{"id":"https://openalex.org/W3005214526","doi":"https://doi.org/10.1109/pacrim47961.2019.8985057","title":"Learning from an Imbalanced and Limited Dataset and an Application to Medical Imaging","display_name":"Learning from an Imbalanced and Limited Dataset and an Application to Medical Imaging","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W3005214526","doi":"https://doi.org/10.1109/pacrim47961.2019.8985057","mag":"3005214526"},"language":"en","primary_location":{"id":"doi:10.1109/pacrim47961.2019.8985057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pacrim47961.2019.8985057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)","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/A5101820861","display_name":"Xiaoli Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Xiaoli Qin","raw_affiliation_strings":["University of Saskatchewan,Department of Electrical and Computer Engineering,Saskatoon,Canada","Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada"],"affiliations":[{"raw_affiliation_string":"University of Saskatchewan,Department of Electrical and Computer Engineering,Saskatoon,Canada","institution_ids":["https://openalex.org/I32625721"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071017561","display_name":"Francis M. Bui","orcid":"https://orcid.org/0000-0002-8799-5965"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Francis M. Bui","raw_affiliation_strings":["University of Saskatchewan,Department of Electrical and Computer Engineering,Saskatoon,Canada","Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada"],"affiliations":[{"raw_affiliation_string":"University of Saskatchewan,Department of Electrical and Computer Engineering,Saskatoon,Canada","institution_ids":["https://openalex.org/I32625721"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100635655","display_name":"Ha H. Nguyen","orcid":"https://orcid.org/0000-0001-6481-0422"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ha H. Nguyen","raw_affiliation_strings":["University of Saskatchewan,Department of Electrical and Computer Engineering,Saskatoon,Canada","Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada"],"affiliations":[{"raw_affiliation_string":"University of Saskatchewan,Department of Electrical and Computer Engineering,Saskatoon,Canada","institution_ids":["https://openalex.org/I32625721"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Saskatchewan, Saskatoon, Canada","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101820861"],"corresponding_institution_ids":["https://openalex.org/I32625721"],"apc_list":null,"apc_paid":null,"fwci":1.028,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78563351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2019","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.996999979019165,"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":0.996999979019165,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9848999977111816,"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/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.9839000105857849,"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/oversampling","display_name":"Oversampling","score":0.8892923593521118},{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.8743538856506348},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7993963956832886},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7650814056396484},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.738746166229248},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6136537790298462},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5092686414718628},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.46262454986572266},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45982933044433594},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.45913106203079224},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4169531464576721},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3576722741127014},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.10230758786201477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09671944379806519}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8892923593521118},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.8743538856506348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993963956832886},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7650814056396484},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.738746166229248},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6136537790298462},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5092686414718628},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.46262454986572266},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45982933044433594},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.45913106203079224},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4169531464576721},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3576722741127014},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.10230758786201477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09671944379806519},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pacrim47961.2019.8985057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pacrim47961.2019.8985057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM)","raw_type":"proceedings-article"},{"id":"mag:3037445417","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=202002236509715784","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1533861849","https://openalex.org/W1766594731","https://openalex.org/W1849277567","https://openalex.org/W2043025385","https://openalex.org/W2099471712","https://openalex.org/W2118978333","https://openalex.org/W2173520492","https://openalex.org/W2415642486","https://openalex.org/W2775795276","https://openalex.org/W2788633781","https://openalex.org/W2794022343","https://openalex.org/W2794736759","https://openalex.org/W2801837154","https://openalex.org/W2890139949","https://openalex.org/W2951523806","https://openalex.org/W2963684088","https://openalex.org/W4241578052","https://openalex.org/W4300485340","https://openalex.org/W4301597213","https://openalex.org/W4320013936","https://openalex.org/W6621378261","https://openalex.org/W6631943919","https://openalex.org/W6685352114","https://openalex.org/W6738297899","https://openalex.org/W6746693533","https://openalex.org/W6747218270","https://openalex.org/W6754577982"],"related_works":["https://openalex.org/W32988189","https://openalex.org/W4308469503","https://openalex.org/W2904737874","https://openalex.org/W80466363","https://openalex.org/W4389233021","https://openalex.org/W2399571531","https://openalex.org/W2947132063","https://openalex.org/W4390415670","https://openalex.org/W4288337828","https://openalex.org/W4287816717"],"abstract_inverted_index":{"Chest":[0],"X-rays":[1],"(CXRs)":[2],"are":[3],"routinely":[4],"acquired":[5,27],"in":[6,81],"medical":[7,36],"imaging":[8],"for":[9,17,73,113],"the":[10,26,57,115,159,166,206,210],"purpose":[11],"of":[12,25,59,71,117,142,146,165,209],"diagnosing":[13],"lung":[14],"diseases.":[15],"But":[16],"many":[18],"patients,":[19],"accurate":[20],"and":[21,38,68,96,162,181,197],"timely":[22],"radiologic":[23],"interpretation":[24],"CXRs":[28,72,98],"is":[29,79],"not":[30],"always":[31],"feasible,":[32],"due":[33],"to":[34,55,99,134,151,171],"limited":[35,97],"personnel":[37],"resources.":[39],"A":[40],"computer":[41],"aided":[42],"diagnosis":[43],"(CAD)":[44],"system":[45,78],"based":[46],"on":[47,92,176],"machine":[48],"learning":[49,93,118,126,172,199],"would":[50],"be":[51],"an":[52,110,147],"effective":[53,111],"solution":[54],"enhance":[56],"efficiency":[58],"disease":[60],"diagnosis.":[61],"However,":[62],"obtaining":[63],"a":[64,76,88,153,188],"sufficiently":[65],"large-scale,":[66],"balanced,":[67],"annotated":[69],"dataset":[70],"effectively":[74],"training":[75],"CAD":[77],"challenging":[80],"practice.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,137,174,193],"present":[87],"comprehensive":[89],"comparative":[90],"study":[91],"from":[94],"imbalanced":[95,148],"detect":[100],"pneumonia,":[101],"tackling":[102],"two":[103,139],"main":[104],"questions:":[105],"(1)":[106],"Is":[107],"data":[108,135,149,155,211],"sampling":[109,130,212],"method":[112],"improving":[114],"performance":[116],"models?":[119],"(2)":[120],"Are":[121],"there":[122],"quantifiable":[123],"differences":[124],"between":[125],"models":[127,200],"with":[128,205],"different":[129],"techniques?":[131],"With":[132,169],"respect":[133,170],"sampling,":[136],"investigate":[138],"general":[140],"categories":[141],"techniques":[143],"that":[144,195],"modify":[145],"set":[150],"deliver":[152],"balanced":[154],"distribution:":[156],"(i)":[157],"undersampling":[158],"majority":[160],"class;":[161],"(ii)":[163],"oversampling/augmentation":[164],"minority":[167],"class.":[168],"models,":[173],"focus":[175],"Support":[177],"Vector":[178],"Machine":[179],"(SVM)":[180],"deep":[182],"convolutional":[183],"neural":[184],"network":[185],"(CNN).":[186],"Using":[187],"publicly":[189],"available":[190],"CXR":[191],"dataset,":[192],"demonstrate":[194],"SVM":[196],"CNN":[198],"both":[201],"exhibit":[202],"improved":[203],"performance,":[204],"proper":[207],"selection":[208],"strategies.":[213]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}