{"id":"https://openalex.org/W3203730897","doi":"https://doi.org/10.1007/s10278-021-00505-7","title":"The Trials and Tribulations of Assembling Large Medical Imaging Datasets for Machine Learning Applications","display_name":"The Trials and Tribulations of Assembling Large Medical Imaging Datasets for Machine Learning Applications","publication_year":2021,"publication_date":"2021-10-04","ids":{"openalex":"https://openalex.org/W3203730897","doi":"https://doi.org/10.1007/s10278-021-00505-7","mag":"3203730897","pmid":"https://pubmed.ncbi.nlm.nih.gov/34608591"},"language":"en","primary_location":{"id":"doi:10.1007/s10278-021-00505-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10278-021-00505-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10278-021-00505-7.pdf","source":{"id":"https://openalex.org/S62275304","display_name":"Journal of Digital Imaging","issn_l":"0897-1889","issn":["0897-1889","1618-727X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Digital Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10278-021-00505-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066782057","display_name":"Kirti Magudia","orcid":"https://orcid.org/0000-0001-7037-433X"},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kirti Magudia","raw_affiliation_strings":["Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA. kirti.magudia@duke.edu","Department of Radiology, Duke University School of Medicine, Durham, NC, 27710, USA. kirti.magudia@duke.edu","Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7037-433X","affiliations":[{"raw_affiliation_string":"Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA. kirti.magudia@duke.edu","institution_ids":["https://openalex.org/I1283280774"]},{"raw_affiliation_string":"Department of Radiology, Duke University School of Medicine, Durham, NC, 27710, USA. kirti.magudia@duke.edu","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1283280774"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079669314","display_name":"Christopher P. Bridge","orcid":"https://orcid.org/0000-0002-2242-351X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher P. Bridge","raw_affiliation_strings":["MGH & BWH Center for Clinical Data Science, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MGH & BWH Center for Clinical Data Science, Boston, MA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089624408","display_name":"Katherine P. Andriole","orcid":"https://orcid.org/0000-0001-7774-4225"},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine P. Andriole","raw_affiliation_strings":["Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA","MGH & BWH Center for Clinical Data Science, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1283280774"]},{"raw_affiliation_string":"MGH & BWH Center for Clinical Data Science, Boston, MA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031717380","display_name":"Michael H. Rosenthal","orcid":"https://orcid.org/0000-0002-5085-3904"},"institutions":[{"id":"https://openalex.org/I1283280774","display_name":"Brigham and Women's Hospital","ror":"https://ror.org/04b6nzv94","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283280774","https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael H. Rosenthal","raw_affiliation_strings":["Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology, Brigham & Women's Hospital, Boston, MA, USA","institution_ids":["https://openalex.org/I1283280774"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066782057"],"corresponding_institution_ids":["https://openalex.org/I1283280774","https://openalex.org/I170897317"],"apc_list":{"value":3190,"currency":"EUR","value_usd":4190},"apc_paid":{"value":3190,"currency":"EUR","value_usd":4190},"fwci":1.7203,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.84623958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"34","issue":"6","first_page":"1424","last_page":"1429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9947999715805054,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9947999715805054,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.993399977684021,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T12386","display_name":"Advanced X-ray and CT Imaging","score":0.977400004863739,"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/medicine","display_name":"Medicine","score":0.5525550246238708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5487226247787476},{"id":"https://openalex.org/keywords/medical-physics","display_name":"Medical physics","score":0.4888388514518738},{"id":"https://openalex.org/keywords/dicom","display_name":"DICOM","score":0.47591859102249146},{"id":"https://openalex.org/keywords/institutional-review-board","display_name":"Institutional review board","score":0.47205835580825806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46873220801353455},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41487085819244385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4022146463394165},{"id":"https://openalex.org/keywords/radiology","display_name":"Radiology","score":0.3839072287082672},{"id":"https://openalex.org/keywords/surgery","display_name":"Surgery","score":0.12561187148094177}],"concepts":[{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.5525550246238708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5487226247787476},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.4888388514518738},{"id":"https://openalex.org/C77331912","wikidata":"https://www.wikidata.org/wiki/Q81095","display_name":"DICOM","level":2,"score":0.47591859102249146},{"id":"https://openalex.org/C2777106319","wikidata":"https://www.wikidata.org/wiki/Q362104","display_name":"Institutional review board","level":2,"score":0.47205835580825806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46873220801353455},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41487085819244385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4022146463394165},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.3839072287082672},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","level":1,"score":0.12561187148094177}],"mesh":[{"descriptor_ui":"D000005","descriptor_name":"Abdomen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000005","descriptor_name":"Abdomen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000005","descriptor_name":"Abdomen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000005","descriptor_name":"Abdomen","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011859","descriptor_name":"Radiography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011859","descriptor_name":"Radiography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011859","descriptor_name":"Radiography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011859","descriptor_name":"Radiography","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012189","descriptor_name":"Retrospective Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014057","descriptor_name":"Tomography, X-Ray Computed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014057","descriptor_name":"Tomography, X-Ray Computed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014057","descriptor_name":"Tomography, X-Ray Computed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014057","descriptor_name":"Tomography, X-Ray Computed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1007/s10278-021-00505-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10278-021-00505-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10278-021-00505-7.pdf","source":{"id":"https://openalex.org/S62275304","display_name":"Journal of Digital Imaging","issn_l":"0897-1889","issn":["0897-1889","1618-727X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Digital Imaging","raw_type":"journal-article"},{"id":"pmid:34608591","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34608591","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of digital imaging","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8669054","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8669054","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Digit Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s10278-021-00505-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10278-021-00505-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10278-021-00505-7.pdf","source":{"id":"https://openalex.org/S62275304","display_name":"Journal of Digital Imaging","issn_l":"0897-1889","issn":["0897-1889","1618-727X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Digital Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3203730897.pdf","grobid_xml":"https://content.openalex.org/works/W3203730897.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2028138594","https://openalex.org/W2900243258","https://openalex.org/W2913223168","https://openalex.org/W2914203365","https://openalex.org/W2919356958","https://openalex.org/W2939071985","https://openalex.org/W3007935259","https://openalex.org/W3023284086","https://openalex.org/W3088943327","https://openalex.org/W3089653673"],"related_works":["https://openalex.org/W2352944256","https://openalex.org/W2528730528","https://openalex.org/W2358954258","https://openalex.org/W2376146719","https://openalex.org/W2355550873","https://openalex.org/W2370879019","https://openalex.org/W1513288651","https://openalex.org/W2351853078","https://openalex.org/W2347834369","https://openalex.org/W2021592708"],"abstract_inverted_index":{"With":[0],"vast":[1],"interest":[2],"in":[3,68,90],"machine":[4,16,204],"learning":[5,17,205],"applications,":[6],"more":[7],"investigators":[8,175],"are":[9],"proposing":[10],"to":[11,21,26,35,92,186],"assemble":[12],"large":[13,113],"datasets":[14],"for":[15,85,180],"applications.":[18],"We":[19,168,183],"aim":[20],"delineate":[22],"multiple":[23,76],"possible":[24],"roadblocks":[25],"exam":[27,82,121],"retrieval":[28,50,86,131,161],"that":[29,173,193],"may":[30,162,194],"present":[31],"themselves":[32],"and":[33,49,54,59,104,117,127,138,154,160,178],"lead":[34],"significant":[36],"time":[37,137,144],"delays.":[38],"This":[39],"HIPAA-compliant,":[40],"institutional":[41],"review":[42],"board-approved,":[43],"retrospective":[44],"clinical":[45],"study":[46],"required":[47],"identification":[48],"of":[51,109,135,143],"all":[52],"outpatient":[53],"emergency":[55],"patients":[56],"undergoing":[57],"abdominal":[58,77,95],"pelvic":[60],"computed":[61],"tomography":[62],"(CT)":[63],"at":[64,139],"three":[65],"affiliated":[66],"hospitals":[67],"the":[69,80,146,191],"year":[70],"2012.":[71],"If":[72],"a":[73,151,155],"patient":[74],"had":[75],"CT":[78,96,101],"exams,":[79],"first":[81],"was":[83],"selected":[84],"(n=23,186).":[87],"Our":[88],"experience":[89,171],"attempting":[91],"retrieve":[93],"23,186":[94],"exams":[97,103],"yielded":[98],"22,852":[99],"valid":[100],"abdomen/pelvis":[102],"identified":[105],"four":[106],"major":[107],"categories":[108],"challenges":[110],"when":[111],"retrieving":[112,119],"datasets:":[114],"cohort":[115],"selection":[116,159],"processing,":[118],"DICOM":[120],"files":[122],"from":[123],"PACS,":[124],"data":[125,152],"storage,":[126],"non-recoverable":[128],"failures.":[129],"The":[130],"took":[132],"3":[133],"months":[134],"project":[136],"minimum":[140],"300":[141],"person-hours":[142],"between":[145],"primary":[147],"investigator":[148],"(a":[149],"radiologist),":[150],"scientist,":[153],"software":[156],"engineer.":[157],"Exam":[158],"take":[163],"significantly":[164],"longer":[165],"than":[166],"planned.":[167],"share":[169],"our":[170],"so":[172],"other":[174],"can":[176],"anticipate":[177],"plan":[179],"these":[181],"challenges.":[182],"also":[184],"hope":[185],"help":[187],"institutions":[188],"better":[189],"understand":[190],"demands":[192],"be":[195],"placed":[196],"on":[197],"their":[198],"infrastructure":[199],"by":[200],"large-scale":[201],"medical":[202],"imaging":[203],"projects.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}