{"id":"https://openalex.org/W7163638378","doi":"https://doi.org/10.1109/access.2026.3700707","title":"Toward Robust Unsupervised Multi-Class Chest X-Ray Clustering: Comparing Reconstruction-Driven and Self- Supervised Representation Learning","display_name":"Toward Robust Unsupervised Multi-Class Chest X-Ray Clustering: Comparing Reconstruction-Driven and Self- Supervised Representation Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7163638378","doi":"https://doi.org/10.1109/access.2026.3700707"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3700707","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3700707","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3700707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114286468","display_name":"Salma Ouhsousou","orcid":null},"institutions":[{"id":"https://openalex.org/I227306068","display_name":"Ondokuz May\u0131s University","ror":"https://ror.org/028k5qw24","country_code":"TR","type":"education","lineage":["https://openalex.org/I227306068"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Salma Ouhsousou","raw_affiliation_strings":["Department of Computer Engineering, Ondokuz Mayıs University, Atakum, Samsun, Türkiye"],"raw_orcid":"https://orcid.org/0009-0008-1208-2257","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Ondokuz Mayıs University, Atakum, Samsun, Türkiye","institution_ids":["https://openalex.org/I227306068"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083385521","display_name":"Zinnet Duygu Ak\u015feh\u0131r","orcid":"https://orcid.org/0000-0002-6834-6847"},"institutions":[{"id":"https://openalex.org/I227306068","display_name":"Ondokuz May\u0131s University","ror":"https://ror.org/028k5qw24","country_code":"TR","type":"education","lineage":["https://openalex.org/I227306068"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Zinnet Duygu Ak\u015fehir","raw_affiliation_strings":["Department of Computer Engineering, Ondokuz Mayıs University, Atakum, Samsun, Türkiye"],"raw_orcid":"https://orcid.org/0000-0002-6834-6847","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Ondokuz Mayıs University, Atakum, Samsun, Türkiye","institution_ids":["https://openalex.org/I227306068"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052088319","display_name":"Erdal K\u0131l\u0131\u00e7","orcid":"https://orcid.org/0000-0003-1585-0991"},"institutions":[{"id":"https://openalex.org/I227306068","display_name":"Ondokuz May\u0131s University","ror":"https://ror.org/028k5qw24","country_code":"TR","type":"education","lineage":["https://openalex.org/I227306068"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Erdal Kili\u00e7","raw_affiliation_strings":["Department of Computer Engineering, Ondokuz Mayıs University, Atakum, Samsun, Türkiye"],"raw_orcid":"https://orcid.org/0000-0003-1585-0991","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Ondokuz Mayıs University, Atakum, Samsun, Türkiye","institution_ids":["https://openalex.org/I227306068"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I227306068"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73922157,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"86133","last_page":"86151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.37229999899864197,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.37229999899864197,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.3208000063896179,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.08330000191926956,"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/representation","display_name":"Representation (politics)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4668000042438507},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4194999933242798},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.39719998836517334},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38929998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7925000190734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6962000131607056},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5080999732017517},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4668000042438507},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4194999933242798},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.39719998836517334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38929998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3700707","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3700707","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6f1ebab4f1dc4ec683de906bf6e1b01e","is_oa":true,"landing_page_url":"https://doaj.org/article/6f1ebab4f1dc4ec683de906bf6e1b01e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 86133-86151 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3700707","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3700707","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unsupervised":[0],"clustering":[1,30,125,197,248],"of":[2,111,196,216,283],"medical":[3],"images":[4],"remains":[5,176],"a":[6,60,86,95,101,134,143,235,288],"challenging":[7],"problem,":[8],"particularly":[9],"in":[10],"radiology,":[11],"where":[12],"reliable":[13],"annotations":[14],"are":[15,83,184,206],"scarce":[16],"and":[17,62,69,100,119,129,158,265,298],"visual":[18],"differences":[19],"between":[20,65],"disease":[21],"categories":[22,162],"can":[23],"be":[24],"subtle.":[25],"Many":[26],"existing":[27],"chest":[28,78],"X-ray":[29,79],"studies":[31],"rely":[32],"on":[33,181,274],"Convolutional":[34],"autoencoders":[35],"(CAEs)":[36],"to":[37,45,186,251,263,272],"learn":[38],"latent":[39],"features;":[40],"however,":[41],"reconstruction-based":[42],"objectives":[43],"tend":[44],"emphasize":[46],"low-level":[47],"image":[48,296],"similarity":[49],"rather":[50],"than":[51,163],"clinically":[52],"meaningful":[53],"structure.":[54],"In":[55,192],"this":[56],"work,":[57],"we":[58],"present":[59],"controlled":[61],"systematic":[63],"comparison":[64],"reconstruction-driven":[66],"autoencoder":[67,164],"representations":[68,72,205,229],"self-supervised":[70,284],"transformer":[71],"derived":[73],"from":[74,261,270],"DINO":[75],"for":[76,292],"multi-class":[77],"clustering.":[80],"All":[81],"methods":[82],"evaluated":[84],"under":[85,133],"unified":[87],"experimental":[88],"protocol":[89],"across":[90],"three":[91],"dataset":[92,99,183,189],"scales,":[93],"including":[94],"balanced":[96],"4,000-image":[97],"development":[98],"strict":[102,236],"cross-dataset":[103,237],"generalization":[104],"setting.":[105],"We":[106],"further":[107,170],"examine":[108],"the":[109,194,213,240,258,266,281],"influence":[110],"dimensionality":[112],"reduction":[113],"by":[114],"comparing":[115],"linear":[116],"projection":[117,167],"(PCA-32)":[118],"nonlinear":[120],"manifold":[121],"learning":[122],"(UMAP-32),and":[123],"assess":[124],"robustness":[126],"using":[127],"K-Means":[128],"Gaussian":[130],"Mixture":[131],"Models":[132],"strictly":[135],"inductive":[136],"protocol,":[137,239],"with":[138,160,168],"Spectral":[139],"Clustering":[140],"included":[141],"as":[142,287],"secondary":[144],"exploratory":[145],"reference.":[146],"Across":[147],"all":[148],"configurations,":[149],"DINO-based":[150,228],"embeddings":[151],"consistently":[152],"yield":[153],"stronger":[154],"cluster":[155,172],"compactness,":[156],"separation,":[157],"alignment":[159],"clinical":[161,295],"features.":[165],"Nonlinear":[166],"UMAP":[169],"enhances":[171],"structure,":[173],"while":[174,222],"performance":[175],"stable":[177],"when":[178,203],"models":[179],"trained":[180],"one":[182],"transferred":[185],"an":[187,275],"independent":[188],"without":[190],"refitting.":[191],"contrast,":[193],"choice":[195],"algorithm":[198],"has":[199],"comparatively":[200],"limited":[201],"impact":[202],"high-quality":[204],"used,":[207],"indicating":[208],"that":[209,221],"representation":[210,290],"geometry":[211],"is":[212],"primary":[214],"driver":[215],"performance.":[217],"Our":[218],"results":[219],"demonstrate":[220],"CAEs":[223],"primarily":[224],"capture":[225],"pixel-level":[226],"textures,":[227],"encode":[230],"higher-level":[231],"semantic":[232],"structures.":[233],"Under":[234],"evaluation":[238],"proposed":[241],"hybrid":[242],"strategy":[243],"(Strategy":[244,255],"B)":[245],"substantially":[246],"improved":[247],"quality":[249],"compared":[250],"direct":[252],"feature":[253],"fusion":[254],"A),":[256],"increasing":[257],"Silhouette":[259],"score":[260],"0.056":[262],"0.564":[264],"Rand":[267],"Index":[268],"(RI)":[269],"0.762":[271],"0.860":[273],"external":[276],"dataset.":[277],"These":[278],"findings":[279],"highlight":[280],"potential":[282],"vision":[285],"transformers":[286],"robust":[289],"foundation":[291],"future":[293],"unsupervised":[294],"analysis":[297],"decision":[299],"support":[300],"systems.":[301]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2026-06-06T00:00:00"}