{"id":"https://openalex.org/W7225323786","doi":"https://doi.org/10.1186/s12880-026-03007-6","title":"A unified attention-gated multi-task network for joint classification and lesion segmentation of breast ultrasound images","display_name":"A unified attention-gated multi-task network for joint classification and lesion segmentation of breast ultrasound images","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225323786","doi":"https://doi.org/10.1186/s12880-026-03007-6"},"language":"en","primary_location":{"id":"doi:10.1186/s12880-026-03007-6","doi":"https://doi.org/10.1186/s12880-026-03007-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12880-026-03007-6","pdf_url":null,"source":{"id":"https://openalex.org/S6505649","display_name":"BMC Medical Imaging","issn_l":"1471-2342","issn":["1471-2342"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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":"BMC Medical Imaging","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12880-026-03007-6","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152987350","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-8627-2327","observed_orcids":["https://orcid.org/0000-0002-8627-2327"]},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]},{"id":"https://openalex.org/I4210127266","display_name":"First Affiliated Hospital of Chengdu Medical College","ror":"https://ror.org/03jckbw05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210127266"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China"],"raw_orcid":"https://orcid.org/0000-0002-8627-2327","affiliations":[{"raw_affiliation_string":"Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China","institution_ids":["https://openalex.org/I207528943","https://openalex.org/I4210127266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125905182","display_name":"Shi-Min Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]},{"id":"https://openalex.org/I4210127266","display_name":"First Affiliated Hospital of Chengdu Medical College","ror":"https://ror.org/03jckbw05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210127266"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi-min Liang","raw_affiliation_strings":["Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China","institution_ids":["https://openalex.org/I207528943","https://openalex.org/I4210127266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414645","display_name":"Jian Liu","orcid":"https://orcid.org/0000-0001-9719-2923","observed_orcids":["https://orcid.org/0000-0001-9719-2923"]},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]},{"id":"https://openalex.org/I4210127266","display_name":"First Affiliated Hospital of Chengdu Medical College","ror":"https://ror.org/03jckbw05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210127266"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Liu","raw_affiliation_strings":["Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China","institution_ids":["https://openalex.org/I207528943","https://openalex.org/I4210127266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319718","display_name":"Wen Wen","orcid":"https://orcid.org/0000-0002-5189-2139","observed_orcids":["https://orcid.org/0000-0002-5189-2139"]},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]},{"id":"https://openalex.org/I4210127266","display_name":"First Affiliated Hospital of Chengdu Medical College","ror":"https://ror.org/03jckbw05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210127266"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wen Wen","raw_affiliation_strings":["Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Ultrasound, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China","institution_ids":["https://openalex.org/I207528943","https://openalex.org/I4210127266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101081072","display_name":"Fan Ying-jun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I207528943","display_name":"Chengdu Medical College","ror":"https://ror.org/01c4jmp52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I207528943"]},{"id":"https://openalex.org/I4210127266","display_name":"First Affiliated Hospital of Chengdu Medical College","ror":"https://ror.org/03jckbw05","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210127266"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ying-jun Fan","raw_affiliation_strings":["Department of Neurosurgery, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China","Key Laboratory of Neural Injury and Repair at Chengdu Medical College of Sichuan Province, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Neurosurgery, Clinical College of Chengdu Medical College, The First Affiliated Hospital of Chengdu Medical College, Chengdu, 610599, China","institution_ids":["https://openalex.org/I207528943","https://openalex.org/I4210127266"]},{"raw_affiliation_string":"Key Laboratory of Neural Injury and Repair at Chengdu Medical College of Sichuan Province, Chengdu, China","institution_ids":["https://openalex.org/I207528943"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100319718","https://openalex.org/A5101081072"],"corresponding_institution_ids":["https://openalex.org/I207528943","https://openalex.org/I4210127266"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"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":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9810000061988831,"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":0.9810000061988831,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.01720000058412552,"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"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.0003000000142492354,"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/breast-ultrasound","display_name":"breast ultrasound","score":0.9330000281333923},{"id":"https://openalex.org/keywords/breast-cancer-screening","display_name":"breast cancer screening","score":0.7639999985694885},{"id":"https://openalex.org/keywords/lesion-classification","display_name":"lesion classification","score":0.6079999804496765},{"id":"https://openalex.org/keywords/lesion-segmentation","display_name":"lesion segmentation","score":0.9829999804496765},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.9290000200271606},{"id":"https://openalex.org/keywords/attention-gate","display_name":"attention gate","score":0.8640000224113464},{"id":"https://openalex.org/keywords/shared-encoder","display_name":"shared encoder","score":0.7239999771118164},{"id":"https://openalex.org/keywords/resnet34","display_name":"ResNet34","score":0.9440000057220459},{"id":"https://openalex.org/keywords/parameter-efficiency","display_name":"parameter efficiency","score":0.699999988079071},{"id":"https://openalex.org/keywords/computer-aided-diagnosis","display_name":"computer-aided diagnosis","score":0.9430000185966492},{"id":"https://openalex.org/keywords/busi-dataset","display_name":"BUSI dataset","score":0.8799999952316284},{"id":"https://openalex.org/keywords/benign-malignant-classification","display_name":"benign and malignant classification","score":0.609000027179718},{"id":"https://openalex.org/keywords/model-size-reduction","display_name":"model size reduction","score":0.453000009059906},{"id":"https://openalex.org/keywords/dice-score","display_name":"Dice score","score":0.3179999887943268},{"id":"https://openalex.org/keywords/mcnemar-test","display_name":"McNemar test","score":0.6690000295639038},{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.9490000009536743},{"id":"https://openalex.org/keywords/bootstrap-confidence-intervals","display_name":"bootstrap confidence intervals","score":0.8420000076293945},{"id":"https://openalex.org/keywords/breast-lesion-classification","display_name":"breast lesion classification","score":0.36800000071525574}],"concepts":[{"id":"https://openalex.org/C186282968","wikidata":"https://www.wikidata.org/wiki/Q1434261","display_name":"McNemar's test","level":2,"score":0.8519999980926514},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.829800009727478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7211999893188477},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.59579998254776},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.5253999829292297},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C2777423100","wikidata":"https://www.wikidata.org/wiki/Q1888238","display_name":"Breast ultrasound","level":5,"score":0.4706000089645386},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.39910000562667847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3921999931335449},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2777432617","wikidata":"https://www.wikidata.org/wiki/Q22905905","display_name":"Breast imaging","level":5,"score":0.303600013256073},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.3034999966621399},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.2793000042438507},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C2781156865","wikidata":"https://www.wikidata.org/wiki/Q827023","display_name":"Lesion","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2628999948501587},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/s12880-026-03007-6","doi":"https://doi.org/10.1186/s12880-026-03007-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12880-026-03007-6","pdf_url":null,"source":{"id":"https://openalex.org/S6505649","display_name":"BMC Medical Imaging","issn_l":"1471-2342","issn":["1471-2342"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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":"BMC Medical Imaging","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/s12880-026-03007-6","doi":"https://doi.org/10.1186/s12880-026-03007-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12880-026-03007-6","pdf_url":null,"source":{"id":"https://openalex.org/S6505649","display_name":"BMC Medical Imaging","issn_l":"1471-2342","issn":["1471-2342"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","doyens","jufo-1","ki-jl-1","medline","norway-1","oarl","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"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":"BMC Medical Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8048999905586243,"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3182850645","https://openalex.org/W7161230087","https://openalex.org/W4409275281","https://openalex.org/W4225009244","https://openalex.org/W4315926030","https://openalex.org/W7172260521","https://openalex.org/W4386597152","https://openalex.org/W4405401085","https://openalex.org/W4290973154","https://openalex.org/W7201958279"],"abstract_inverted_index":{"Breast":[0],"ultrasound":[1,302],"(BUS)":[2],"is":[3,13],"widely":[4],"used":[5],"for":[6,108,159,265,287,332,342],"breast":[7,301],"cancer":[8],"screening,":[9],"but":[10],"its":[11],"interpretation":[12],"operator-dependent.":[14],"In":[15],"computer-aided":[16,335],"diagnosis,":[17],"lesion":[18,21,86,212,305],"classification":[19,81,185,203,303],"and":[20,37,85,125,150,193,268,304,337],"segmentation":[22,87,142,213,227,246,306],"are":[23],"conventionally":[24],"addressed":[25],"by":[26,167],"separate":[27,289],"deep-learning":[28],"models,":[29,316],"which":[30],"increases":[31],"the":[32,52,94,112,138,145,160,171,179,201,225,239,276,320,326,329],"parameter":[33,168,321],"budget,":[34],"computational":[35],"cost,":[36],"complexity":[38],"of":[39,54,187,191,196,313,328],"clinical":[40],"deployment.":[41],"It":[42],"remains":[43],"unclear":[44],"whether":[45],"a":[46,73,89,119,122,126,184],"single":[47,90,295],"multi-task":[48,67,297],"model":[49,114,128,182,204,228,257,278,298],"can":[50,299],"match":[51],"performance":[53,214],"two":[55,288],"dedicated":[56,117,202,226,314],"single-task":[57,315,346],"models":[58,134,143],"while":[59,317],"reducing":[60],"this":[61],"overhead.":[62],"We":[63],"developed":[64],"an":[65],"attention-gated":[66,296],"learning":[68],"(MTL)":[69],"framework":[70,331],"built":[71],"on":[72],"shared":[74],"ResNet-34":[75],"encoder":[76],"that":[77,312],"simultaneously":[78],"performs":[79],"three-class":[80],"(normal,":[82],"benign,":[83],"malignant)":[84],"in":[88],"forward":[91],"pass.":[92],"Using":[93],"publicly":[95],"available":[96],"BUSI":[97],"dataset":[98],"(780":[99],"images;":[100],"stratified":[101],"70%/15%/15%":[102],"train/validation/test":[103],"split;":[104],"fixed":[105],"random":[106],"seed":[107],"reproducibility),":[109],"we":[110],"compared":[111,136,283],"unified":[113,180,256,277,330],"against":[115],"three":[116],"baselines:":[118],"classification-only":[120],"model,":[121,124],"segmentation-only":[123,127,240],"equipped":[129],"with":[130,262,284,307],"attention":[131,236],"gates.":[132],"Classification":[133],"were":[135,157],"using":[137,144],"paired":[139,146],"McNemar":[140,207],"test,":[141,149],"Wilcoxon":[147,231],"signed-rank":[148],"bootstrap":[151],"95%":[152,218],"confidence":[153],"intervals":[154],"(1,000":[155],"resamples)":[156],"computed":[158],"principal":[161],"metrics.":[162],"Model":[163],"efficiency":[164],"was":[165,221],"quantified":[166],"count.":[169,322],"On":[170],"held-out":[172],"test":[173],"set":[174],"(":[175],"n":[176],"=":[177,209,233,253],"117),":[178],"MTL":[181],"achieved":[183],"accuracy":[186,247,308,343],"93.16%,":[188],"macro":[189,194],"F1-score":[190],"0.931,":[192],"AUC":[195],"0.984,":[197],"statistically":[198,222,309],"comparable":[199,223,310],"to":[200,224,238,311],"(accuracy":[205],"91.45%;":[206],"p":[208,232,252],"0.63).":[210],"Its":[211],"(mean":[215],"Dice":[216],"0.766,":[217],"CI":[219],"0.710\u20130.819)":[220],"(Dice":[229,248],"0.810;":[230,251],"0.22).":[234],"Adding":[235],"gates":[237],"baseline":[241],"did":[242],"not":[243],"significantly":[244],"change":[245],"0.813":[249],"vs.":[250],"0.50).":[254],"The":[255],"preserved":[258],"clinically":[259],"important":[260],"behaviour,":[261],"100%":[263],"recall":[264],"normal":[266],"images":[267],"no":[269],"malignant":[270],"case":[271],"misclassified":[272],"as":[273],"normal.":[274],"Critically,":[275],"required":[279],"24.7":[280],"million":[281,286],"parameters,":[282],"45.9":[285],"task-specific":[290],"models\u2014a":[291],"46%":[292],"reduction.":[293],"A":[294],"deliver":[300],"nearly":[318],"halving":[319],"These":[323],"findings":[324],"support":[325],"value":[327],"efficient,":[333],"integrated":[334],"diagnosis":[336],"workflow":[338],"consolidation,":[339],"rather":[340],"than":[341],"gains":[344],"over":[345],"approaches.":[347]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}