{"id":"https://openalex.org/W7161290840","doi":"https://doi.org/10.1016/j.array.2026.100892","title":"Lesion-aware dual attention fusion with MedSAM-2 and hierarchical Swin-SENet for robust diabetic retinopathy grading","display_name":"Lesion-aware dual attention fusion with MedSAM-2 and hierarchical Swin-SENet for robust diabetic retinopathy grading","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161290840","doi":"https://doi.org/10.1016/j.array.2026.100892"},"language":"en","primary_location":{"id":"doi:10.1016/j.array.2026.100892","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100892","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.array.2026.100892","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136233270","display_name":"Kathiresh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kathiresh Gopalakarishnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072174527","display_name":"Deepika Roselind Johnson","orcid":"https://orcid.org/0000-0002-3610-2979"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Deepika Roselind Johnson","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India \u2013 600041"],"raw_orcid":"https://orcid.org/0000-0002-3610-2979","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India \u2013 600041","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134946680","display_name":"G Logeswari","orcid":null},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"G. Logeswari","raw_affiliation_strings":["School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India \u2013 600041"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Chennai, India \u2013 600041","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5072174527"],"corresponding_institution_ids":["https://openalex.org/I876193797"],"apc_list":{"value":1350,"currency":"USD","value_usd":1350},"apc_paid":{"value":1350,"currency":"USD","value_usd":1350},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75662997,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"30","issue":null,"first_page":"100892","last_page":"100892"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.9581999778747559,"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"}},"topics":[{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.9581999778747559,"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/T10170","display_name":"Retinal Diseases and Treatments","score":0.022099999710917473,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0024999999441206455,"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/segmentation","display_name":"Segmentation","score":0.7354999780654907},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6237000226974487},{"id":"https://openalex.org/keywords/grading","display_name":"Grading (engineering)","score":0.5604000091552734},{"id":"https://openalex.org/keywords/diabetic-retinopathy","display_name":"Diabetic retinopathy","score":0.5533000230789185},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5401999950408936},{"id":"https://openalex.org/keywords/cohens-kappa","display_name":"Cohen's kappa","score":0.4124999940395355},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.38690000772476196}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7648000121116638},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7354999780654907},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6237000226974487},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.566100001335144},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.5604000091552734},{"id":"https://openalex.org/C2779829184","wikidata":"https://www.wikidata.org/wiki/Q631361","display_name":"Diabetic retinopathy","level":3,"score":0.5533000230789185},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5401999950408936},{"id":"https://openalex.org/C163864269","wikidata":"https://www.wikidata.org/wiki/Q1107106","display_name":"Cohen's kappa","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34929999709129333},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.3463999927043915},{"id":"https://openalex.org/C141898687","wikidata":"https://www.wikidata.org/wiki/Q1501997","display_name":"Hausdorff distance","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C2776391266","wikidata":"https://www.wikidata.org/wiki/Q9612","display_name":"Fundus (uterus)","level":2,"score":0.321399986743927},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.305400013923645},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C2778724333","wikidata":"https://www.wikidata.org/wiki/Q14401","display_name":"Kappa","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2858000099658966},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25209999084472656},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.array.2026.100892","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100892","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:db0e7cb8663443fcbba10bb3ba8e5d80","is_oa":true,"landing_page_url":"https://doaj.org/article/db0e7cb8663443fcbba10bb3ba8e5d80","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,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Array, Vol 30, Iss , Pp 100892- (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.array.2026.100892","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.array.2026.100892","pdf_url":null,"source":{"id":"https://openalex.org/S4210194039","display_name":"Array","issn_l":"2590-0056","issn":["2590-0056"],"is_oa":true,"is_in_doaj":true,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Array","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7306272983551025,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2162698990","https://openalex.org/W2194775991","https://openalex.org/W2557738935","https://openalex.org/W2752782242","https://openalex.org/W2765490497","https://openalex.org/W2828862258","https://openalex.org/W2963446712","https://openalex.org/W3081111549","https://openalex.org/W3081752372","https://openalex.org/W3113253886","https://openalex.org/W3138516171","https://openalex.org/W3175311671","https://openalex.org/W4296341525","https://openalex.org/W4379141755","https://openalex.org/W4385481295","https://openalex.org/W4388037833","https://openalex.org/W4392203599","https://openalex.org/W4401819803","https://openalex.org/W4402242741","https://openalex.org/W4406990476","https://openalex.org/W4412825822"],"related_works":[],"abstract_inverted_index":{"Background":[0],"and":[1,17,50,56,171,183,202,222,235,272],"Objective":[2],"Diabetic":[3],"retinopathy":[4],"(DR)":[5],"ranks":[6],"as":[7,53],"the":[8,15,147,217],"major":[9],"cause":[10],"of":[11,33,61,136,181,186,200,205,211,237],"preventable":[12],"blindness":[13],"in":[14,39],"world,":[16],"is":[18,115,153,165,229,264],"estimated":[19],"to":[20,74,81,103,118,255,266],"affect":[21],"some":[22],"160":[23],"million":[24],"diabetics.":[25],"Severity":[26],"grading":[27,195,261],"demands":[28],"a":[29,76,89,105,125,137,169,178,251],"very":[30],"accurate":[31],"identification":[32],"subtle,":[34],"spatially":[35],"heterogeneous,":[36],"retinal":[37,149],"lesions":[38],"5":[40],"clinical":[41],"stages.":[42],"Current":[43],"deep":[44],"learning":[45],"pipelines":[46],"regard":[47],"lesion":[48,107,268],"segmentation":[49,170,179,257],"disease":[51],"classification":[52],"separate":[54],"processes":[55],"do":[57],"not":[58],"make":[59],"use":[60],"spatial":[62,120],"pathological":[63,143],"priors":[64,258],"for":[65,220],"feature":[66],"learning.":[67],"To":[68],"this":[69,71,84],"end,":[70],"study":[72],"aims":[73],"develop":[75],"unified":[77],"segmentation-guided":[78],"dual-attention":[79],"framework":[80,164],"explicitly":[82],"fill":[83],"methodological":[85],"gap":[86],"by":[87,123,141],"designing":[88],"learnable":[90,119,253],"lesion-aware":[91],"attention":[92,121],"fusion":[93],"mechanism.":[94],"Methods":[95],"Medical":[96],"Segment":[97],"Anything":[98],"Model-2":[99],"(MedSAM-2;":[100],"ViT-B":[101],"backbone)":[102],"provide":[104],"soft":[106],"probability":[108],"map":[109,114],"on":[110,188,241,275],"fundus":[111],"images.":[112],"This":[113],"then":[116],"translated":[117],"weights":[122],"using":[124,168],"novel":[126],"Lesion-Aware":[127],"Attention":[128],"Fusion":[129],"(LAAF)":[130],"module,":[131],"which":[132,263],"reweights":[133],"intermediate":[134],"features":[135],"hierarchical":[138],"Swin-SENet":[139],"classifier":[140],"boosting":[142],"regions":[144],"while":[145],"maintaining":[146],"global":[148],"context.":[150],"Inter-class":[151],"discriminability":[152],"further":[154],"improved":[155],"through":[156,159],"channel-wise":[157],"recalibration":[158],"Squeeze-and-Excitation":[160],"(SE)":[161],"blocks.":[162],"The":[163,213,247],"trained":[166],"end-to-end":[167],"weighted":[172],"cross-entropy":[173],"loss.":[174],"Results":[175],"MedSAM-2":[176],"achieves":[177,196],"IoU":[180],"0.8978":[182],"Dice":[184],"coefficient":[185],"0.8843":[187],"IDRiD":[189],"(988":[190],"augmented":[191],"images).":[192,245],"Five-class":[193],"DR":[194,224],"92.7%":[197],"accuracy,":[198],"F1-score":[199],"0.92":[201],"Cohen's":[203],"Kappa":[204],"0.89,":[206],"with":[207,232],"bootstrap":[208],"95%":[209],"CI":[210],"91.1-94.2%.":[212],"LAAF":[214,248],"module":[215,249],"shows":[216],"highest":[218],"improvement":[219],"Mild":[221],"Moderate":[223],"(F1:":[225],"0.88,":[226],"0.90).":[227],"It":[228],"cross-dataset":[230],"generalizable":[231],"89.3%":[233],"accuracy":[234],"kappa":[236],"0.85":[238],"when":[239],"tested":[240],"APTOS":[242],"2019":[243],"(3,662":[244],"Conclusions":[246],"offers":[250],"principled":[252],"route":[254],"incorporate":[256],"into":[259],"transformer-based":[260],"networks,":[262],"shown":[265],"enhance":[267],"sensitivity,":[269],"inter-grade":[270],"separability":[271],"diagnostic":[273],"reliability":[274],"various":[276],"benchmark":[277],"datasets.":[278]},"counts_by_year":[],"updated_date":"2026-06-15T08:34:33.830935","created_date":"2026-05-16T00:00:00"}