{"id":"https://openalex.org/W4375869151","doi":"https://doi.org/10.1109/icassp49357.2023.10096379","title":"Optimizing Vision Transformers for Medical Image Segmentation","display_name":"Optimizing Vision Transformers for Medical Image Segmentation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869151","doi":"https://doi.org/10.1109/icassp49357.2023.10096379"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/292461/1/292461.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073540330","display_name":"Qianying Liu","orcid":"https://orcid.org/0000-0003-0765-7243"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qianying Liu","raw_affiliation_strings":["University of Glasgow,School of Computing Science","School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076295200","display_name":"Chaitanya Kaul","orcid":"https://orcid.org/0000-0003-4893-6222"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chaitanya Kaul","raw_affiliation_strings":["University of Glasgow,School of Computing Science","School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384874","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0003-1581-8369"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University of Warwick"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001331936","display_name":"Christos Anagnostopoulos","orcid":"https://orcid.org/0000-0003-1517-6757"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christos Anagnostopoulos","raw_affiliation_strings":["University of Glasgow,School of Computing Science","School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070918132","display_name":"Roderick Murray\u2010Smith","orcid":"https://orcid.org/0000-0003-4228-7962"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Roderick Murray-Smith","raw_affiliation_strings":["University of Glasgow,School of Computing Science","School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082776788","display_name":"Fani Deligianni","orcid":"https://orcid.org/0000-0003-1306-5017"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fani Deligianni","raw_affiliation_strings":["University of Glasgow,School of Computing Science","School of Computing Science, University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network 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/T10036","display_name":"Advanced Neural Network 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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.998199999332428,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9962999820709229,"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/computer-science","display_name":"Computer science","score":0.7646929025650024},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.726158857345581},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6302014589309692},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5920372009277344},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5811710357666016},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4488093852996826},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3699972927570343},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3543025851249695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10120067000389099},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09795916080474854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646929025650024},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.726158857345581},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6302014589309692},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5920372009277344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5811710357666016},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4488093852996826},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3699972927570343},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3543025851249695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10120067000389099},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09795916080474854},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:292461","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/63358.html>,","pdf_url":"https://eprints.gla.ac.uk/292461/1/292461.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:292461","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/63358.html>,","pdf_url":"https://eprints.gla.ac.uk/292461/1/292461.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6166417340","display_name":null,"funder_award_id":"EP/W01212X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4375869151.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2804047627","https://openalex.org/W2884436604","https://openalex.org/W2888358068","https://openalex.org/W2962725274","https://openalex.org/W3015788359","https://openalex.org/W3094502228","https://openalex.org/W3127751679","https://openalex.org/W3138516171","https://openalex.org/W3164280370","https://openalex.org/W3168491317","https://openalex.org/W3198035652","https://openalex.org/W3199613405","https://openalex.org/W3203480968","https://openalex.org/W3204166336","https://openalex.org/W3204700807","https://openalex.org/W3212933375","https://openalex.org/W4214493665","https://openalex.org/W4214634256","https://openalex.org/W4319300365","https://openalex.org/W4321232185","https://openalex.org/W4386561400","https://openalex.org/W6757817989","https://openalex.org/W6790275670","https://openalex.org/W6801350836","https://openalex.org/W6801589178","https://openalex.org/W6839435894","https://openalex.org/W6902762063"],"related_works":["https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4239306820","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W2947043951","https://openalex.org/W4399188509","https://openalex.org/W2318112981","https://openalex.org/W1522196789"],"abstract_inverted_index":{"For":[0],"medical":[1,59],"image":[2],"semantic":[3],"segmentation":[4],"(MISS),":[5],"Vision":[6],"Transformers":[7,52],"have":[8],"emerged":[9],"as":[10],"strong":[11],"alternatives":[12],"to":[13,18,22,47,68],"convolutional":[14],"neural":[15],"networks":[16],"thanks":[17],"their":[19],"inherent":[20,130],"ability":[21,104],"capture":[23],"long-range":[24],"correlations.":[25],"However,":[26],"existing":[27],"research":[28],"uses":[29],"off-the-shelf":[30],"vision":[31],"Transformer":[32,85,116],"blocks":[33],"based":[34],"on":[35,57,64,149],"linear":[36],"projections":[37],"and":[38,44,62,83,101,125,134,151,157],"feature":[39],"processing":[40],"which":[41,90,119],"lack":[42],"spatial":[43,100,132],"local":[45,102],"context":[46,133],"refine":[48],"organ":[49],"boundaries.":[50],"Furthermore,":[51],"do":[53],"not":[54],"generalize":[55],"well":[56],"small":[58],"imaging":[60],"datasets":[61,153],"rely":[63],"large-scale":[65],"pre-training":[66,141],"due":[67],"limited":[69],"inductive":[70,135],"biases.":[71,136],"To":[72],"address":[73],"these":[74],"problems,":[75],"we":[76],"demonstrate":[77,138],"the":[78],"design":[79,96],"of":[80,105],"a":[81,94],"compact":[82],"accurate":[84],"network":[86],"for":[87,97,128],"MISS,":[88],"CS-Unet,":[89],"introduces":[91],"convolutions":[92,121],"in":[93],"multi-stage":[95],"hierarchically":[98],"enhancing":[99],"modeling":[103],"Transformers.":[106],"This":[107],"is":[108,163],"mainly":[109],"achieved":[110],"by":[111,146],"our":[112],"well-designed":[113],"Convolutional":[114],"Swin":[115],"(CST)":[117],"block":[118],"merges":[120],"with":[122,154],"Multi-Head":[123],"Self-Attention":[124],"Feed-Forward":[126],"Networks":[127],"providing":[129],"localized":[131],"Experiments":[137],"CS-Unet":[139],"without":[140],"out-":[142],"performs":[143],"other":[144],"counterparts":[145],"large":[147],"margins":[148],"multi-organ":[150],"cardiac":[152],"fewer":[155],"parameters":[156],"achieves":[158],"state-of-the-art":[159],"performance.":[160],"Our":[161],"code":[162],"available":[164],"at":[165],"Github":[166],"<sup":[167],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[168],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[169],".":[170]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}