{"id":"https://openalex.org/W7165044055","doi":"https://doi.org/10.1109/access.2026.3704749","title":"MammoClean: Toward Reproducible and Bias-Aware AI in Mammography Through Dataset Harmonization","display_name":"MammoClean: Toward Reproducible and Bias-Aware AI in Mammography Through Dataset Harmonization","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7165044055","doi":"https://doi.org/10.1109/access.2026.3704749"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3704749","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704749","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.2026.3704749","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094275052","display_name":"Yalda Zafari-Ghadim","orcid":"https://orcid.org/0009-0004-9737-7134"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Yalda Zafari","raw_affiliation_strings":["Department of Mathematics and Statistics, Qatar University, Doha, Qatar"],"raw_orcid":"https://orcid.org/0009-0004-9737-7134","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002608156","display_name":"Hongyi Pan","orcid":"https://orcid.org/0000-0001-9421-3936"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongyi Pan","raw_affiliation_strings":["Department of Radiology, Northwestern University, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-9421-3936","affiliations":[{"raw_affiliation_string":"Department of Radiology, Northwestern University, Chicago, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033826718","display_name":"G\u00f6rkem Durak","orcid":"https://orcid.org/0000-0002-1608-1955"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gorkem Durak","raw_affiliation_strings":["Department of Radiology, Northwestern University, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Northwestern University, Chicago, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030188696","display_name":"Ula\u015f Ba\u011fc\u0131","orcid":"https://orcid.org/0000-0001-7379-6829"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ulas Bagci","raw_affiliation_strings":["Department of Radiology, Northwestern University, Chicago, IL, USA"],"raw_orcid":"https://orcid.org/0000-0001-7379-6829","affiliations":[{"raw_affiliation_string":"Department of Radiology, Northwestern University, Chicago, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879425","display_name":"Essam A. Rashed","orcid":"https://orcid.org/0000-0001-6571-9807"},"institutions":[{"id":"https://openalex.org/I180941496","display_name":"University of Hyogo","ror":"https://ror.org/0151bmh98","country_code":"JP","type":"education","lineage":["https://openalex.org/I180941496"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Essam A. Rashed","raw_affiliation_strings":["Graduate School of Information Science, University of Hyogo, Kobe, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6571-9807","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, University of Hyogo, Kobe, Japan","institution_ids":["https://openalex.org/I180941496"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042556381","display_name":"Mohamed A. Mabrok","orcid":"https://orcid.org/0000-0003-3638-4424"},"institutions":[{"id":"https://openalex.org/I60342839","display_name":"Qatar University","ror":"https://ror.org/00yhnba62","country_code":"QA","type":"education","lineage":["https://openalex.org/I60342839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mohamed Mabrok","raw_affiliation_strings":["Department of Mathematics and Statistics, Qatar University, Doha, Qatar"],"raw_orcid":"https://orcid.org/0000-0003-3638-4424","affiliations":[{"raw_affiliation_string":"Department of Mathematics and Statistics, Qatar University, Doha, Qatar","institution_ids":["https://openalex.org/I60342839"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.78042485,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"93834","last_page":"93853"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.8554999828338623,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.8554999828338623,"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/T11361","display_name":"Digital Radiography and Breast Imaging","score":0.02459999918937683,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.013299999758601189,"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/mammography","display_name":"Mammography","score":0.7825000286102295},{"id":"https://openalex.org/keywords/harmonization","display_name":"Harmonization","score":0.448199987411499},{"id":"https://openalex.org/keywords/digital-mammography","display_name":"Digital mammography","score":0.32899999618530273},{"id":"https://openalex.org/keywords/mammography-screening","display_name":"Mammography screening","score":0.30239999294281006}],"concepts":[{"id":"https://openalex.org/C2780472235","wikidata":"https://www.wikidata.org/wiki/Q324634","display_name":"Mammography","level":4,"score":0.7825000286102295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708899974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45019999146461487},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C2781281974","wikidata":"https://www.wikidata.org/wiki/Q324634","display_name":"Digital mammography","level":5,"score":0.32899999618530273},{"id":"https://openalex.org/C2994436140","wikidata":"https://www.wikidata.org/wiki/Q17011492","display_name":"Mammography screening","level":5,"score":0.30239999294281006},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.24009999632835388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2386000007390976},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.23579999804496765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3704749","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704749","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:1078e7088f5e40a2a2705c023353e5eb","is_oa":false,"landing_page_url":"https://doaj.org/article/1078e7088f5e40a2a2705c023353e5eb","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 93834-93853 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3704749","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3704749","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":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.537151038646698}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,218],"development":[1],"of":[2,37,85,99,128,158,184],"clinically":[3],"reliable":[4],"artificial":[5],"intelligence":[6],"(AI)":[7],"systems":[8],"for":[9,52,198,207],"mammography":[10,59,92],"is":[11],"hindered":[12],"by":[13],"profound":[14],"heterogeneity":[15,28],"in":[16,58,146,211],"data":[17,129,159],"quality,":[18],"metadata":[19,74],"standards,":[20],"and":[21,55,69,72,90,124,149,181],"population":[22],"distributions":[23],"across":[24,216],"public":[25,50,91],"datasets.":[26,60],"This":[27],"introduces":[29],"dataset-specific":[30],"biases":[31],"that":[32],"can":[33,187],"compromise":[34],"the":[35,126,138,155],"generalizability":[36],"AI":[38,132,161],"models,":[39],"a":[40,49,76,82,116,196,204],"fundamental":[41],"barrier":[42],"to":[43,94,104,120,137,172,179],"clinical":[44],"deployment.":[45],"We":[46,80,101,152],"present":[47],"MammoClean,":[48],"framework":[51],"dataset":[53,209],"standardization":[54],"bias":[56],"identification":[57],"MammoClean":[61,103,136,178,202],"standardizes":[62],"case":[63,118],"selection,":[64],"image":[65],"processing":[66],"(including":[67],"laterality":[68],"intensity":[70],"correction),":[71],"unifies":[73],"into":[75],"consistent":[77],"multi-view":[78],"structure.":[79],"provide":[81],"targeted":[83],"review":[84],"breast":[86,147],"anatomy,":[87],"imaging":[88],"characteristics,":[89],"datasets":[93,108,166],"systematically":[95],"identify":[96,180],"key":[97],"sources":[98,183],"heterogeneity.":[100],"apply":[102],"three":[105,139],"large-scale":[106],"heterogeneous":[107],"with":[109],"detailed":[110],"annotations":[111],"(CBIS-DDSM,":[112],"TOMPEI-CMMD,":[113],"VinDr-Mammo)":[114],"as":[115,195],"focused":[117],"study":[119],"quantify":[121,142],"distributional":[122,144],"shifts":[123,145],"illustrate":[125,154],"impact":[127,157],"corruption":[130],"on":[131,164],"model":[133],"performance.":[134],"Applying":[135],"datasets,":[140],"we":[141],"substantial":[143],"density":[148],"abnormality":[150],"prevalence.":[151],"further":[153],"direct":[156],"corruption:":[160],"models":[162],"trained":[163],"corrupted":[165],"exhibit":[167],"notable":[168],"performance":[169],"degradation":[170],"compared":[171],"their":[173],"curated":[174],"counterparts.":[175],"By":[176],"using":[177],"document":[182],"heterogeneity,":[185],"researchers":[186],"more":[188],"reliably":[189],"prepare":[190],"unified":[191],"multi-dataset":[192],"training":[193],"corpora":[194],"foundation":[197],"developing":[199],"robust":[200],"models.":[201],"provides":[203],"reproducible":[205],"pipeline":[206],"bias-aware":[208],"preparation":[210],"mammography,":[212],"facilitating":[213],"fairer":[214],"comparisons":[215],"studies.":[217],"open-source":[219],"code":[220],"will":[221],"be":[222],"publicly":[223],"available":[224],"from:":[225],"<uri>https://github.com/Minds-R-Lab/MammoClean</uri>":[226]},"counts_by_year":[],"updated_date":"2026-06-25T06:16:34.145877","created_date":"2026-06-18T00:00:00"}