{"id":"https://openalex.org/W4362663824","doi":"https://doi.org/10.1117/12.2655267","title":"Correcting class imbalances with self-training for improved universal lesion detection and tagging","display_name":"Correcting class imbalances with self-training for improved universal lesion detection and tagging","publication_year":2023,"publication_date":"2023-04-06","ids":{"openalex":"https://openalex.org/W4362663824","doi":"https://doi.org/10.1117/12.2655267"},"language":"en","primary_location":{"id":"doi:10.1117/12.2655267","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2655267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Imaging 2023: Computer-Aided Diagnosis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12306813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030011829","display_name":"Alexander Shieh","orcid":"https://orcid.org/0009-0005-7450-2702"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Alexander Te-Wei Shieh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048201234","display_name":"Tejas Sudharshan Mathai","orcid":"https://orcid.org/0009-0005-8440-1702"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tejas Sudharshan Mathai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101543443","display_name":"Jianfei Liu","orcid":"https://orcid.org/0000-0001-9885-1695"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfei Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053707075","display_name":"Angshuman Paul","orcid":"https://orcid.org/0000-0002-0935-0256"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Angshuman Paul","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016047550","display_name":"Ronald M. Summers","orcid":"https://orcid.org/0000-0001-8081-7376"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ronald M. Summers","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030011829"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03042372,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12033","issue":null,"first_page":"35","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9732000231742859,"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":0.9732000231742859,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9674999713897705,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9598000049591064,"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/class","display_name":"Class (philosophy)","score":0.6867402791976929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6827811002731323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5447895526885986},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4168664216995239},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33700087666511536},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07217323780059814}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6867402791976929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827811002731323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5447895526885986},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4168664216995239},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33700087666511536},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07217323780059814},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1117/12.2655267","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1117/12.2655267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Medical Imaging 2023: Computer-Aided Diagnosis","raw_type":"proceedings-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12306813","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12306813","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ArXiv","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12306813","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12306813","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ArXiv","raw_type":"Text"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2115113482","https://openalex.org/W2883683269","https://openalex.org/W2884584803","https://openalex.org/W2963008565","https://openalex.org/W2970105478","https://openalex.org/W2979362285","https://openalex.org/W2979564444","https://openalex.org/W3013377280","https://openalex.org/W3097722521","https://openalex.org/W3117686595","https://openalex.org/W3127743092","https://openalex.org/W3165446958","https://openalex.org/W3172087149","https://openalex.org/W3184439416","https://openalex.org/W4200409436","https://openalex.org/W4210851927","https://openalex.org/W4285540447","https://openalex.org/W4285717408","https://openalex.org/W4295934491","https://openalex.org/W4296965585","https://openalex.org/W6753721087","https://openalex.org/W6759142798","https://openalex.org/W6763376248","https://openalex.org/W6766509321","https://openalex.org/W6782744377","https://openalex.org/W6784094891","https://openalex.org/W6795805722","https://openalex.org/W6798838024","https://openalex.org/W6803745986"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W230091440","https://openalex.org/W2390279801","https://openalex.org/W2233261550","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Universal":[0],"lesion":[1,20,116,165,237],"detection":[2],"and":[3,15,68,104,113,128,150,205],"tagging":[4],"(ULDT)":[5],"in":[6,76,107,190,195],"CT":[7,50,108],"studies":[8],"is":[9,64],"critical":[10],"for":[11,58,84,234],"tumor":[12],"burden":[13],"assessment":[14],"tracking":[16],"the":[17,33,42,152,161,168,175,211,230],"progression":[18],"of":[19,28,35,96,163,170],"status":[21],"(growth/shrinkage)":[22],"over":[23,131],"time.":[24],"However,":[25,173],"a":[26,81,92,119,182,187,206],"lack":[27],"fully":[29],"annotated":[30,67],"data":[31,122],"hinders":[32],"development":[34],"effective":[36],"ULDT":[37],"approaches.":[38],"Prior":[39],"work":[40],"used":[41],"DeepLesion":[43,97],"dataset":[44,63],"(4,427":[45],"patients,":[46],"10,594":[47],"studies,":[48],"32,120":[49],"slices,":[51],"32,735":[52],"lesions,":[53],"8":[54,236],"body":[55],"part":[56],"labels)":[57],"algorithmic":[59],"development,":[60],"but":[61],"this":[62,77],"not":[65],"completely":[66],"contains":[69],"class":[70,153,200],"imbalances.":[71,154],"To":[72],"address":[73],"these":[74],"issues,":[75],"work,":[78],"we":[79,221],"developed":[80],"self-training":[82,135,159,179,198,213],"pipeline":[83],"ULDT.":[85],"A":[86],"VFNet":[87],"model":[88],"was":[89],"trained":[90],"on":[91],"limited":[93],"11.5\\%":[94],"subset":[95,123],"(bounding":[98],"boxes":[99],"+":[100],"tags)":[101],"to":[102,143,197,210],"detect":[103],"classify":[105],"lesions":[106,146,176],"studies.":[109],"Then,":[110],"it":[111],"identified":[112],"incorporated":[114],"novel":[115],"candidates":[117],"from":[118],"larger":[120],"unseen":[121],"into":[124],"its":[125],"training":[126],"set,":[127],"self-trained":[129],"itself":[130],"multiple":[132],"rounds.":[133],"Multiple":[134],"experiments":[136],"were":[137],"conducted":[138],"with":[139,147,181],"different":[140],"threshold":[141,184],"policies":[142],"select":[144],"predicted":[145],"higher":[148],"quality":[149],"cover":[151],"We":[155],"discovered":[156],"that":[157,223],"direct":[158],"improved":[160,227],"sensitivities":[162],"over-represented":[164],"classes":[166],"at":[167,192,232],"expense":[169],"under-represented":[171],"classes.":[172,238],"upsampling":[174,216],"mined":[177],"during":[178],"along":[180],"variable":[183],"policy":[185,214],"yielded":[186],"6.5\\%":[188],"increase":[189,208],"sensitivity":[191,231],"4":[193],"FP":[194],"contrast":[196],"without":[199,215],"balancing":[201],"(72\\%":[202],"vs":[203,218],"78.5\\%)":[204],"11.7\\%":[207],"compared":[209],"same":[212],"(66.8\\%":[217],"78.5\\%).":[219],"Furthermore,":[220],"show":[222],"our":[224],"results":[225],"either":[226],"or":[228],"maintained":[229],"4FP":[233],"all":[235]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}