{"id":"https://openalex.org/W7148989664","doi":"https://doi.org/10.48550/arxiv.2604.01612","title":"NEMESIS: Noise-suppressed Efficient MAE with Enhanced Superpatch Integration Strategy","display_name":"NEMESIS: Noise-suppressed Efficient MAE with Enhanced Superpatch Integration Strategy","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148989664","doi":"https://doi.org/10.48550/arxiv.2604.01612"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01612","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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.01612","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132873489","display_name":"Kyeonghun Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Kyeonghun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046000978","display_name":"Hyeonseok Jung","orcid":"https://orcid.org/0000-0001-8902-9624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jung, Hyeonseok","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132858721","display_name":"Youngung Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Youngung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126322351","display_name":"Hyunsu Go","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Go, Hyunsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126336636","display_name":"Eunseob Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Eunseob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132916468","display_name":"Seongbin Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Seongbin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032091387","display_name":"Junsu Lim","orcid":"https://orcid.org/0000-0002-8585-5686"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lim, Junsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132922419","display_name":"Jiwon Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jiwon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132867313","display_name":"Sumin Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Sumin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132894686","display_name":"Insung Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hwang, Insung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028602586","display_name":"Ken Ying-Kai Liao","orcid":"https://orcid.org/0000-0001-7815-8199"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Ken Ying-Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132898250","display_name":"Nam-Joon Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Nam-Joon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.26919999718666077,"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"}},"topics":[{"id":"https://openalex.org/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.26919999718666077,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.13420000672340393,"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/T12386","display_name":"Advanced X-ray and CT Imaging","score":0.11909999698400497,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6421999931335449},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.6283000111579895},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4945000112056732},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.49390000104904175},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41609999537467957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3817000091075897},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.37209999561309814},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.33739998936653137},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.3334999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153000235557556},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6421999931335449},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5547000169754028},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4945000112056732},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.49390000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33340001106262207},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.30379998683929443},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2687000036239624},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2779627259","wikidata":"https://www.wikidata.org/wiki/Q779763","display_name":"Pretext","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01612","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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.01612","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01612","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":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Volumetric":[0],"CT":[1,28,46],"imaging":[2],"is":[3,12,49],"essential":[4],"for":[5,111,181,191],"clinical":[6],"diagnosis,":[7],"yet":[8],"annotating":[9],"3D":[10,27,192],"volumes":[11],"expensive":[13],"and":[14,40,102,106,126,141,188],"time-consuming,":[15],"motivating":[16],"self-supervised":[17],"learning":[18],"(SSL)":[19],"from":[20],"unlabeled":[21],"data.":[22],"However,":[23],"applying":[24],"SSL":[25],"to":[26,32,171,178],"remains":[29],"challenging":[30],"due":[31],"the":[33,41,116,165,182],"high":[34],"memory":[35],"cost":[36,170],"of":[37,45,134,151,158],"full-volume":[38,183],"transformers":[39],"anisotropic":[42],"spatial":[43],"structure":[44],"data,":[47],"which":[48],"not":[50],"well":[51],"captured":[52],"by":[53],"conventional":[54],"masking":[55],"strategies.":[56],"We":[57],"propose":[58],"NEMESIS,":[59],"a":[60,87,123,127,131,145,186],"masked":[61],"autoencoder":[62],"(MAE)":[63],"framework":[64],"that":[65,96],"operates":[66],"on":[67],"local":[68],"128x128x128":[69],"superpatches,":[70],"enabling":[71],"memory-efficient":[72],"training":[73],"while":[74],"preserving":[75],"anatomical":[76],"detail.":[77],"NEMESIS":[78,108,121],"introduces":[79],"three":[80],"key":[81],"components:":[82],"(i)":[83],"noise-enhanced":[84],"reconstruction":[85],"as":[86],"pretext":[88],"task,":[89],"(ii)":[90],"Masked":[91],"Anatomical":[92],"Transformer":[93],"Blocks":[94],"(MATB)":[95],"perform":[97],"dual-masking":[98],"through":[99],"parallel":[100],"plane-wise":[101],"axis-wise":[103],"token":[104],"removal,":[105],"(iii)":[107],"Tokens":[109],"(NT)":[110],"cross-scale":[112],"context":[113],"aggregation.":[114],"On":[115],"BTCV":[117],"multi-organ":[118],"classification":[119],"benchmark,":[120],"with":[122,148],"frozen":[124],"backbone":[125],"linear":[128],"classifier":[129],"achieves":[130],"mean":[132],"AUROC":[133,157],"0.9633,":[135],"surpassing":[136],"fully":[137],"fine-tuned":[138],"SuPreM":[139],"(0.9493)":[140],"VoCo":[142],"(0.9387).":[143],"Under":[144],"low-label":[146],"regime":[147],"only":[149],"10%":[150],"available":[152],"annotations,":[153],"it":[154],"retains":[155],"an":[156],"0.9075,":[159],"demonstrating":[160],"strong":[161],"label":[162],"efficiency.":[163],"Furthermore,":[164],"superpatch-based":[166],"design":[167],"reduces":[168],"computational":[169],"31.0":[172],"GFLOPs":[173,180],"per":[174],"forward":[175],"pass,":[176],"compared":[177],"985.8":[179],"baseline,":[184],"providing":[185],"scalable":[187],"robust":[189],"foundation":[190],"medical":[193],"imaging.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-04T00:00:00"}