{"id":"https://openalex.org/W1580235436","doi":"https://doi.org/10.3233/978-1-61499-078-9-250","title":"The impact of OCR accuracy on automated cancer classification of pathology reports","display_name":"The impact of OCR accuracy on automated cancer classification of pathology reports","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1580235436","doi":"https://doi.org/10.3233/978-1-61499-078-9-250","mag":"1580235436","pmid":"https://pubmed.ncbi.nlm.nih.gov/22797049"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-078-9-250","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-078-9-250","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"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/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I4210141844","display_name":"Australian e-Health Research Centre","ror":"https://ror.org/04ywhbc61","country_code":"AU","type":"facility","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801244131","https://openalex.org/I2801453606","https://openalex.org/I4210141844","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zuccon Guido","raw_affiliation_strings":["The Australian e-Health Research Centre, CSIRO ICT Centre, Brisbane, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Australian e-Health Research Centre, CSIRO ICT Centre, Brisbane, Australia","institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I4210141844"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023213398","display_name":"Anthony Nguyen","orcid":"https://orcid.org/0000-0002-6215-6954"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen Anthony N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090331254","display_name":"Anton Bergheim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bergheim Anton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065892100","display_name":"Sandra Wickman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wickman Sandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5004261333","display_name":"Narelle Grayson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grayson Narelle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5234,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.93538913,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"178","issue":null,"first_page":"250","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.3813000023365021,"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":0.3813000023365021,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.2556000053882599,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.14749999344348907,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.582273006439209},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.5273578763008118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4335617423057556},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.39721089601516724},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3813844919204712},{"id":"https://openalex.org/keywords/medical-physics","display_name":"Medical physics","score":0.35986754298210144},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32695814967155457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582273006439209},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.5273578763008118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4335617423057556},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.39721089601516724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3813844919204712},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.35986754298210144},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32695814967155457}],"mesh":[{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001331","descriptor_name":"Automation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003308","descriptor_name":"Copying Processes","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D003308","descriptor_name":"Copying Processes","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D003308","descriptor_name":"Copying Processes","qualifier_ui":"Q000592","qualifier_name":"standards","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":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008499","descriptor_name":"Medical Records","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000473","qualifier_name":"pathology","is_major_topic":false},{"descriptor_ui":"D010336","descriptor_name":"Pathology","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010336","descriptor_name":"Pathology","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010336","descriptor_name":"Pathology","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D010338","descriptor_name":"Pathology, Clinical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010338","descriptor_name":"Pathology, Clinical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010338","descriptor_name":"Pathology, Clinical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-078-9-250","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-078-9-250","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:22797049","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22797049","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":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W4393187896","https://openalex.org/W3204019825"],"abstract_inverted_index":{"OBJECTIVE:":[0],"To":[1],"evaluate":[2],"the":[3,11,39,50,58,62,67,75,104,113,124,134,167,184],"effects":[4],"of":[5,15,21,61,74,116,126,136,169,186],"Optical":[6],"Character":[7],"Recognition":[8],"(OCR)":[9],"on":[10,57,112],"automatic":[12,114,149],"cancer":[13,36,137,150,187],"classification":[14,37,68,115,151],"pathology":[16,22,88,118,171],"reports.":[17,52,77],"METHOD:":[18],"Scanned":[19],"images":[20,175],"reports":[23,63,89,119,172],"were":[24,64,107],"converted":[25],"to":[26,47,85,92,98,109,160,163],"electronic":[27],"free-text":[28],"using":[29],"a":[30,70],"commercial":[31],"OCR":[32,51,59,76,81,105,127,177],"system.":[33],"A":[34],"state-of-the-art":[35],"system,":[38,44],"Medical":[40],"Text":[41],"Extraction":[42],"(MEDTEX)":[43],"was":[45,83],"used":[46,153],"automatically":[48],"classify":[49],"Classifications":[53],"produced":[54,165],"by":[55,166],"MEDTEX":[56],"versions":[60],"compared":[65],"with":[66,90],"from":[69,173],"human":[71],"amended":[72],"version":[73],"RESULTS:":[78],"The":[79,148],"employed":[80],"system":[82,152],"found":[84,108],"recognise":[86],"scanned":[87,117,174],"up":[91,97],"99.12%":[93],"character":[94],"accuracy":[95],"and":[96],"98.95%":[99],"word":[100],"accuracy.":[101],"Errors":[102],"in":[103,154],"processing":[106],"minimally":[110],"impact":[111,125],"into":[120],"notifiable":[121],"groups.":[122],"However,":[123,179],"errors":[128,164],"is":[129],"not":[130],"negligible":[131],"when":[132,182],"considering":[133,183],"extraction":[135,185],"notification":[138,188],"items,":[139],"such":[140],"as":[141],"primary":[142],"site,":[143],"histological":[144],"type,":[145],"etc.":[146],"CONCLUSIONS:":[147],"this":[155],"work,":[156],"MEDTEX,":[157],"has":[158],"proven":[159],"be":[161],"robust":[162],"acquisition":[168],"freetext":[170],"through":[176],"software.":[178],"issues":[180],"emerge":[181],"items.":[189]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
