{"id":"https://openalex.org/W7160607587","doi":"https://doi.org/10.48550/arxiv.2605.05891","title":"MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors","display_name":"MTL-MAD: Multi-Task Learners are Effective Medical Anomaly Detectors","publication_year":2026,"publication_date":"2026-05-07","ids":{"openalex":"https://openalex.org/W7160607587","doi":"https://doi.org/10.48550/arxiv.2605.05891"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05891","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.05891","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037516343","display_name":"Bogdan Bercean","orcid":"https://orcid.org/0000-0003-2443-085X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bercean, Bogdan Alexandru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107114097","display_name":"Florinel Alin Croitoru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Croitoru, Florinel Alin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079598088","display_name":"Vlad Hondru","orcid":"https://orcid.org/0009-0003-8074-6266"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hondru, Vlad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135714918","display_name":"Ciprian Mihai Ceausescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ceausescu, Ciprian Mihai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126334021","display_name":"Andreea Iuliana Ionescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ionescu, Andreea Iuliana","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135703062","display_name":"Radu Tudor Ionescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ionescu, Radu Tudor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037516343"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9728999733924866,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9728999733924866,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.007300000172108412,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.0038999998942017555,"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/anomaly-detection","display_name":"Anomaly detection","score":0.704800009727478},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5579000115394592},{"id":"https://openalex.org/keywords/anomaly","display_name":"Anomaly (physics)","score":0.5145000219345093},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4681999981403351},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.3206999897956848},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.29249998927116394},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.2921999990940094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253999710083008},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.704800009727478},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5579000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5546000003814697},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.5145000219345093},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4681999981403351},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4316999912261963},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05891","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.05891","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05891","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.7874330878257751,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Anomaly":[0],"detection":[1],"in":[2,139],"medical":[3,107],"images":[4],"is":[5,118],"a":[6,20,26,47,65,98,103],"challenging":[7],"task,":[8],"since":[9],"anomalies":[10],"are":[11],"not":[12],"typically":[13],"available":[14],"during":[15,90],"training.":[16],"Recent":[17],"methods":[18],"leverage":[19],"single":[21],"pretext":[22],"task":[23,89],"coupled":[24],"with":[25],"large-scale":[27],"pre-trained":[28],"model":[29,49,62,131],"to":[30,37],"reach":[31],"state-of-the-art":[32,125],"performance.":[33],"Instead,":[34],"we":[35],"propose":[36],"learn":[38],"multiple":[39,57],"self-supervised":[40],"and":[41],"pseudo-labeling":[42],"tasks":[43],"from":[44],"scratch,":[45],"using":[46],"joint":[48,61],"based":[50,79],"on":[51,80,96,127],"Mixture-of-Experts":[52],"(MoE).":[53],"By":[54],"carefully":[55],"integrating":[56],"proxy":[58],"tasks,":[59],"the":[60,83],"effectively":[63],"learns":[64],"robust":[66],"representation":[67],"of":[68,106],"normal":[69],"anatomical":[70],"structures,":[71],"so":[72],"that":[73,101,114],"anomaly":[74,121,134],"scores":[75],"can":[76],"be":[77],"derived":[78],"how":[81],"well":[82],"multi-task":[84,116],"learner":[85,117],"(MTL)":[86],"solves":[87],"each":[88],"inference.":[91],"We":[92],"perform":[93],"comprehensive":[94],"experiments":[95],"BMAD,":[97],"recent":[99],"benchmark":[100],"comprises":[102],"broad":[104],"range":[105],"image":[108],"modalities.":[109],"The":[110],"empirical":[111],"results":[112],"indicate":[113],"our":[115,130],"an":[119],"effective":[120],"detector,":[122],"outperforming":[123],"all":[124],"competitors":[126],"BMAD.":[128],"Moreover,":[129],"produces":[132],"interpretable":[133],"maps,":[135],"potentially":[136],"helping":[137],"physicians":[138],"providing":[140],"more":[141],"accurate":[142],"diagnoses.":[143]},"counts_by_year":[],"updated_date":"2026-05-09T06:16:02.287421","created_date":"2026-05-09T00:00:00"}