{"id":"https://openalex.org/W4416772695","doi":"https://doi.org/10.1007/s10489-025-07009-9","title":"Harnessing transformer-based attention mechanisms for multi-scale feature fusion in medical image segmentation","display_name":"Harnessing transformer-based attention mechanisms for multi-scale feature fusion in medical image segmentation","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416772695","doi":"https://doi.org/10.1007/s10489-025-07009-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-025-07009-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-025-07009-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-07009-9.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","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/s10489-025-07009-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104202573","display_name":"Rabeea Fatma Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I28615091","display_name":"Kyonggi University","ror":"https://ror.org/032xf8h46","country_code":"KR","type":"education","lineage":["https://openalex.org/I28615091"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Rabeea Fatma Khan","raw_affiliation_strings":["Department of Computer Science, Graduate School, Kyonggi University, Suwon-si, 16227, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Graduate School, Kyonggi University, Suwon-si, 16227, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I28615091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059304496","display_name":"Mu Sook Lee","orcid":"https://orcid.org/0000-0002-0382-5564"},"institutions":[{"id":"https://openalex.org/I4210128080","display_name":"Keimyung University Dongsan Medical Center","ror":"https://ror.org/035r7hb75","country_code":"KR","type":"healthcare","lineage":["https://openalex.org/I4210128080"]},{"id":"https://openalex.org/I52010207","display_name":"Keimyung University","ror":"https://ror.org/00tjv0s33","country_code":"KR","type":"education","lineage":["https://openalex.org/I52010207"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mu Sook Lee","raw_affiliation_strings":["Department of Radiology, Keimyung University Dongsan Hospital, Daegue, 24601, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Department of Radiology, Keimyung University Dongsan Hospital, Daegue, 24601, Republic of Korea","institution_ids":["https://openalex.org/I52010207","https://openalex.org/I4210128080"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043316202","display_name":"Byoung-Dai Lee","orcid":"https://orcid.org/0000-0002-4028-6168"},"institutions":[{"id":"https://openalex.org/I28615091","display_name":"Kyonggi University","ror":"https://ror.org/032xf8h46","country_code":"KR","type":"education","lineage":["https://openalex.org/I28615091"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byoung-Dai Lee","raw_affiliation_strings":["Department of Computer Science, Graduate School, Kyonggi University, Suwon-si, 16227, Gyeonggi-do, South Korea","Division of AI and Computer Engineering, Kyonggi University, Suwon-si, 16227, Gyeonggi- do, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Graduate School, Kyonggi University, Suwon-si, 16227, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I28615091"]},{"raw_affiliation_string":"Division of AI and Computer Engineering, Kyonggi University, Suwon-si, 16227, Gyeonggi- do, South Korea","institution_ids":["https://openalex.org/I28615091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5104202573"],"corresponding_institution_ids":["https://openalex.org/I28615091"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36456342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":"17","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7760000228881836,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.7760000228881836,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.025599999353289604,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.023399999365210533,"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/encoder","display_name":"Encoder","score":0.661300003528595},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6470999717712402},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6273000240325928},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5396999716758728},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5224000215530396},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.520799994468689},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42160001397132874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4196000099182129},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4025999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.906000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6617000102996826},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.661300003528595},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6470999717712402},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6273000240325928},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4196000099182129},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3901999890804291},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35040000081062317},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3433000147342682},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.33070001006126404},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.31929999589920044},{"id":"https://openalex.org/C205372480","wikidata":"https://www.wikidata.org/wiki/Q210521","display_name":"Image resolution","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-025-07009-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-025-07009-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-07009-9.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10489-025-07009-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10489-025-07009-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10489-025-07009-9.pdf","source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3695139331","display_name":null,"funder_award_id":"2022R1A2C1007169","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G462355944","display_name":null,"funder_award_id":"RS-2020-NR049579","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416772695.pdf","grobid_xml":"https://content.openalex.org/works/W4416772695.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2021707668","https://openalex.org/W2194775991","https://openalex.org/W2991372685","https://openalex.org/W2997286550","https://openalex.org/W3168491317","https://openalex.org/W3172681723","https://openalex.org/W3203841574","https://openalex.org/W3204255739","https://openalex.org/W3208983378","https://openalex.org/W4212875960","https://openalex.org/W4221163766","https://openalex.org/W4295940432","https://openalex.org/W4302363625","https://openalex.org/W4312568229","https://openalex.org/W4321232185","https://openalex.org/W4384159609","https://openalex.org/W4386561400","https://openalex.org/W4388973748","https://openalex.org/W4390345094","https://openalex.org/W4399980280","https://openalex.org/W4400881081"],"related_works":[],"abstract_inverted_index":{"Extensive":[0,159],"research":[1],"has":[2],"focused":[3],"on":[4],"developing":[5],"efficient":[6,203],"and":[7,30,64,67,91,111,121,140,156,163,169,188,202],"accurate":[8],"solutions":[9],"for":[10,206],"the":[11,115,195],"critical":[12],"task":[13],"of":[14,149,197],"medical":[15,207],"image":[16,208],"segmentation.":[17,209],"Approaches":[18],"have":[19,84],"evolved":[20],"from":[21,53],"hand-crafted":[22],"pipelines":[23],"to":[24,33,55,93],"deep":[25],"convolutional":[26],"neural":[27],"networks":[28],"(CNNs),":[29],"more":[31],"recently,":[32],"Transformer-based":[34],"hybrid":[35,157],"models.":[36,158],"Among":[37],"these,":[38],"hierarchical":[39,150],"encoder\u2013decoder":[40,151],"architectures":[41],"remain":[42],"prevalent,":[43],"where":[44],"skip":[45,59,82,104,116,130],"connections":[46,60,131],"are":[47,88],"crucial":[48],"in":[49,62],"transmitting":[50],"spatial":[51],"features":[52,72],"encoders":[54],"decoders.":[56],"However,":[57],"conventional":[58],"operate":[61],"static":[63],"passive":[65],"modes,":[66],"cannot":[68],"adaptively":[69],"fuse":[70],"multi-scale":[71,123],"or":[73],"capture":[74],"semantic":[75,134],"relationships":[76],"across":[77,126,161],"resolution":[78],"levels.":[79],"Although":[80],"attention-based":[81],"enhancements":[83],"been":[85],"proposed,":[86],"they":[87],"often":[89],"architecture-specific":[90],"difficult":[92],"generalize.":[94],"In":[95],"this":[96],"study,":[97],"we":[98],"propose":[99],"TransSkip,":[100],"a":[101,147,200],"novel":[102],"transformer-based":[103],"connection":[105],"module":[106],"that":[107,178],"embeds":[108],"both":[109],"self-attention":[110],"cross-attention":[112],"directly":[113],"within":[114],"path.":[117],"This":[118],"enables":[119],"dynamic":[120],"learnable":[122],"feature":[124],"fusion":[125],"encoder":[127],"levels,":[128],"transforming":[129],"into":[132],"active":[133],"reasoning":[135],"pathways.":[136],"TransSkip":[137,179,198],"is":[138],"modular":[139],"architecture":[141],"agnostic,":[142],"supporting":[143],"seamless":[144],"integration":[145],"with":[146,184],"range":[148],"networks,":[152],"including":[153],"CNN-based,":[154],"Transformer-based,":[155],"experiments":[160],"2D":[162],"3D":[164],"datasets":[165],"(BUSI,":[166],"Kvasir-SEG,":[167],"MSD-Spleen)":[168],"multiple":[170],"network":[171],"backbones":[172],"(U-Net,":[173],"TransUNet,":[174],"TransAttUNet,":[175],"MCV-UNet)":[176],"demonstrate":[177],"consistently":[180],"improves":[181],"segmentation":[182],"accuracy,":[183],"statistically":[185],"significant":[186],"gains":[187],"minimal":[189],"parameter":[190],"overhead.":[191],"These":[192],"results":[193],"highlight":[194],"potential":[196],"as":[199],"generalizable":[201],"architectural":[204],"enhancement":[205]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}