{"id":"https://openalex.org/W2972602340","doi":"https://doi.org/10.1145/3307339.3342173","title":"Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters","display_name":"Extraction of Tumor Site from Cancer Pathology Reports using Deep Filters","publication_year":2019,"publication_date":"2019-09-04","ids":{"openalex":"https://openalex.org/W2972602340","doi":"https://doi.org/10.1145/3307339.3342173","mag":"2972602340"},"language":"en","primary_location":{"id":"doi:10.1145/3307339.3342173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307339.3342173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342173","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049776939","display_name":"Abhishek Dubey","orcid":"https://orcid.org/0000-0002-0168-4948"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhishek K. Dubey","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039044523","display_name":"Jacob Hinkle","orcid":"https://orcid.org/0000-0002-7751-1760"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Hinkle","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037444677","display_name":"J. Blair Christian","orcid":"https://orcid.org/0000-0002-4658-1635"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Blair Christian","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014968146","display_name":"Georgia D. Tourassi","orcid":"https://orcid.org/0000-0002-9418-9638"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Georgia Tourassi","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN, USA","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1289243028"],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.52452737,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"320","last_page":"327"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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/T10028","display_name":"Topic Modeling","score":0.996399998664856,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9904999732971191,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9854000210762024,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5597323775291443},{"id":"https://openalex.org/keywords/cancer","display_name":"Cancer","score":0.46434837579727173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4227096438407898},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.38467395305633545},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.25070565938949585},{"id":"https://openalex.org/keywords/internal-medicine","display_name":"Internal medicine","score":0.14126497507095337},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1393645703792572},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.10161060094833374}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5597323775291443},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.46434837579727173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4227096438407898},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.38467395305633545},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.25070565938949585},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.14126497507095337},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1393645703792572},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.10161060094833374}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3307339.3342173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307339.3342173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342173","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1561636","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1561636","pdf_url":"https://www.osti.gov/servlets/purl/1561636","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:osti.gov:1820880","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1820880","pdf_url":"https://www.osti.gov/servlets/purl/1820880","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3307339.3342173","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3307339.3342173","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3307339.3342173","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G102163711","display_name":null,"funder_award_id":"DE\u2010 AC02\u201006CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G107546177","display_name":null,"funder_award_id":"DE- AC02-06-CH11357","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1313983767","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G1356433355","display_name":null,"funder_award_id":"DE\u2010AC5207NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G14554683","display_name":null,"funder_award_id":"DEAC5207NA27344","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1645119126","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G203625172","display_name":null,"funder_award_id":"DE--AC05--00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2569679037","display_name":null,"funder_award_id":"JDACS4C","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2584197162","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G286898171","display_name":null,"funder_award_id":"DE-AC52-06NA2-5396","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2988778103","display_name":null,"funder_award_id":"DE-AC05?","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3005847338","display_name":null,"funder_award_id":"JDACS4C","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G314071323","display_name":null,"funder_award_id":"JDACS4C","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"},{"id":"https://openalex.org/G4423657506","display_name":null,"funder_award_id":"AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G5713387433","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5738753633","display_name":null,"funder_award_id":"DEAC52-07NA27344","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G5840121450","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G6086734019","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"},{"id":"https://openalex.org/G6750061500","display_name":null,"funder_award_id":"DEAC52-07NA27344","funder_id":"https://openalex.org/F4320338284","funder_display_name":"Argonne National Laboratory"},{"id":"https://openalex.org/G675320460","display_name":null,"funder_award_id":"DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320338287","funder_display_name":"Oak Ridge National Laboratory"},{"id":"https://openalex.org/G7186599013","display_name":null,"funder_award_id":"under Contract DE-AC05-00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G75892134","display_name":null,"funder_award_id":"DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320338304","funder_display_name":"Los Alamos National Laboratory"},{"id":"https://openalex.org/G8906985441","display_name":null,"funder_award_id":"00OR22725","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G928841278","display_name":null,"funder_award_id":"contract DE-AC52-06NA25396","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"},{"id":"https://openalex.org/F4320338287","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56"},{"id":"https://openalex.org/F4320338304","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2972602340.pdf","grobid_xml":"https://content.openalex.org/works/W2972602340.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W232876404","https://openalex.org/W628712619","https://openalex.org/W1530378878","https://openalex.org/W1576347883","https://openalex.org/W1582515031","https://openalex.org/W1603452536","https://openalex.org/W1607983314","https://openalex.org/W1880262756","https://openalex.org/W1969595233","https://openalex.org/W2003994472","https://openalex.org/W2030753668","https://openalex.org/W2072738586","https://openalex.org/W2094711307","https://openalex.org/W2096797897","https://openalex.org/W2122825543","https://openalex.org/W2132052677","https://openalex.org/W2135046866","https://openalex.org/W2143426320","https://openalex.org/W2154053567","https://openalex.org/W2163490846","https://openalex.org/W2167101736","https://openalex.org/W2179694568","https://openalex.org/W2187089797","https://openalex.org/W2250539671","https://openalex.org/W2252215182","https://openalex.org/W2427312199","https://openalex.org/W2591546050","https://openalex.org/W2611254939","https://openalex.org/W2750370324","https://openalex.org/W2781487490","https://openalex.org/W2895715183","https://openalex.org/W3023608713","https://openalex.org/W3135358928","https://openalex.org/W4285719527","https://openalex.org/W4320800818","https://openalex.org/W6679534712"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"\\beginabstract":[0],"Purpose:":[1],"Pathology":[2],"reports":[3,27,50,257,319],"are":[4],"the":[5,11,17,25,30,48,114,124,140,159,169,173,177,183,188,192,218,227,232,236,263,276,283,293,317],"primary":[6,34],"source":[7],"of":[8,13,47,65,127,130,176,191,221,254,295],"information":[9,32,72,92,115,154,211,234,300,307,314,331],"concerning":[10],"millions":[12],"cancer":[14,60,336],"cases":[15],"across":[16],"United":[18],"States.":[19],"%":[20,42,62,83,95,109,132,147,165,196,213,243,245,266,312,338],"Cancer":[21],"registries":[22],"manually":[23],"process":[24],"pathology":[26,49,224,256,318],"to":[28,69,75,105,113,138,157,204,230,275,332],"extract":[29,79],"pertinent":[31],"including":[33],"tumor":[35],"site,":[36],"behavior,":[37],"histology,":[38],"laterality,":[39],"and":[40,77,161,171,186,285,305,329],"grade.":[41],"Processing":[43],"a":[44,52,56,87,143,206,240,252],"large":[45],"volume":[46],"in":[51,226,239,335],"timely":[53],"manner":[54],"is":[55,68,120],"continuing":[57],"challenge":[58],"for":[59,210,303],"registries.":[61],"The":[63,96,247,313],"purpose":[64],"this":[66,134],"study":[67],"develop":[70],"an":[71,151,222],"extraction":[73,93,116,301,308],"pipeline":[74,268,302],"reliably":[76],"efficiently":[78],"reportable":[80],"information.\\\\":[81],"Method:":[82],"We":[84],"have":[85],"developed":[86],"novel":[88,144],"inverse-regression":[89,97,194,202,298],"(IR)":[90],"based":[91,98,155,299],"pipeline.":[94],"supervised":[99,241],"filter":[100,156],"has":[101],"been":[102],"successfully":[103],"applied":[104],"many":[106],"application":[107,112],"domains.":[108],"However,":[110],"its":[111],"from":[117,235,309,316],"unstructured":[118,310],"text":[119],"hindered":[121],"primarily":[122],"by":[123,142],"extreme":[125],"high-dimensionality":[126],"n-gram":[128,163],"representations":[129],"text.":[131,311],"In":[133,214],"study,":[135],"we":[136,149,198,216],"attempt":[137],"overcome":[139],"obstacles":[141],"bootstrapping":[145],"strategy.":[146],"First,":[148],"use":[150,199,217],"information-theoretic":[152],"mutual":[153],"discard":[158],"excessive":[160],"redundant":[162],"features.":[164],"This":[166],"step":[167],"reduces":[168],"size":[170],"improves":[172],"condition":[174],"number":[175],"sample":[178],"covariance":[179],"matrix,":[180],"thus":[181],"reducing":[182,282],"computational":[184],"cost":[185],"improving":[187],"numerical":[189],"stability":[190],"subsequent":[193],"step.":[195],"Then":[197],"localized":[200],"sliced":[201],"(LSIR)":[203],"learn":[205],"low-dimensional":[207],"discriminatory":[208],"subspace":[209],"inference.":[212],"particular,":[215],"k-nearest":[219],"neighbors":[220],"unlabeled":[223],"report":[225],"learned":[228],"representation":[229],"infer":[231],"desired":[233],"labeled":[237],"data":[238],"manner.":[242],"\\\\":[244],"Results:":[246],"experiments":[248],"were":[249],"conducted":[250],"on":[251],"set":[253],"de-identified":[255],"with":[258,324],"human":[259],"expert":[260],"labels":[261],"as":[262],"ground":[264],"truth.":[265],"Our":[267,290],"consistently":[269],"performed":[270],"better":[271],"than":[272],"or":[273],"comparable":[274],"best":[277],"performing":[278],"state-of-the-art":[279],"methods":[280],"while":[281],"training":[284],"inference":[286],"times":[287],"substantially.\\\\":[288],"Conclusion:":[289],"results":[291],"demonstrate":[292],"potential":[294],"\\emergencystretch":[296],"3em":[297],"reliable":[304],"efficient":[306],"extracted":[315],"can":[320],"be":[321],"used":[322],"along":[323],"clinical":[325],"information,":[326],"medical":[327],"imaging,":[328],"genomic":[330],"instigate":[333],"discoveries":[334],"research.":[337],"\\endabstract":[339]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
