{"id":"https://openalex.org/W7164179484","doi":"https://doi.org/10.48550/arxiv.2606.11032","title":"U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training","display_name":"U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164179484","doi":"https://doi.org/10.48550/arxiv.2606.11032"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11032","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.11032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138365490","display_name":"Zhiwen Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zhiwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138357413","display_name":"Jiayin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiayin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138296117","display_name":"Hao Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138342356","display_name":"Hui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006950155","display_name":"Zihua Wang","orcid":"https://orcid.org/0000-0001-6178-3422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033792432","display_name":"Bingzheng Wei","orcid":"https://orcid.org/0000-0001-6979-0459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.8672999739646912,"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/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.8672999739646912,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.04399999976158142,"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/T11216","display_name":"Radiation Detection and Scintillator Technologies","score":0.015799999237060547,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6898000240325928},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.6567000150680542},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.578000009059906},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5016000270843506},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.49950000643730164},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4936999976634979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44690001010894775},{"id":"https://openalex.org/keywords/image-denoising","display_name":"Image denoising","score":0.4275999963283539}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6919999718666077},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6887999773025513},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.578000009059906},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4936999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.4275999963283539},{"id":"https://openalex.org/C2775842073","wikidata":"https://www.wikidata.org/wiki/Q208376","display_name":"Positron emission tomography","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.39579999446868896},{"id":"https://openalex.org/C2779751349","wikidata":"https://www.wikidata.org/wiki/Q1474480","display_name":"Scanner","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3086000084877014},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2775999903678894}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11032","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11032","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"deep":[1],"learning":[2],"models":[3,37],"for":[4],"Positron":[5],"Emission":[6],"Tomography":[7],"(PET)":[8],"image":[9],"denoising":[10,155],"often":[11],"suffer":[12],"from":[13,31],"severe":[14],"performance":[15,156],"degradation":[16],"under":[17,161],"distribution":[18,163],"shifts,":[19,164],"fundamentally":[20],"restricting":[21],"their":[22],"robust":[23,60],"clinical":[24],"deployment.":[25],"This":[26],"lack":[27],"of":[28,35,90,101],"generalization":[29,160],"stems":[30],"the":[32,87,98,135],"conventional":[33],"paradigm":[34],"fixed-parameter":[36],"that":[38,69,150],"cannot":[39],"adapt":[40],"to":[41,75,86,95],"variations":[42],"in":[43],"test":[44,92],"data":[45],"(e.g.,":[46],"dose":[47,168],"levels":[48,169],"or":[49],"scanner":[50],"types)":[51],"after":[52],"training.":[53],"To":[54],"overcome":[55],"this":[56],"limitation":[57],"and":[58,118,129,142,157,170],"achieve":[59],"generalization,":[61],"we":[62],"introduce":[63],"U-TTT,":[64],"a":[65,107,112,119],"novel":[66],"U-shaped":[67],"model":[68,78],"integrates":[70],"Test-Time":[71,114,121],"Training":[72,115,122],"(TTT)":[73],"layers":[74],"dynamically":[76],"adjust":[77],"parameters":[79],"during":[80],"inference":[81],"through":[82],"self-supervision,":[83],"thereby":[84],"adapting":[85],"specific":[88],"characteristics":[89],"each":[91],"instance.":[93],"Furthermore,":[94],"comprehensively":[96],"capture":[97],"complex":[99],"degradations":[100],"3D":[102],"PET":[103,154],"data,":[104],"U-TTT":[105,151],"features":[106],"dual-domain":[108],"adaptation":[109],"mechanism":[110],"comprising":[111],"Spatial":[113],"(S-TTT)":[116],"layer":[117,127,137],"Frequency":[120],"(F-TTT)":[123],"layer.":[124],"The":[125],"S-TTT":[126],"captures":[128],"corrects":[130],"spatial":[131],"structural":[132],"degradations,":[133],"while":[134],"F-TTT":[136],"suppresses":[138],"global":[139],"noise":[140],"spectra":[141],"restores":[143],"delicate":[144],"high-frequency":[145],"details.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"achieves":[152],"state-of-the-art":[153],"exhibits":[158],"superior":[159],"challenging":[162],"including":[165],"both":[166],"unseen":[167,171],"scanners.":[172],"Our":[173],"code":[174],"will":[175],"be":[176],"available":[177],"at":[178],"https://github.com/Yaziwel/U-TTT.":[179]},"counts_by_year":[],"updated_date":"2026-07-09T05:49:46.723101","created_date":"2026-06-11T00:00:00"}