{"id":"https://openalex.org/W7126043861","doi":"https://doi.org/10.1109/bibm66473.2025.11356626","title":"Multi-Exit Class Activation Map Guided Feature Masking for Unsupervised Out-of-Distribution Detection in Medical Imaging","display_name":"Multi-Exit Class Activation Map Guided Feature Masking for Unsupervised Out-of-Distribution Detection in Medical Imaging","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126043861","doi":"https://doi.org/10.1109/bibm66473.2025.11356626"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5124279815","display_name":"Zixuan Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zixuan Pan","raw_affiliation_strings":["University of Notre Dame,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100731682","display_name":"Yu-Jen Chen","orcid":"https://orcid.org/0000-0003-4960-3702"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu-Jen Chen","raw_affiliation_strings":["National Tsing Hua University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Taiwan","institution_ids":["https://openalex.org/I25846049"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123221927","display_name":"Jun Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Xia","raw_affiliation_strings":["University of Notre Dame,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124174617","display_name":"Max Ficco","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max Ficco","raw_affiliation_strings":["University of Notre Dame,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123059531","display_name":"Jianxu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121365","display_name":"Leibniz Institute for Analytical Sciences - ISAS","ror":"https://ror.org/02jhqqg57","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210121365"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jianxu Chen","raw_affiliation_strings":["Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V.,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz-Institut für Analytische Wissenschaften - ISAS - e.V.,Germany","institution_ids":["https://openalex.org/I4210121365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111381937","display_name":"Tsung-Yi Ho","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tsung-Yi Ho","raw_affiliation_strings":["The Chinese University of Hong Kong,Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123197509","display_name":"Yiyu Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiyu Shi","raw_affiliation_strings":["University of Notre Dame,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame,USA","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":4,"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":0.73227902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2699","last_page":"2706"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.7487999796867371,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.7487999796867371,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1404000073671341,"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/T11448","display_name":"Face recognition and analysis","score":0.023600000888109207,"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/robustness","display_name":"Robustness (evolution)","score":0.7437999844551086},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6550999879837036},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5957000255584717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.52920001745224},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49129998683929443},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4830000102519989},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.428600013256073},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.41040000319480896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7538999915122986},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7437999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7184000015258789},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5957000255584717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.52920001745224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49129998683929443},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4830000102519989},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.428600013256073},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3578999936580658},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3450999855995178},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2615000009536743}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356626","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2794825826","https://openalex.org/W2914203365","https://openalex.org/W2914568698","https://openalex.org/W2962858109","https://openalex.org/W2963946669","https://openalex.org/W3013277995","https://openalex.org/W3135057764","https://openalex.org/W3159616808","https://openalex.org/W3176482836","https://openalex.org/W4213014431","https://openalex.org/W4312284582","https://openalex.org/W4312776478","https://openalex.org/W4317436377","https://openalex.org/W4317437782","https://openalex.org/W4386075650","https://openalex.org/W4387211299","https://openalex.org/W4387211485","https://openalex.org/W4387211583","https://openalex.org/W4390880024","https://openalex.org/W4391948243","https://openalex.org/W4396621884","https://openalex.org/W4402727489","https://openalex.org/W4403054719","https://openalex.org/W4410296777","https://openalex.org/W4413147756"],"related_works":[],"abstract_inverted_index":{"Out-of-distribution":[0],"(OOD)":[1],"detection":[2,156,231,252],"is":[3,271],"crucial":[4],"for":[5,84,127,138,253,259],"ensuring":[6],"the":[7,69,96,185,239,257],"safety":[8],"and":[9,61,77,163,179,199,201,213,215,244,262],"reliability":[10],"of":[11,51,71,98,187,241],"deep":[12,72],"learning":[13],"models":[14,53,73,264],"in":[15,36,45,124,248,265],"high-stakes":[16],"domains":[17],"such":[18,42,106],"as":[19],"medical":[20,207,254],"imaging.":[21],"However,":[22],"existing":[23],"methods":[24],"often":[25,104],"struggle":[26],"to":[27,95],"detect":[28],"subtle":[29],"or":[30],"localized":[31],"anomalies,":[32],"which":[33],"are":[34,92],"common":[35],"clinical":[37,266],"settings.":[38],"We":[39,190],"hypothesize":[40],"that":[41,79,91,114,134,158,225],"challenges":[43],"stem":[44],"part":[46],"from":[47,170],"a":[48,99,132,152],"limited":[49],"understanding":[50],"how":[52],"focus":[54],"on":[55,110,142,193],"different":[56,75],"image":[57,218],"regions":[58,90],"under":[59,74],"ID":[60,128,195],"OOD":[62,102,130,155,188,208,219,230,251],"inputs.":[63],"To":[64],"investigate":[65],"this,":[66,111],"we":[67,112,145],"analyze":[68],"behavior":[70],"inputs,":[76],"observe":[78],"class":[80],"activation":[81],"maps":[82],"(CAMs)":[83],"in-distribution":[85],"(ID)":[86],"data":[87,103],"typically":[88],"emphasize":[89],"highly":[93],"relevant":[94],"prediction":[97],"model,":[100],"whereas":[101],"lacks":[105],"focused":[107],"activations.":[108],"Building":[109],"find":[113],"masking":[115,247],"input":[116],"images":[117],"with":[118],"inverted":[119],"CAMs":[120,162,169],"induces":[121],"larger":[122],"shifts":[123],"feature":[125,165,181,246],"representations":[126],"than":[129],"data,":[131],"signal":[133],"can":[135],"be":[136],"leveraged":[137],"robust":[139],"detection.":[140,189],"Based":[141],"this":[143],"insight,":[144],"propose":[146],"Multi-Exit":[147],"Class":[148],"Activation":[149],"Map":[150],"(MECAM),":[151],"novel":[153],"unsupervised":[154,250],"framework":[157],"integrates":[159],"aggregated":[160],"multi-exit":[161,242],"CAM-guided":[164,245],"masking.":[166],"By":[167],"combining":[168],"multiple":[171],"network":[172],"depths,":[173],"our":[174],"method":[175],"captures":[176],"both":[177],"global":[178],"local":[180],"representations,":[182],"thereby":[183],"enhancing":[184],"robustness":[186],"evaluate":[191],"MECAM":[192,226],"two":[194],"datasets,":[196,209],"including":[197],"ISIC19":[198],"PathMNIST,":[200],"test":[202],"its":[203,234],"performance":[204],"against":[205],"three":[206],"RSNA":[210],"Pneumonia,":[211],"COVID-19,":[212],"HeadCT,":[214],"one":[216],"natural":[217],"dataset,":[220],"iSUN.":[221],"Comprehensive":[222],"experiments":[223],"demonstrate":[224],"consistently":[227],"outperforms":[228],"state-of-theart":[229],"methods,":[232],"validating":[233],"effectiveness.":[235],"These":[236],"findings":[237],"highlight":[238],"potential":[240],"architectures":[243],"advancing":[249],"imaging,":[255],"paving":[256],"way":[258],"more":[260],"reliable":[261],"interpretable":[263],"practice.":[267],"The":[268],"source":[269],"code":[270],"available":[272],"at":[273],"https://github.com/zx-pan/MECAM-OOD.":[274]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-30T00:00:00"}