{"id":"https://openalex.org/W7214953771","doi":"https://doi.org/10.5826/dpc.160s1a7739","title":"An Explainable Hybrid Deep Learning Framework Combining Fine-Tuned Convolutional Neural Network Ensembles for Dermoscopic Images of Skin Lesions","display_name":"An Explainable Hybrid Deep Learning Framework Combining Fine-Tuned Convolutional Neural Network Ensembles for Dermoscopic Images of Skin Lesions","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214953771","doi":"https://doi.org/10.5826/dpc.160s1a7739"},"language":"en","primary_location":{"id":"doi:10.5826/dpc.160s1a7739","doi":"https://doi.org/10.5826/dpc.160s1a7739","is_oa":true,"landing_page_url":"https://doi.org/10.5826/dpc.160s1a7739","pdf_url":null,"source":{"id":"https://openalex.org/S2764830028","display_name":"Dermatology Practical & Conceptual","issn_l":"2160-9381","issn":["2160-9381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","dongbi-d","ki-jl-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4320800659","host_organization_name":"Mattioli 1885","host_organization_lineage":["https://openalex.org/P4320800659"],"host_organization_lineage_names":["Mattioli 1885"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dermatology Practical & Conceptual","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.5826/dpc.160s1a7739","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033373339","display_name":"B\u00fc\u015fra DUYGU \u00c7EL\u0130K","orcid":"https://orcid.org/0000-0001-9640-1025","observed_orcids":["https://orcid.org/0000-0001-9640-1025"]},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"B\u00fc\u015fra Duygu \u00c7elik","raw_affiliation_strings":["Gazi University, Graduate School of Natural and Applied Sciences, Computer Engineering Department, Ankara, Turkey; Gazi University, Faculty of Technology, Dept. of Computer Engineering, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-9640-1025","affiliations":[{"raw_affiliation_string":"Gazi University, Graduate School of Natural and Applied Sciences, Computer Engineering Department, Ankara, Turkey; Gazi University, Faculty of Technology, Dept. of Computer Engineering, Ankara, Turkey","institution_ids":["https://openalex.org/I95634034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011595926","display_name":"Burcu Beksa\u00e7","orcid":"https://orcid.org/0000-0001-5726-0696","observed_orcids":["https://orcid.org/0000-0001-5726-0696"]},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Burcu Beksa\u00e7","raw_affiliation_strings":["Department of Dermatology, Faculty of Medicine Gazi University, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-5726-0696","affiliations":[{"raw_affiliation_string":"Department of Dermatology, Faculty of Medicine Gazi University, Ankara, Turkey","institution_ids":["https://openalex.org/I95634034"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084645817","display_name":"Esra Ad\u0131\u015fen","orcid":"https://orcid.org/0000-0002-8768-231X","observed_orcids":["https://orcid.org/0000-0002-8768-231X"]},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Esra Ad\u0131\u015fen","raw_affiliation_strings":["Department of Dermatology, Faculty of Medicine Gazi University, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-8768-231X","affiliations":[{"raw_affiliation_string":"Department of Dermatology, Faculty of Medicine Gazi University, Ankara, Turkey","institution_ids":["https://openalex.org/I95634034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029049241","display_name":"Adem Tekerek","orcid":"https://orcid.org/0000-0002-0880-7955","observed_orcids":["https://orcid.org/0000-0002-0880-7955"]},"institutions":[{"id":"https://openalex.org/I95634034","display_name":"Gazi University","ror":"https://ror.org/054xkpr46","country_code":"TR","type":"education","lineage":["https://openalex.org/I95634034"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Adem Tekerek","raw_affiliation_strings":["Computer Engineering Department, Technology Faculty, Gazi University, Ankara, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-0880-7955","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Technology Faculty, Gazi University, Ankara, Turkey","institution_ids":["https://openalex.org/I95634034"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95634034"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"S1","first_page":"7739","last_page":"7739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10392","display_name":"Cutaneous Melanoma Detection and Management","score":0.9779999852180481,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/T10862","display_name":"AI in cancer detection","score":0.016200000420212746,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.000699999975040555,"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/skin-lesion-classification","display_name":"skin lesion classification","score":0.9150000214576721},{"id":"https://openalex.org/keywords/dermoscopic-images","display_name":"dermoscopic images","score":0.9300000071525574},{"id":"https://openalex.org/keywords/skin-cancer-diagnosis","display_name":"skin cancer diagnosis","score":0.6890000104904175},{"id":"https://openalex.org/keywords/ensemble-of-convolutional-neural-networks","display_name":"ensemble convolutional neural networks","score":0.8550000190734863},{"id":"https://openalex.org/keywords/soft-voting-ensemble","display_name":"soft voting ensemble","score":0.7419999837875366},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.5849999785423279},{"id":"https://openalex.org/keywords/grad-cam","display_name":"Grad-CAM","score":0.8169999718666077},{"id":"https://openalex.org/keywords/lime","display_name":"lime","score":0.9330000281333923},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.8159999847412109},{"id":"https://openalex.org/keywords/ham10000","display_name":"HAM10000","score":0.8349999785423279},{"id":"https://openalex.org/keywords/resnet34","display_name":"ResNet34","score":0.6729999780654907},{"id":"https://openalex.org/keywords/efficientnet-b0","display_name":"EfficientNetB0","score":0.902999997138977},{"id":"https://openalex.org/keywords/mobilenetv3","display_name":"MobileNetV3","score":0.8809999823570251}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7595000267028809},{"id":"https://openalex.org/C2988168687","wikidata":"https://www.wikidata.org/wiki/Q949302","display_name":"Skin lesion","level":2,"score":0.7505000233650208},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.713100016117096},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.685699999332428},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6373000144958496},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5583000183105469},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5274999737739563},{"id":"https://openalex.org/C2781156865","wikidata":"https://www.wikidata.org/wiki/Q827023","display_name":"Lesion","level":2,"score":0.4884999990463257},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4032000005245209},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2759000062942505},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25589999556541443}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5826/dpc.160s1a7739","doi":"https://doi.org/10.5826/dpc.160s1a7739","is_oa":true,"landing_page_url":"https://doi.org/10.5826/dpc.160s1a7739","pdf_url":null,"source":{"id":"https://openalex.org/S2764830028","display_name":"Dermatology Practical & Conceptual","issn_l":"2160-9381","issn":["2160-9381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","dongbi-d","ki-jl-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4320800659","host_organization_name":"Mattioli 1885","host_organization_lineage":["https://openalex.org/P4320800659"],"host_organization_lineage_names":["Mattioli 1885"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dermatology Practical & Conceptual","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:02c823bfcf7a4cbf84468b33f5154de2","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/02c823bfcf7a4cbf84468b33f5154de2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dermatology Practical & Conceptual, Vol 16, Iss S1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.5826/dpc.160s1a7739","doi":"https://doi.org/10.5826/dpc.160s1a7739","is_oa":true,"landing_page_url":"https://doi.org/10.5826/dpc.160s1a7739","pdf_url":null,"source":{"id":"https://openalex.org/S2764830028","display_name":"Dermatology Practical & Conceptual","issn_l":"2160-9381","issn":["2160-9381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","dongbi-d","ki-jl-1","poland-20","russia-white-list-2"],"host_organization":"https://openalex.org/P4320800659","host_organization_name":"Mattioli 1885","host_organization_lineage":["https://openalex.org/P4320800659"],"host_organization_lineage_names":["Mattioli 1885"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Dermatology Practical & Conceptual","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.5683000087738037}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2084413241","https://openalex.org/W2765793020","https://openalex.org/W2794825826","https://openalex.org/W2981731882","https://openalex.org/W4225114491","https://openalex.org/W4225597912","https://openalex.org/W4313647451","https://openalex.org/W4365480620","https://openalex.org/W4366966460","https://openalex.org/W4385362878","https://openalex.org/W4387435338","https://openalex.org/W4395055012","https://openalex.org/W4400944237","https://openalex.org/W4405221269","https://openalex.org/W4407186962","https://openalex.org/W4415665659","https://openalex.org/W7126262814","https://openalex.org/W7129190407","https://openalex.org/W7171660462","https://openalex.org/W7172290927"],"related_works":["https://openalex.org/W7223405531","https://openalex.org/W7207592955","https://openalex.org/W7154604610","https://openalex.org/W7130402537","https://openalex.org/W7213637489","https://openalex.org/W7202394043","https://openalex.org/W4412691868","https://openalex.org/W7202186914","https://openalex.org/W7202370588","https://openalex.org/W7140632246"],"abstract_inverted_index":{"Introduction:":[0],"Accurate":[1],"diagnosis":[2,25],"in":[3,72,89],"dermoscopic":[4],"examination":[5],"is":[6],"challenging":[7],"due":[8],"to":[9,40,95,179],"the":[10,18,21,107,157,160,192],"visual":[11],"similarity":[12],"between":[13,98],"skin":[14,29,32,58],"lesion":[15,59,216],"types":[16],"and":[17,26,42,52,75,128,137,168,224],"variability":[19],"within":[20],"same":[22],"group.":[23],"Early":[24],"treatment":[27],"of":[28,109],"diseases,":[30],"especially":[31],"cancer,":[33],"are":[34],"vital.":[35],"Objectives:":[36],"This":[37],"study":[38],"aimed":[39],"develop":[41],"evaluate":[43],"an":[44,83,102],"explainable":[45],"multi-architecture":[46],"framework":[47],"integrating":[48],"convolutional,":[49],"transformer-based,":[50],"hybrid,":[51],"ensemble":[53,158,200],"learning":[54],"approaches":[55],"for":[56],"multi-class":[57],"classification.":[60],"Methods:":[61],"Using":[62],"HAM10000,":[63],"four":[64],"architectures":[65],"(EfficientNet-B0,":[66],"MobileNetV3-Large,":[67],"ResNet34,":[68],"DeiT-Small)":[69],"were":[70],"fine-tuned":[71],"two":[73],"phases":[74],"combined":[76],"into":[77],"a":[78],"validation-optimized,":[79],"macro-F1-driven":[80],"soft-voting":[81],"ensemble;":[82],"independent":[84],"ResNet34+XGBoost":[85],"hybrid":[86],"was":[87,93],"evaluated":[88,144],"parallel.":[90],"Lesion-grouped":[91],"partitioning":[92,110],"used":[94,115],"prevent":[96],"overlap":[97,214],"data":[99],"subsets,":[100],"with":[101,141,163,183,215],"additional":[103],"image-level":[104],"experiment":[105],"assessing":[106],"influence":[108],"strategy":[111],"on":[112],"performance.":[113],"Evaluation":[114],"accuracy,":[116,165],"macro-averaged":[117],"precision,":[118],"recall,":[119],"F1-score,":[120],"per-class":[121],"metrics,":[122],"nested":[123],"5-fold":[124],"cross-validation,":[125],"McNemar's":[126],"test,":[127],"lesion-clustered":[129,185],"bootstrap":[130],"effect":[131],"sizes":[132],"(95%":[133],"CIs).":[134],"Grad-CAM,":[135],"Grad-CAM++,":[136],"LIME":[138],"provided":[139],"interpretability,":[140],"Grad-CAM":[142,195],"localization":[143,209],"against":[145],"segmentation":[146],"masks":[147],"via":[148],"Intersection":[149],"over":[150,174],"Union":[151],"(IoU).":[152],"Results:":[153],"Under":[154],"lesion-grouped":[155,206],"evaluation,":[156],"achieved":[159,201],"highest":[161,193],"performance,":[162],"85.76%":[164],"75.24%":[166],"macro-F1,":[167],"0.971":[169],"macro-AUC.":[170],"Paired":[171],"accuracy":[172],"gains":[173],"comparators":[175],"ranged":[176],"from":[177],"2.36":[178],"7.57":[180],"percentage":[181],"points,":[182],"all":[184],"95%":[186],"CIs":[187],"excluding":[188],"zero.":[189],"ResNet34":[190],"yielded":[191],"mean":[194],"IoU":[196],"(0.456).":[197],"Conclusion:":[198],"The":[199],"improved":[202],"classification":[203],"performance":[204],"under":[205],"evaluation.":[207],"Quantitative":[208],"analysis":[210],"showed":[211],"measurable":[212],"spatial":[213],"regions,":[217],"although":[218],"clinical":[219],"usefulness":[220],"requires":[221],"reader":[222],"studies":[223],"external":[225],"validation.":[226]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-01T00:00:00"}