{"id":"https://openalex.org/W4402352075","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650683","title":"Symbolic Knowledge Extraction and Distillation into Convolutional Neural Networks to Improve Medical Image Classification","display_name":"Symbolic Knowledge Extraction and Distillation into Convolutional Neural Networks to Improve Medical Image Classification","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352075","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650683"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650683","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5064727846","display_name":"Kwun Ho Ngan","orcid":"https://orcid.org/0000-0001-7623-942X"},"institutions":[{"id":"https://openalex.org/I4210153853","display_name":"Fujitsu (United Kingdom)","ror":"https://ror.org/053ny5136","country_code":"GB","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210153853"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kwun Ho Ngan","raw_affiliation_strings":["Fujitsu Research of Europe Ltd,Slough,UK,SL1 2BE"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of Europe Ltd,Slough,UK,SL1 2BE","institution_ids":["https://openalex.org/I4210153853"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107244189","display_name":"J.J. Phelan","orcid":"https://orcid.org/0000-0001-9431-2002"},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Phelan","raw_affiliation_strings":["University of London,London,UK,EC1 0HB"],"affiliations":[{"raw_affiliation_string":"University of London,London,UK,EC1 0HB","institution_ids":["https://openalex.org/I124357947"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029919865","display_name":"Joe Townsend","orcid":"https://orcid.org/0000-0002-5478-0028"},"institutions":[{"id":"https://openalex.org/I4210153853","display_name":"Fujitsu (United Kingdom)","ror":"https://ror.org/053ny5136","country_code":"GB","type":"company","lineage":["https://openalex.org/I2252096349","https://openalex.org/I4210153853"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joe Townsend","raw_affiliation_strings":["Fujitsu Research of Europe Ltd,Slough,UK,SL1 2BE"],"affiliations":[{"raw_affiliation_string":"Fujitsu Research of Europe Ltd,Slough,UK,SL1 2BE","institution_ids":["https://openalex.org/I4210153853"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060005929","display_name":"Artur d\u2019Avila Garcez","orcid":"https://orcid.org/0000-0001-7375-9518"},"institutions":[{"id":"https://openalex.org/I124357947","display_name":"University of London","ror":"https://ror.org/04cw6st05","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Artur d\u2019Avila Garcez","raw_affiliation_strings":["University of London,London,UK,EC1 0HB"],"affiliations":[{"raw_affiliation_string":"University of London,London,UK,EC1 0HB","institution_ids":["https://openalex.org/I124357947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064727846"],"corresponding_institution_ids":["https://openalex.org/I4210153853"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1289772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3432","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.996999979019165,"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":0.996999979019165,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9947999715805054,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9936000108718872,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.787020206451416},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401253581047058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6352792382240295},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6103330254554749},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5678626298904419},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5641078352928162},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5038549304008484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4908078610897064},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4680319130420685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39327260851860046},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.06923073530197144},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05426231026649475}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.787020206451416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401253581047058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352792382240295},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6103330254554749},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5678626298904419},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5641078352928162},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5038549304008484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4908078610897064},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4680319130420685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39327260851860046},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.06923073530197144},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05426231026649475}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650683","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10650683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:openaccess.city.ac.uk:34417","is_oa":false,"landing_page_url":"https://openaccess.city.ac.uk/view/creators_id/a=2Egarcez.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306401940","display_name":"City Research Online (City University London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I180825142","host_organization_name":"City, University of London","host_organization_lineage":["https://openalex.org/I180825142"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1849277567","https://openalex.org/W1965104804","https://openalex.org/W1998473914","https://openalex.org/W2005585436","https://openalex.org/W2019566532","https://openalex.org/W2019904567","https://openalex.org/W2129278392","https://openalex.org/W2295107390","https://openalex.org/W2396590199","https://openalex.org/W2611650229","https://openalex.org/W2616247523","https://openalex.org/W2767128594","https://openalex.org/W2962883557","https://openalex.org/W2963081790","https://openalex.org/W2963466845","https://openalex.org/W2972844547","https://openalex.org/W2979997102","https://openalex.org/W3006348122","https://openalex.org/W3012873273","https://openalex.org/W3015984951","https://openalex.org/W3082665562","https://openalex.org/W3083155260","https://openalex.org/W3085109610","https://openalex.org/W3091460434","https://openalex.org/W3101156210","https://openalex.org/W3102564565","https://openalex.org/W3110114931","https://openalex.org/W3113149630","https://openalex.org/W3127215335","https://openalex.org/W3128601380","https://openalex.org/W3208405171","https://openalex.org/W4300668030","https://openalex.org/W4312897400","https://openalex.org/W4392044798","https://openalex.org/W6638523607","https://openalex.org/W6712817012","https://openalex.org/W6775424083","https://openalex.org/W6783655119","https://openalex.org/W6803072907","https://openalex.org/W7055268164"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W2952813363","https://openalex.org/W4360783045","https://openalex.org/W2963346891","https://openalex.org/W3176438653","https://openalex.org/W2770149305","https://openalex.org/W3167930666","https://openalex.org/W3014952856"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"have":[4],"achieved":[5],"outstanding":[6],"performance":[7],"in":[8,36,95,106,213],"radiology":[9],"tasks.":[10],"However,":[11],"CNNs":[12],"lack":[13],"the":[14,37,89,107,167,204],"transparency":[15],"and":[16,43,171,195],"explainability":[17],"necessary":[18],"to":[19,34,67,87,102,123,131,165],"enable":[20],"their":[21],"practical":[22],"clinical":[23],"adoption.":[24],"This":[25],"paper":[26],"introduces":[27],"a":[28,51,60,81,96,145,153,179,196],"neural-symbolic":[29],"approach":[30,64,177,208],"allowing":[31,84,121],"domain":[32,85],"experts":[33,86],"intervene":[35],"training":[38,74],"of":[39,46,109,183,199,206],"CNNs.":[40],"Following":[41],"extraction":[42],"expert":[44],"validation":[45,202],"meaningful":[47],"symbolic":[48,78,103],"knowledge":[49,55,104,114,141],"from":[50,160],"trained":[52],"CNN,":[53,83],"such":[54],"is":[56,65,115],"distilled":[57],"back":[58,143],"into":[59,80,144],"streamlined":[61],"CNN.":[62,148],"The":[63,93,175],"shown":[66],"enhance":[68],"user":[69],"control":[70,88],"over":[71],"conventional":[72],"CNN":[73,98,155],"by":[75],"combining":[76],"interpretable":[77],"representations":[79,105],"simplified":[82],"decision":[90,216],"making":[91],"process.":[92],"kernels":[94,130,170],"given":[97],"layer":[99],"are":[100],"mapped":[101],"form":[108],"logic":[110],"programming":[111],"rules.":[112],"Extracted":[113],"evaluated":[116],"against":[117],"known":[118],"radiomics":[119],"features,":[120],"doctors":[122],"decide":[124],"based":[125],"on":[126],"best":[127],"practice":[128],"which":[129],"keep":[132],"or":[133],"reject.":[134],"Expert":[135,201],"intervention":[136],"takes":[137],"place":[138],"through":[139],"relevant":[140,169],"distillation":[142],"more":[146],"compact":[147],"Our":[149],"results":[150],"show":[151],"that":[152],"student":[154],"can":[156],"learn":[157],"successfully":[158],"even":[159],"multiple":[161],"teachers":[162],"(different":[163],"knowledge-bases)":[164],"replicate":[166],"selected":[168],"corresponding":[172],"classification":[173],"results.":[174],"proposed":[176],"delivers":[178],"trainable":[180],"parameter":[181],"reduction":[182],"at":[184,209],"least":[185],"56.3%":[186],"while":[187],"achieving":[188],"high":[189],"cosine":[190],"similarity":[191],"for":[192],"kernel":[193],"replication":[194],"fidelity":[197],"score":[198],"99.2%.":[200],"highlights":[203],"importance":[205],"this":[207],"fostering":[210],"greater":[211],"trust":[212],"AI-driven":[214],"medical":[215],"making.":[217]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}