{"id":"https://openalex.org/W7131085032","doi":"https://doi.org/10.1109/iccvw69036.2025.00066","title":"Understanding Dataset Bias in Medical Imaging: A Case Study on Chest X-rays","display_name":"Understanding Dataset Bias in Medical Imaging: A Case Study on Chest X-rays","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131085032","doi":"https://doi.org/10.1109/iccvw69036.2025.00066"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043594658","display_name":"Ethan Dack","orcid":null},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ethan Dack","raw_affiliation_strings":["University of Bern"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bern","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015055434","display_name":"Chengliang Dai","orcid":"https://orcid.org/0000-0002-9931-5437"},"institutions":[{"id":"https://openalex.org/I4210150862","display_name":"Biopharma Technology (United Kingdom)","ror":"https://ror.org/04ny0re85","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210150862"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chengliang Dai","raw_affiliation_strings":["UCB Biopharma UK Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCB Biopharma UK Imperial College London","institution_ids":["https://openalex.org/I47508984","https://openalex.org/I4210150862"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0182,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83231503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"584","last_page":"594"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.2883000075817108,"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":0.2883000075817108,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.12309999763965607,"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/T11361","display_name":"Digital Radiography and Breast Imaging","score":0.08760000020265579,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7820000052452087},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5490000247955322},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4641000032424927},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.3828999996185303},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.3714999854564667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3172000050544739}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7820000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044000029563904},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5490000247955322},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47609999775886536},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4742000102996826},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3828999996185303},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3714999854564667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C106977388","wikidata":"https://www.wikidata.org/wiki/Q2752427","display_name":"Medical research","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2712000012397766},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2644999921321869}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W153185079","https://openalex.org/W1852255964","https://openalex.org/W2001610032","https://openalex.org/W2031342017","https://openalex.org/W2108598243","https://openalex.org/W2152772232","https://openalex.org/W2194775991","https://openalex.org/W2295107390","https://openalex.org/W2611650229","https://openalex.org/W2618530766","https://openalex.org/W2757251151","https://openalex.org/W2912664121","https://openalex.org/W2914203365","https://openalex.org/W2962858109","https://openalex.org/W2963466845","https://openalex.org/W2991676991","https://openalex.org/W2992308087","https://openalex.org/W2995225687","https://openalex.org/W3035682985","https://openalex.org/W3114128166","https://openalex.org/W3119527628","https://openalex.org/W3137522685","https://openalex.org/W3151449316","https://openalex.org/W3185094524","https://openalex.org/W3204899787","https://openalex.org/W4220839569","https://openalex.org/W4229574167","https://openalex.org/W4246193833","https://openalex.org/W4292958735","https://openalex.org/W4296027312","https://openalex.org/W4296963805","https://openalex.org/W4319300958","https://openalex.org/W4322736086","https://openalex.org/W4387097385","https://openalex.org/W4387430233","https://openalex.org/W4387435243","https://openalex.org/W4391843481","https://openalex.org/W4394976513","https://openalex.org/W4399539485","https://openalex.org/W4400126525","https://openalex.org/W4402581391","https://openalex.org/W4404734610","https://openalex.org/W4408865267"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"works":[1],"[35],":[2],"[61]":[3],"have":[4],"revisited":[5],"the":[6,22,37,77,101,104,119,141,153,179,186],"infamous":[7],"task":[8,25,39],"\u201cName":[9],"That":[10],"Dataset\u201d":[11],"[54],":[12],"demonstrating":[13],"that":[14,21],"non-medical":[15],"datasets":[16,68,184],"contain":[17],"underlying":[18],"biases":[19],"and":[20,107,113,161,178],"dataset":[23,85],"origin":[24],"can":[26,191],"be":[27,192],"solved":[28],"with":[29],"high":[30],"accuracy.":[31],"In":[32],"this":[33,166],"work,":[34,95],"we":[35,80,96],"revisit":[36],"same":[38,78,105],"applied":[40],"to":[41,53,58,65,82,100,111,129],"popular":[42,71],"open-source":[43,56,67,183],"chest":[44],"X-ray":[45],"datasets.":[46,91],"Medical":[47],"images":[48],"are":[49,134,138],"naturally":[50],"more":[51,170,182],"difficult":[52],"release":[54],"for":[55,72],"due":[57],"their":[59],"sen-sitive":[60],"nature,":[61],"which":[62],"has":[63],"led":[64],"certain":[66],"being":[69,173],"extremely":[70],"research":[73,172],"purposes.":[74],"By":[75],"performing":[76],"task,":[79,106],"wish":[81],"explore":[83],"whether":[84,131],"bias":[86],"also":[87],"exists":[88],"in":[89,124,175,185],"these":[90],"To":[92],"extend":[93],"our":[94],"apply":[97],"simple":[98],"transformations":[99],"datasets,":[102],"repeat":[103],"perform":[108],"an":[109],"analysis":[110],"identify":[112],"explain":[114],"any":[115],"detected":[116],"biases.":[117],"Given":[118],"importance":[120],"of":[121,148,181],"AI":[122],"applications":[123],"medical":[125,176,187],"imaging,":[126],"it's":[127],"vital":[128],"establish":[130],"modern":[132],"methods":[133],"taking":[135],"shortcuts":[136],"or":[137],"focused":[139],"on":[140,152],"rele-vant":[142],"pathology.":[143],"We":[144,164],"implement":[145],"a":[146],"range":[147],"different":[149],"network":[150],"architectures":[151],"datasets:":[154],"NIH":[155],"[56],":[156],"CheXpert":[157],"[27],":[158],"MIMIC-CXR":[159],"[29]":[160],"PadChest":[162],"[6].":[163],"hope":[165],"work":[167],"will":[168],"encourage":[169],"explainable":[171],"performed":[174],"imaging":[177],"creation":[180],"domain.":[188],"Our":[189],"code":[190],"found":[193],"here:":[194],"https://github.com/eedack01/x_ray_ds_bias.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-24T00:00:00"}