{"id":"https://openalex.org/W4401072508","doi":"https://doi.org/10.1109/memea60663.2024.10596826","title":"Bayesian XAI Methods Towards a Robustness-Centric Approach to Deep Learning: An ABIDE I Study","display_name":"Bayesian XAI Methods Towards a Robustness-Centric Approach to Deep Learning: An ABIDE I Study","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4401072508","doi":"https://doi.org/10.1109/memea60663.2024.10596826"},"language":"en","primary_location":{"id":"doi:10.1109/memea60663.2024.10596826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/memea60663.2024.10596826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","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/A5092991727","display_name":"Filippo Bargagna","orcid":"https://orcid.org/0009-0006-6403-0585"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Bargagna","raw_affiliation_strings":["University of Pisa,Dip. di Ingegneria,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa,Dip. di Ingegneria,Pisa,Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076728110","display_name":"Lisa Anita De Santi","orcid":"https://orcid.org/0000-0001-7239-4270"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lisa Anita De Santi","raw_affiliation_strings":["University of Pisa,Dip. di Ingegneria,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa,Dip. di Ingegneria,Pisa,Italy","institution_ids":["https://openalex.org/I108290504"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044785782","display_name":"Maria Filomena Santarelli","orcid":"https://orcid.org/0000-0001-8332-7006"},"institutions":[{"id":"https://openalex.org/I4210106076","display_name":"Istituto di Fisiologia Clinica","ror":"https://ror.org/01kdj2848","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210106076","https://openalex.org/I4210155236"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Maria Filomena Santarelli","raw_affiliation_strings":["Institute of Clinical Physiology CNR,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Clinical Physiology CNR,Pisa,Italy","institution_ids":["https://openalex.org/I4210106076"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090506270","display_name":"Vincenzo Positano","orcid":"https://orcid.org/0000-0001-6955-9572"},"institutions":[{"id":"https://openalex.org/I4210158339","display_name":"Fondazione Toscana Gabriele Monasterio","ror":"https://ror.org/058a2pj71","country_code":"IT","type":"other","lineage":["https://openalex.org/I4210155236","https://openalex.org/I4210158339"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vincenzo Positano","raw_affiliation_strings":["Fondazione Toscana Gabriele Monasterio,Bioengineering Unit,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fondazione Toscana Gabriele Monasterio,Bioengineering Unit,Pisa,Italy","institution_ids":["https://openalex.org/I4210158339"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066412301","display_name":"Nicola Vanello","orcid":"https://orcid.org/0000-0002-2312-6699"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Nicola Vanello","raw_affiliation_strings":["University of Pisa,Dip. di Ingegneria,Pisa,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pisa,Dip. di Ingegneria,Pisa,Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2196,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82501049,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9980999827384949,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9980999827384949,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9883999824523926,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9807999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8378313779830933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6461384296417236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5923096537590027},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5310592651367188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.419288694858551}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8378313779830933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6461384296417236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5923096537590027},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5310592651367188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.419288694858551},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/memea60663.2024.10596826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/memea60663.2024.10596826","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arpi.unipi.it:11568/1267848","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1267848","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1787224781","https://openalex.org/W2021630210","https://openalex.org/W2058046532","https://openalex.org/W2167868121","https://openalex.org/W2657631929","https://openalex.org/W2752558629","https://openalex.org/W2902820651","https://openalex.org/W2945976633","https://openalex.org/W2964059111","https://openalex.org/W2973136764","https://openalex.org/W3023823933","https://openalex.org/W3040685212","https://openalex.org/W3149668772","https://openalex.org/W4225510469","https://openalex.org/W4301462412","https://openalex.org/W4312302217","https://openalex.org/W4367301275","https://openalex.org/W4381929541","https://openalex.org/W4386525359","https://openalex.org/W4386897466","https://openalex.org/W4391848979","https://openalex.org/W6747874465"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Developing":[0],"reliable":[1],"and":[2,12,97],"explainable":[3,44],"models":[4],"is":[5],"a":[6,76,114,161,189,193,198,202],"crucial":[7],"point":[8],"to":[9,34,48,79,99,148,166,208],"effectively":[10],"integrate":[11],"exploit":[13,32,91],"the":[14,52,57,74,81,92,101,108,131,150,157,173,177,209],"potentials":[15],"offered":[16,94],"by":[17,43,95],"Deep":[18],"Learning":[19],"(DL)":[20],"architectures":[21],"in":[22,105,156],"high-stakes":[23],"scenarios":[24],"like":[25],"healthcare.":[26],"There":[27],"are":[28,87],"several":[29],"applications":[30,89],"that":[31,171],"DL":[33],"support":[35,100],"Autism":[36,132],"Spectrum":[37],"Disorder":[38],"(ASD)":[39],"diagnosis,":[40],"eventually":[41],"augmented":[42],"AI":[45],"(XAI)":[46],"tools":[47],"provide":[49],"hints":[50],"on":[51,176],"decision-making":[53],"process":[54],"implemented.":[55],"On":[56],"other":[58],"hand,":[59],"Bayesian":[60],"Neural":[61],"Networks":[62],"(BNNs)":[63],"can":[64],"provide,":[65],"together":[66],"with":[67,197],"their":[68],"prediction,":[69],"epistemic":[70],"uncertainty":[71],"(uncertainty":[72],"of":[73,103,152,181,212],"model),":[75],"key":[77],"component":[78],"asserting":[80],"model's":[82,178],"reliability.":[83],"To":[84],"date,":[85],"there":[86],"no":[88],"which":[90,116,191],"advantages":[93],"BNNs":[96],"XAI":[98,199],"research":[102],"biomarkers":[104],"ASD.":[106],"In":[107],"present":[109],"work,":[110],"authors":[111],"first":[112],"developed":[113],"BNN":[115],"classifies":[117],"ASD":[118,182,213],"subjects":[119],"from":[120,130],"resting":[121],"state":[122],"functional":[123,168],"Magnetic":[124],"Resonance":[125],"Imaging":[126,134],"(rs-fMRI)":[127],"data":[128],"obtained":[129],"Brain":[133],"Data":[135],"Exchange":[136],"(ABIDE)":[137],"dataset.":[138],"A":[139],"Layerwise":[140],"Relevance":[141],"Propagation":[142],"(LRP)":[143],"algorithm":[144],"was":[145,164],"then":[146],"used":[147],"estimate":[149],"importance":[151],"cross-correlation":[153],"connectivity":[154],"coefficients":[155],"returned":[158],"predictions.":[159],"Finally,":[160],"group":[162],"analysis":[163],"performed":[165],"highlight":[167],"brain":[169],"connections":[170],"report":[172],"highest":[174],"impact":[175],"correct":[179],"classification":[180],"subjects.":[183],"This":[184],"work":[185],"ended":[186],"up":[187],"producing":[188],"framework":[190],"combines":[192],"bayesian":[194],"neural":[195],"network":[196],"methodology,":[200],"towards":[201],"robustness-centric":[203],"deep":[204],"learning":[205],"approach,":[206],"applied":[207],"case":[210],"study":[211],"diagnosis.":[214]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}