{"id":"https://openalex.org/W4392130711","doi":"https://doi.org/10.1007/s40747-024-01359-6","title":"ViT-UperNet: a hybrid vision transformer with unified-perceptual-parsing network for medical image segmentation","display_name":"ViT-UperNet: a hybrid vision transformer with unified-perceptual-parsing network for medical image segmentation","publication_year":2024,"publication_date":"2024-02-24","ids":{"openalex":"https://openalex.org/W4392130711","doi":"https://doi.org/10.1007/s40747-024-01359-6"},"language":"en","primary_location":{"id":"doi:10.1007/s40747-024-01359-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01359-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01359-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"Complex & Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01359-6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang Ruiping","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yang Ruiping","raw_affiliation_strings":["College of Economics & Management, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Economics & Management, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045075979","display_name":"Kun Liu","orcid":"https://orcid.org/0000-0002-7349-8730"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liu Kun","raw_affiliation_strings":["College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China"],"raw_orcid":"https://orcid.org/0000-0002-7349-8730","affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079048949","display_name":"Shaohua Xu","orcid":"https://orcid.org/0000-0002-0422-1180"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xu Shaohua","raw_affiliation_strings":["College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yin Jian","orcid":null},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yin Jian","raw_affiliation_strings":["College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028310716","display_name":"Zhen Zhang","orcid":"https://orcid.org/0000-0001-6966-0208"},"institutions":[{"id":"https://openalex.org/I80143920","display_name":"Shandong University of Science and Technology","ror":"https://ror.org/04gtjhw98","country_code":"CN","type":"education","lineage":["https://openalex.org/I80143920"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhang Zhen","raw_affiliation_strings":["College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Engineering, Shandong University of Science and Technology, Qianwangang Road, Qingdao, 266590, Shandong, China","institution_ids":["https://openalex.org/I80143920"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028310716","https://openalex.org/A5045075979","https://openalex.org/A5079048949"],"corresponding_institution_ids":["https://openalex.org/I80143920"],"apc_list":{"value":1320,"currency":"GBP","value_usd":1619},"apc_paid":{"value":1320,"currency":"GBP","value_usd":1619},"fwci":2.8569,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91604004,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"10","issue":"3","first_page":"3819","last_page":"3831"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9973000288009644,"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/parsing","display_name":"Parsing","score":0.8163902759552002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6091790795326233},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5980504155158997},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5557270050048828},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.5396997332572937},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5270545482635498},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5237616896629333},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.43979576230049133},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.41184067726135254},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3844013214111328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35509276390075684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32882028818130493},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.194159597158432},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17139720916748047},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11187928915023804},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.1051996648311615},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.0696096122264862}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8163902759552002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6091790795326233},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5980504155158997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5557270050048828},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.5396997332572937},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5270545482635498},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5237616896629333},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.43979576230049133},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.41184067726135254},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3844013214111328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35509276390075684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32882028818130493},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.194159597158432},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17139720916748047},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11187928915023804},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.1051996648311615},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0696096122264862}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s40747-024-01359-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01359-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01359-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"Complex & Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:df6986c0dcb6402bb186b43f5a804e24","is_oa":true,"landing_page_url":"https://doaj.org/article/df6986c0dcb6402bb186b43f5a804e24","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Complex & Intelligent Systems, Vol 10, Iss 3, Pp 3819-3831 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s40747-024-01359-6","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s40747-024-01359-6","pdf_url":"https://link.springer.com/content/pdf/10.1007/s40747-024-01359-6.pdf","source":{"id":"https://openalex.org/S3035462843","display_name":"Complex & Intelligent Systems","issn_l":"2198-6053","issn":["2198-6053","2199-4536"],"is_oa":true,"is_in_doaj":true,"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":"Complex & Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392130711.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2804047627","https://openalex.org/W2884436604","https://openalex.org/W2884822772","https://openalex.org/W2905338897","https://openalex.org/W2907750714","https://openalex.org/W2949736877","https://openalex.org/W2952370363","https://openalex.org/W2963855133","https://openalex.org/W2964227007","https://openalex.org/W2964309882","https://openalex.org/W3015788359","https://openalex.org/W3092462072","https://openalex.org/W3092557781","https://openalex.org/W3110386488","https://openalex.org/W3138516171","https://openalex.org/W3171516518","https://openalex.org/W3197217317","https://openalex.org/W3204166336","https://openalex.org/W3216802946","https://openalex.org/W4206693420","https://openalex.org/W4312290555","https://openalex.org/W4312307873","https://openalex.org/W4312358791","https://openalex.org/W4312702383","https://openalex.org/W4312815172","https://openalex.org/W4313156423","https://openalex.org/W4315705623","https://openalex.org/W4320713051","https://openalex.org/W4321232185","https://openalex.org/W6600213211"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W2083429127","https://openalex.org/W2358855848","https://openalex.org/W2142145894","https://openalex.org/W2033808215","https://openalex.org/W2359307945","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Abstract":[0],"The":[1,47,183,206],"existing":[2],"image":[3,32,48,169],"semantic":[4,94,105],"segmentation":[5,131,170],"models":[6],"have":[7],"low":[8,54],"accuracy":[9,185],"in":[10,39,213],"detecting":[11],"tiny":[12],"targets":[13],"or":[14],"multi-targets":[15],"at":[16],"overlapping":[17],"regions.":[18],"This":[19],"work":[20],"proposes":[21],"a":[22,40,70,75,81,137],"hybrid":[23],"vision":[24,41],"transformer":[25,42],"with":[26,64,125,202],"unified-perceptual-parsing":[27,71],"network":[28,72,78],"(ViT-UperNet)":[29],"for":[30,86,146,181,218],"medical":[31,214],"segmentation.":[33,95,182],"A":[34],"self-attention":[35],"mechanism":[36],"is":[37,144,186,191,196],"embedded":[38],"to":[43,55,118,129],"extract":[44,123],"multi-level":[45],"features.":[46],"features":[49,92,124],"are":[50,163,179,199],"extracted":[51],"hierarchically":[52],"from":[53],"high":[56],"dimensions":[57],"using":[58],"4":[59],"groups":[60],"of":[61,89,158,211],"Transformer":[62],"blocks":[63],"different":[65],"numbers.":[66],"Then,":[67],"it":[68],"uses":[69],"based":[73],"on":[74,107,165],"feature":[76,160],"pyramid":[77,82],"(FPN)":[79],"and":[80,93,102,122,154,174,177,193,221],"pooling":[83],"module":[84],"(PPM)":[85],"the":[87,114,134,150,156,159,172,188,203,209,219],"fusion":[88],"multi-scale":[90],"contextual":[91],"FPN":[96],"can":[97,111],"naturally":[98],"use":[99,113],"hierarchical":[100],"features,":[101],"generate":[103],"strong":[104],"information":[106,128],"all":[108],"scales.":[109],"PPM":[110],"better":[112],"global":[115,126],"prior":[116],"knowledge":[117],"understand":[119],"complex":[120],"scenes,":[121],"context":[127],"improve":[130],"results.":[132],"In":[133],"training":[135],"process,":[136],"scalable":[138],"self-supervised":[139],"learner":[140],"named":[141],"masked":[142],"autoencoder":[143],"used":[145],"pre-training,":[147],"which":[148,198],"strengthens":[149],"visual":[151],"representation":[152],"ability":[153],"improves":[155],"efficiency":[157],"learning.":[161],"Experiments":[162],"conducted":[164],"cardiac":[166],"magnetic":[167],"resonance":[168],"where":[171],"left":[173],"right":[175],"atrium":[176],"ventricle":[178],"selected":[180],"pixels":[184],"93.85%,":[187],"Dice":[189],"coefficient":[190],"92.61%":[192],"Hausdorff":[194],"distance":[195],"11.16,":[197],"improved":[200],"compared":[201],"other":[204],"methods.":[205],"results":[207],"show":[208],"superiority":[210],"Vit-UperNet":[212],"images":[215],"segmentation,":[216],"especially":[217],"low-recognition":[220],"serious-occlusion":[222],"targets.":[223]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}