{"id":"https://openalex.org/W4311001826","doi":"https://doi.org/10.48550/arxiv.2212.04497","title":"UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation","display_name":"UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4311001826","doi":"https://doi.org/10.48550/arxiv.2212.04497"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2212.04497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/2212.04497","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079602015","display_name":"Abdelrahman Shaker","orcid":"https://orcid.org/0000-0001-7651-4057"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaker, Abdelrahman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034370385","display_name":"Muhammad Maaz","orcid":"https://orcid.org/0000-0002-3869-631X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maaz, Muhammad","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064948724","display_name":"Hanoona Rasheed","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rasheed, Hanoona","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101483978","display_name":"Salman Khan","orcid":"https://orcid.org/0000-0001-8732-3395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Salman","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418319","display_name":"Ming\u2013Hsuan Yang","orcid":"https://orcid.org/0000-0003-4848-2304"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ming-Hsuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Fahad Shahbaz","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.854089,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995,"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":0.9995,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9993,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9989,"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/discriminative-model","display_name":"Discriminative model","score":0.51655257},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.46851182},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.42672306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7307432},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.665233},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.62789506},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.51655257},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.50918335},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.46851182},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46341318},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45732796},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.42672306},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4004709},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12347281},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.105528295},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2212.04497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2212.04497","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2212.04497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.65}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4366341510","https://openalex.org/W3104750253","https://openalex.org/W3021239166","https://openalex.org/W2906397153","https://openalex.org/W2586273397","https://openalex.org/W2483429559","https://openalex.org/W2390936256","https://openalex.org/W2385445039","https://openalex.org/W2016385589","https://openalex.org/W2009559548"],"abstract_inverted_index":{"Owing":[0],"to":[1,33,46,143,237],"the":[2,18,21,27,38,57,102,144,158,176,193,238,242],"success":[3],"of":[4,26,89,98,104,123,160,195,200,217,226,231],"transformer":[5,19],"models,":[6,20],"recent":[7],"works":[8],"study":[9],"their":[10],"applicability":[11],"in":[12,52,87,198,229,241],"3D":[13,60,70],"medical":[14,54,71],"segmentation":[15,73,81],"tasks.":[16],"Within":[17],"self-attention":[22,39],"mechanism":[23],"is":[24,101,136],"one":[25],"main":[28],"building":[29],"blocks":[30],"that":[31,77,112,166],"strives":[32],"capture":[34],"long-range":[35],"dependencies.":[36],"However,":[37],"operation":[40],"has":[41],"quadratic":[42],"complexity":[43,140],"which":[44],"proves":[45],"be":[47],"a":[48,69,105,121,168,210,214,224],"computational":[49],"bottleneck,":[50],"especially":[51],"volumetric":[53],"imaging,":[55],"where":[56],"inputs":[58],"are":[59],"with":[61,141,213,223],"numerous":[62],"slices.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,156],"propose":[68],"image":[72],"approach,":[74],"named":[75],"UNETR++,":[76],"offers":[78],"both":[79,201,232],"high-quality":[80],"masks":[82],"as":[83,85],"well":[84],"efficiency":[86,202],"terms":[88,199,230],"parameters,":[90],"compute":[91],"cost,":[92],"and":[93,116,129,153,162,190,203,234],"inference":[94],"speed.":[95],"The":[96],"core":[97],"our":[99,196,207],"design":[100],"introduction":[103],"novel":[106],"efficient":[107,137,222],"paired":[108],"attention":[109,134],"(EPA)":[110],"block":[111],"efficiently":[113],"learns":[114],"spatial":[115,128,133,152],"channel-wise":[117],"discriminative":[118],"features":[119],"using":[120],"pair":[122],"inter-dependent":[124],"branches":[125],"based":[126],"on":[127,183],"channel":[130],"attention.":[131],"Our":[132,180],"formulation":[135],"having":[138],"linear":[139],"respect":[142],"input":[145],"sequence":[146],"length.":[147],"To":[148],"enable":[149],"communication":[150],"between":[151],"channel-focused":[154],"branches,":[155],"share":[157],"weights":[159],"query":[161],"key":[163],"mapping":[164],"functions":[165],"provide":[167],"complimentary":[169],"benefit":[170],"(paired":[171],"attention),":[172],"while":[173,219],"also":[174],"reducing":[175],"overall":[177],"network":[178],"parameters.":[179],"extensive":[181],"evaluations":[182],"five":[184],"benchmarks,":[185],"Synapse,":[186,206],"BTCV,":[187],"ACDC,":[188],"BRaTs,":[189],"Decathlon-Lung,":[191],"reveal":[192],"effectiveness":[194],"contributions":[197],"accuracy.":[204],"On":[205],"UNETR++":[208],"sets":[209],"new":[211],"state-of-the-art":[212],"Dice":[215],"Score":[216],"87.2%,":[218],"being":[220],"significantly":[221],"reduction":[225],"over":[227],"71%":[228],"parameters":[233],"FLOPs,":[235],"compared":[236],"best":[239],"method":[240],"literature.":[243],"Code:":[244],"https://github.com/Amshaker/unetr_plus_plus.":[245]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4311001826","counts_by_year":[{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":9}],"updated_date":"2025-01-04T18:22:23.151237","created_date":"2022-12-22"}