{"id":"https://openalex.org/W4399882778","doi":"https://doi.org/10.3390/make6020064","title":"Image Text Extraction and Natural Language Processing of Unstructured Data from Medical Reports","display_name":"Image Text Extraction and Natural Language Processing of Unstructured Data from Medical Reports","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4399882778","doi":"https://doi.org/10.3390/make6020064"},"language":"en","primary_location":{"id":"doi:10.3390/make6020064","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6020064","pdf_url":"https://www.mdpi.com/2504-4990/6/2/64/pdf?version=1718722209","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/6/2/64/pdf?version=1718722209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093610652","display_name":"Ivan Malashin","orcid":"https://orcid.org/0009-0008-8986-402X"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Ivan Malashin","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081253409","display_name":"Igor Masich","orcid":"https://orcid.org/0000-0002-3997-342X"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Igor Masich","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045549119","display_name":"\u0412 \u0421 \u0422\u044b\u043d\u0447\u0435\u043d\u043a\u043e","orcid":"https://orcid.org/0000-0002-3959-2969"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Vadim Tynchenko","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059986632","display_name":"Andrei Gantimurov","orcid":"https://orcid.org/0009-0001-4246-9742"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Andrei Gantimurov","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053346800","display_name":"Vladimir Nelyub","orcid":"https://orcid.org/0000-0003-4263-2367"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]},{"id":"https://openalex.org/I204947315","display_name":"Far Eastern Federal University","ror":"https://ror.org/0412y9z21","country_code":"RU","type":"education","lineage":["https://openalex.org/I204947315"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Nelyub","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","Scientific Department, Far Eastern Federal University, 690922 Vladivostok, Russia"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]},{"raw_affiliation_string":"Scientific Department, Far Eastern Federal University, 690922 Vladivostok, Russia","institution_ids":["https://openalex.org/I204947315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032053296","display_name":"\u0410. \u0421. \u0411\u043e\u0440\u043e\u0434\u0443\u043b\u0438\u043d","orcid":"https://orcid.org/0000-0002-9648-2395"},"institutions":[{"id":"https://openalex.org/I177537411","display_name":"Bauman Moscow State Technical University","ror":"https://ror.org/00pb8h375","country_code":"RU","type":"education","lineage":["https://openalex.org/I177537411"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aleksei Borodulin","raw_affiliation_strings":["Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia","institution_ids":["https://openalex.org/I177537411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045549119","https://openalex.org/A5093610652"],"corresponding_institution_ids":["https://openalex.org/I177537411"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":2.5732,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89851504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"6","issue":"2","first_page":"1361","last_page":"1377"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8008999824523926,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8008999824523926,"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"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.7749999761581421,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.6725000143051147,"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":0.6657007336616516},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6472102999687195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5488923788070679},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.48393040895462036},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.46869874000549316},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.4627613425254822},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.45145970582962036},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3919110596179962},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.17754682898521423},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.15966704487800598},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.1392441689968109},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.056561172008514404},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05077177286148071}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657007336616516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6472102999687195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5488923788070679},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.48393040895462036},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.46869874000549316},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.4627613425254822},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.45145970582962036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3919110596179962},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.17754682898521423},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.15966704487800598},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.1392441689968109},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.056561172008514404},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05077177286148071},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/make6020064","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6020064","pdf_url":"https://www.mdpi.com/2504-4990/6/2/64/pdf?version=1718722209","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:debc5377fa834b8a85e8e2c56a183c0a","is_oa":true,"landing_page_url":"https://doaj.org/article/debc5377fa834b8a85e8e2c56a183c0a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 6, Iss 2, Pp 1361-1377 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/make6020064","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make6020064","pdf_url":"https://www.mdpi.com/2504-4990/6/2/64/pdf?version=1718722209","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399882778.pdf"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W44597921","https://openalex.org/W1488125194","https://openalex.org/W1702375188","https://openalex.org/W1992257524","https://openalex.org/W2027883219","https://openalex.org/W2065042463","https://openalex.org/W2135231474","https://openalex.org/W2141053090","https://openalex.org/W2340583188","https://openalex.org/W2768488789","https://openalex.org/W2778385450","https://openalex.org/W2796986051","https://openalex.org/W2991356721","https://openalex.org/W2999089077","https://openalex.org/W3000627755","https://openalex.org/W3005844399","https://openalex.org/W3006156918","https://openalex.org/W3008537971","https://openalex.org/W3008993296","https://openalex.org/W3011570378","https://openalex.org/W3014925206","https://openalex.org/W3029538695","https://openalex.org/W3038203375","https://openalex.org/W3080429061","https://openalex.org/W3081518866","https://openalex.org/W3096005429","https://openalex.org/W3101025102","https://openalex.org/W3102944297","https://openalex.org/W3112065054","https://openalex.org/W3115677442","https://openalex.org/W3118519475","https://openalex.org/W3128197136","https://openalex.org/W3128720655","https://openalex.org/W3136021864","https://openalex.org/W3153993091","https://openalex.org/W3156614709","https://openalex.org/W3163548907","https://openalex.org/W3163650427","https://openalex.org/W3165345393","https://openalex.org/W3166925692","https://openalex.org/W3180026636","https://openalex.org/W3183698554","https://openalex.org/W3186942977","https://openalex.org/W3193521099","https://openalex.org/W3198980621","https://openalex.org/W3201922353","https://openalex.org/W3205290066","https://openalex.org/W4224291284","https://openalex.org/W4281253290","https://openalex.org/W4285805241","https://openalex.org/W4292582552","https://openalex.org/W4294233400","https://openalex.org/W4297347697","https://openalex.org/W4313585449","https://openalex.org/W4316019745","https://openalex.org/W4322756266","https://openalex.org/W4327960899","https://openalex.org/W4386378792","https://openalex.org/W4389237317","https://openalex.org/W4392959955","https://openalex.org/W4393080597","https://openalex.org/W4394877427","https://openalex.org/W6797920689","https://openalex.org/W6980682505"],"related_works":["https://openalex.org/W2030910246","https://openalex.org/W4389912246","https://openalex.org/W4205553786","https://openalex.org/W4385489363","https://openalex.org/W2372366649","https://openalex.org/W4362731990","https://openalex.org/W4316660311","https://openalex.org/W3155464240","https://openalex.org/W2368651715","https://openalex.org/W1516746680"],"abstract_inverted_index":{"This":[0,55],"study":[1],"presents":[2],"an":[3,44],"integrated":[4],"approach":[5],"for":[6,47],"automatically":[7],"extracting":[8],"and":[9,27],"structuring":[10],"information":[11,82,119],"from":[12,51],"medical":[13,52,103],"reports,":[14],"captured":[15],"as":[16,114],"scanned":[17],"documents":[18],"or":[19],"photographs,":[20],"through":[21],"a":[22,58,115],"combination":[23],"of":[24,102,118],"image":[25],"recognition":[26,36,66],"natural":[28],"language":[29],"processing":[30,77],"(NLP)":[31],"techniques":[32],"like":[33],"named":[34],"entity":[35],"(NER).":[37],"The":[38],"primary":[39],"aim":[40],"was":[41],"to":[42,62,78,127],"develop":[43],"adaptive":[45],"model":[46],"efficient":[48],"text":[49,71],"extraction":[50,72,120],"report":[53,104],"images.":[54],"involved":[56],"utilizing":[57],"genetic":[59],"algorithm":[60],"(GA)":[61],"fine-tune":[63],"optical":[64],"character":[65],"(OCR)":[67],"hyperparameters,":[68],"ensuring":[69],"maximal":[70],"length,":[73],"followed":[74],"by":[75],"NER":[76],"categorize":[79],"the":[80,99,107],"extracted":[81,93],"into":[83],"required":[84],"entities,":[85],"adjusting":[86],"parameters":[87],"if":[88],"entities":[89],"were":[90],"not":[91],"correctly":[92],"based":[94],"on":[95],"manual":[96],"annotations.":[97],"Despite":[98],"diverse":[100],"formats":[101],"images":[105],"in":[106,110],"dataset,":[108],"all":[109],"Russian,":[111],"this":[112],"serves":[113],"conceptual":[116],"example":[117],"(IE)":[121],"that":[122],"can":[123],"be":[124],"easily":[125],"extended":[126],"other":[128],"languages.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}