{"id":"https://openalex.org/W7140208621","doi":"https://doi.org/10.1016/j.procs.2026.03.099","title":"Comparative Analysis of CNNs and Vision Transformers for Lesion Classification in Capsule Endoscopy","display_name":"Comparative Analysis of CNNs and Vision Transformers for Lesion Classification in Capsule Endoscopy","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140208621","doi":"https://doi.org/10.1016/j.procs.2026.03.099"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2026.03.099","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.03.099","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1016/j.procs.2026.03.099","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Carolina Tabosa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Carolina Tabosa","raw_affiliation_strings":["University of Tr\u00e1s-os-Montes e Alto Douro, Vila Real, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tr\u00e1s-os-Montes e Alto Douro, Vila Real, Portugal","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Marta Salgado","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marta Salgado","raw_affiliation_strings":["Centro Hospitalar Universit\u00e1rio de Santo Ant\u00f3nio, Porto, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centro Hospitalar Universit\u00e1rio de Santo Ant\u00f3nio, Porto, Portugal","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Danilo Leite","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danilo Leite","raw_affiliation_strings":["University of Tr\u00e1s-os-Montes e Alto Douro, Vila Real, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tr\u00e1s-os-Montes e Alto Douro, Vila Real, Portugal","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Ant\u00f3nio Cunha","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ant\u00f3nio Cunha","raw_affiliation_strings":["ALGORITMI Research Centre, Guimar\u00e3es, Portugal","University of Tr\u00e1s-os-Montes e Alto Douro, Vila Real, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALGORITMI Research Centre, Guimar\u00e3es, Portugal","institution_ids":[]},{"raw_affiliation_string":"University of Tr\u00e1s-os-Montes e Alto Douro, Vila Real, Portugal","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66059894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"278","issue":null,"first_page":"1186","last_page":"1193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11378","display_name":"Gastrointestinal Bleeding Diagnosis and Treatment","score":0.8853999972343445,"subfield":{"id":"https://openalex.org/subfields/2715","display_name":"Gastroenterology"},"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/T11378","display_name":"Gastrointestinal Bleeding Diagnosis and Treatment","score":0.8853999972343445,"subfield":{"id":"https://openalex.org/subfields/2715","display_name":"Gastroenterology"},"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/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.10220000147819519,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.0005000000237487257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5716000199317932},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49540001153945923},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4778999984264374},{"id":"https://openalex.org/keywords/capsule-endoscopy","display_name":"Capsule endoscopy","score":0.45750001072883606},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.41760000586509705},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4147999882698059},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4050999879837036},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.40209999680519104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8736000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6944000124931335},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C2777333622","wikidata":"https://www.wikidata.org/wiki/Q116753","display_name":"Capsule endoscopy","level":2,"score":0.45750001072883606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45100000500679016},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4147999882698059},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40209999680519104},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31790000200271606},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.25589999556541443},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2026.03.099","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.03.099","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2026.03.099","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2026.03.099","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8546976447105408,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2616247523","https://openalex.org/W3112313341","https://openalex.org/W3164631742","https://openalex.org/W4308495732","https://openalex.org/W4311015156","https://openalex.org/W4402413646","https://openalex.org/W4402499135"],"related_works":[],"abstract_inverted_index":{"Video":[0],"capsule":[1],"endoscopy":[2],"(VCE)":[3],"enables":[4],"high-resolution":[5],"visualisation":[6],"of":[7,17,19,116,158],"the":[8,54,90,156,180],"small":[9],"bowel":[10],"but":[11],"remains":[12],"constrained":[13],"by":[14,127],"manual":[15],"review":[16],"thousands":[18],"frames,":[20],"which":[21,162],"is":[22],"time-consuming":[23],"and":[24,69,80,86,119,131,155,189,199,204,214],"error-prone":[25],"under":[26,202],"class":[27,153],"imbalance.":[28],"This":[29],"study":[30],"investigates":[31],"deep":[32],"learning":[33],"for":[34,174,182],"automatic":[35],"multiclass":[36],"lesion":[37],"classification":[38],"in":[39,104],"VCE,":[40],"comparing":[41],"two":[42,48],"convolutional":[43],"networks":[44],"(ResNet-50,":[45],"EfficientNet-B3)":[46],"with":[47,78,100,196],"Vision":[49],"Transformers":[50],"(Swin,":[51],"DeiT)":[52],"on":[53,147,185,211],"public":[55,150],"Kvasir-Capsule":[56],"dataset":[57],"(47,161":[58],"images;":[59],"11":[60],"classes).":[61],"The":[62],"pipeline":[63],"comprises":[64],"standard":[65],"preprocessing,":[66],"class-aware":[67],"augmentation":[68],"adaptive":[70],"data":[71,74],"augmentation,":[72],"stratified":[73],"partitioning,":[75],"hyperparameter":[76],"optimisation":[77],"Optuna,":[79],"evaluation":[81],"using":[82],"accuracy,":[83],"precision,":[84],"recall,":[85],"F1-score.":[87],"DeiT":[88],"achieved":[89],"best":[91],"overall":[92],"performance":[93],"(accuracy":[94],"=":[95,98],"0.98;":[96],"F1":[97],"0.96),":[99],"strong":[101],"class-wise":[102],"results":[103],"clinically":[105],"salient":[106],"categories":[107],"(e.g.,":[108],"ulcer,":[109],"fresh":[110],"blood,":[111],"angiectasia),":[112],"indicating":[113],"effective":[114],"modelling":[115],"long-range":[117],"dependencies":[118],"subtle":[120],"patterns.":[121],"We":[122],"further":[123],"assess":[124],"computational":[125],"feasibility":[126],"reporting":[128],"training":[129],"configuration":[130],"indicative":[132],"inference":[133],"time":[134,213],"per":[135],"image,":[136],"supporting":[137],"potential":[138],"integration":[139],"into":[140],"assisted":[141],"reading":[142,212],"workflows.":[143],"Limitations":[144],"include":[145],"reliance":[146],"a":[148],"single":[149],"dataset,":[151],"pronounced":[152],"imbalance,":[154,203],"absence":[157],"prospective":[159,206],"clinical":[160],"validation,":[161,191],"may":[163],"affect":[164],"generalisability.":[165],"These":[166],"findings":[167],"position":[168],"Transformer-based":[169],"models":[170],"as":[171],"promising":[172],"candidates":[173],"VCE":[175],"decision":[176],"support,":[177],"while":[178],"underscoring":[179],"need":[181],"future":[183],"work":[184],"(i)":[186],"multicentric":[187],"datasets":[188],"external":[190],"(ii)":[192],"comprehensive":[193],"statistical":[194],"analysis":[195],"confidence":[197],"intervals":[198],"robust":[200],"baselines":[201],"(iii)":[205],"studies":[207],"quantifying":[208],"end-to-end":[209],"impact":[210],"diagnostic":[215],"safety.":[216]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}