Samar Elbedwehy","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer and Information Science, Mansoura University, Mansoura, Egypt","Department of Data Science, Faculty of Artificial Intelligence, Kafrelsheikh University, Kafr El-Sheikh, Egypt"],"raw_orcid":"https://orcid.org/0000-0002-2187-0174","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer and Information Science, Mansoura University, Mansoura, Egypt","institution_ids":["https://openalex.org/I159247623"]},{"raw_affiliation_string":"Department of Data Science, Faculty of Artificial Intelligence, Kafrelsheikh University, Kafr El-Sheikh, Egypt","institution_ids":["https://openalex.org/I130309236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022601935","display_name":"T. Medhat","orcid":null},"institutions":[{"id":"https://openalex.org/I130309236","display_name":"Kafrelsheikh University","ror":"https://ror.org/04a97mm30","country_code":"EG","type":"education","lineage":["https://openalex.org/I130309236"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"T. Medhat","raw_affiliation_strings":["Department of Electrical Engineering, Faculty of Engineering, Kafrelsheikh University, Kafr El-Sheikh, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Faculty of Engineering, Kafrelsheikh University, Kafr El-Sheikh, Egypt","institution_ids":["https://openalex.org/I130309236"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047851200","display_name":"Taher Hamza","orcid":"https://orcid.org/0000-0001-5735-8562"},"institutions":[{"id":"https://openalex.org/I159247623","display_name":"Mansoura University","ror":"https://ror.org/01k8vtd75","country_code":"EG","type":"education","lineage":["https://openalex.org/I159247623"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Taher Hamza","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer and Information Science, Mansoura University, Mansoura, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer and Information Science, Mansoura University, Mansoura, Egypt","institution_ids":["https://openalex.org/I159247623"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028856944","display_name":"Mohammed F. Alrahmawy","orcid":"https://orcid.org/0000-0001-8978-8268"},"institutions":[{"id":"https://openalex.org/I159247623","display_name":"Mansoura University","ror":"https://ror.org/01k8vtd75","country_code":"EG","type":"education","lineage":["https://openalex.org/I159247623"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Mohammed F. Alrahmawy","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer and Information Science, Mansoura University, Mansoura, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer and Information Science, Mansoura University, Mansoura, Egypt","institution_ids":["https://openalex.org/I159247623"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040420095"],"corresponding_institution_ids":["https://openalex.org/I130309236","https://openalex.org/I159247623"],"apc_list":null,"apc_paid":null,"fwci":1.1775,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80684399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"83","issue":"12","first_page":"36645","last_page":"36664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9819999933242798,"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/T10862","display_name":"AI in cancer detection","score":0.9251000285148621,"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/closed-captioning","display_name":"Closed captioning","score":0.9321352243423462},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.903563916683197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6934932470321655},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6000658869743347},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46287208795547485},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45403122901916504},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43933457136154175},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4183594584465027},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.416690468788147},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3998638391494751},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3828446865081787},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3301035165786743}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9321352243423462},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.903563916683197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6934932470321655},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6000658869743347},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46287208795547485},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45403122901916504},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43933457136154175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4183594584465027},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.416690468788147},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3998638391494751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3828446865081787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3301035165786743},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11042-023-15884-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-023-15884-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-15884-y.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11042-023-15884-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11042-023-15884-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11042-023-15884-y.pdf","source":{"id":"https://openalex.org/S110206669","display_name":"Multimedia Tools and Applications","issn_l":"1380-7501","issn":["1380-7501","1573-7721"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Tools and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4379056220.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1969616664","https://openalex.org/W2097117768","https://openalex.org/W2101105183","https://openalex.org/W2149557440","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2302086703","https://openalex.org/W2463955103","https://openalex.org/W2791738141","https://openalex.org/W2914329496","https://openalex.org/W2943885184","https://openalex.org/W2946450307","https://openalex.org/W2977433292","https://openalex.org/W2997056851","https://openalex.org/W3034971973","https://openalex.org/W3035524453","https://openalex.org/W3103896273","https://openalex.org/W3134835849","https://openalex.org/W3138516171","https://openalex.org/W3164435055","https://openalex.org/W3175515048","https://openalex.org/W3177029767","https://openalex.org/W3185507966","https://openalex.org/W4221153690","https://openalex.org/W4312443924","https://openalex.org/W4312887059","https://openalex.org/W6602254124","https://openalex.org/W6605520847"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3009270862"],"abstract_inverted_index":{"Abstract":[0],"The":[1,72,90],"interpretation":[2],"of":[3,14,26,55,93,100,126,189,191,208,253],"medical":[4,94],"images":[5],"into":[6],"a":[7,11,39,108,219,246,251],"natural":[8,34],"language":[9,35,221,269],"is":[10,38,225],"developing":[12],"field":[13,22],"artificial":[15,27],"intelligence":[16,28],"(AI)":[17],"called":[18],"image":[19,63,74,79,95,102,134,262],"captioning.":[20],"This":[21,37],"integrates":[23],"two":[24,140,255],"branches":[25],"which":[29,224],"are":[30],"computer":[31],"vision":[32,147,164,192],"and":[33,48,64,153,158,160,171,196,258],"processing.":[36],"challenging":[40],"topic":[41],"that":[42,244,249],"goes":[43],"beyond":[44],"object":[45],"recognition,":[46],"segmentation,":[47],"classification":[49],"since":[50],"it":[51],"demands":[52],"an":[53,62,78,101,120,174,261],"understanding":[54],"the":[56,86,133,163,180,202,209,212,237,254,267,273,277],"relationships":[57],"between":[58],"various":[59],"components":[60],"in":[61,115,230],"how":[65],"these":[66],"objects":[67],"function":[68],"as":[69,173,260],"visual":[70],"representations.":[71],"content-based":[73],"retrieval":[75],"(CBIR)":[76],"uses":[77,250],"captioning":[80,96,247],"model":[81,122,223,271],"to":[82,118,178,198,228,233],"generate":[83],"captions":[84,125],"for":[85,123],"user":[87],"query":[88],"image.":[89,210],"common":[91],"architecture":[92],"systems":[97],"consists":[98],"mainly":[99],"feature":[103,135,206,263],"extractor":[104],"subsystem":[105],"followed":[106],"by":[107],"caption":[109,213],"generation":[110,214],"lingual":[111,215],"subsystem.":[112],"We":[113],"aim":[114],"this":[116],"paper":[117],"build":[119],"optimized":[121],"histopathological":[124],"stomach":[127],"adenocarcinoma":[128],"endoscopic":[129],"biopsy":[130],"specimens.":[131],"For":[132,211],"extraction":[136],"subsystem,":[137,216],"we":[138,143,184,217],"did":[139],"evaluations;":[141],"first,":[142],"tested":[144,185,218],"5":[145],"different":[146,187],"models":[148,165,193,256],"(VGG,":[149],"ResNet,":[150],"PVT,":[151],"SWIN-Large,":[152],"ConvNEXT-Large)":[154,197],"using":[155],"(LSTM,":[156],"RNN,":[157],"bidirectional-RNN)":[159],"then":[161],"compare":[162],"with":[166,266],"(LSTM-without":[167],"augmentation,":[168],"LSTM-with":[169],"augmentation":[170],"BioLinkBERT-Large":[172,226,268],"embedding":[175,222,270],"layer-with":[176],"augmentation)":[177],"find":[179],"accurate":[181,239],"one.":[182],"Second,":[183],"3":[186],"concatenations":[188],"pairs":[190],"(SWIN-Large,":[194],"PVT_v2_b5,":[195],"get":[199],"among":[200,276],"them":[201,236],"most":[203,238],"expressive":[204],"extracted":[205],"vector":[207],"pre-trained":[220],"compared":[227],"LSTM":[229],"both":[231],"evaluations,":[232],"select":[234],"from":[235],"model.":[240],"Our":[241],"experiments":[242],"showed":[243],"building":[245],"system":[248],"concatenation":[252],"ConvNEXT-Large":[257],"PVT_v2_b5":[259],"extractor,":[264],"combined":[265],"produces":[272],"best":[274],"results":[275],"other":[278],"combinations.":[279]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-21T23:30:37.877113","created_date":"2025-10-10T00:00:00"}