{"id":"https://openalex.org/W4306706459","doi":"https://doi.org/10.48550/arxiv.2210.07761","title":"Improved automated lesion segmentation in whole-body FDG/PET-CT via Test-Time Augmentation","display_name":"Improved automated lesion segmentation in whole-body FDG/PET-CT via Test-Time Augmentation","publication_year":2022,"publication_date":"2022-10-14","ids":{"openalex":"https://openalex.org/W4306706459","doi":"https://doi.org/10.48550/arxiv.2210.07761"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2210.07761","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.07761","pdf_url":"https://arxiv.org/pdf/2210.07761","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2210.07761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112609382","display_name":"Sepideh Amiri","orcid":"https://orcid.org/0000-0002-2848-4671","observed_orcids":["https://orcid.org/0000-0002-2848-4671"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Amiri, Sepideh","raw_affiliation_strings":["Department of Computer Science , University of Copenhagen , Copenhagen 2100 , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Copenhagen , Copenhagen 2100 , Denmark","institution_ids":["https://openalex.org/I124055696"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070871008","display_name":"Bulat Ibragimov","orcid":"https://orcid.org/0000-0001-7739-7788","observed_orcids":["https://orcid.org/0000-0001-7739-7788"]},"institutions":[{"id":"https://openalex.org/I124055696","display_name":"University of Copenhagen","ror":"https://ror.org/035b05819","country_code":"DK","type":"education","lineage":["https://openalex.org/I124055696"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Ibragimov, Bulat","raw_affiliation_strings":["Department of Computer Science , University of Copenhagen , Copenhagen 2100 , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Copenhagen , Copenhagen 2100 , Denmark","institution_ids":["https://openalex.org/I124055696"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I124055696"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9609000086784363,"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"}},"topics":[{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9609000086784363,"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/T10522","display_name":"Medical Imaging Techniques and Applications","score":0.012299999594688416,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.0071000000461936,"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/tumor-segmentation","display_name":"tumor segmentation","score":0.7260000109672546},{"id":"https://openalex.org/keywords/fdg-pet-ct","display_name":"FDG PET/CT","score":0.8270000219345093},{"id":"https://openalex.org/keywords/test-time-augmentation","display_name":"test-time augmentation","score":0.9710000157356262},{"id":"https://openalex.org/keywords/whole-body-pet","display_name":"whole-body PET","score":0.6019999980926514},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.8220000267028809},{"id":"https://openalex.org/keywords/nnu-net","display_name":"nnU-Net","score":0.9079999923706055},{"id":"https://openalex.org/keywords/fine-tuning-pre-trained-models","display_name":"pre-trained model fine-tuning","score":0.7490000128746033},{"id":"https://openalex.org/keywords/tumor-burden-assessment","display_name":"tumor burden assessment","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.780624270439148},{"id":"https://openalex.org/C2775842073","wikidata":"https://www.wikidata.org/wiki/Q208376","display_name":"Positron emission tomography","level":2,"score":0.6958192586898804},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6161969900131226},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.533714771270752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5278359055519104},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4860880672931671},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48500654101371765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45169445872306824},{"id":"https://openalex.org/C2989005","wikidata":"https://www.wikidata.org/wiki/Q214963","display_name":"Nuclear medicine","level":1,"score":0.3599283695220947},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.32953646779060364},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.3007325530052185}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2210.07761","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.07761","pdf_url":"https://arxiv.org/pdf/2210.07761","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2210.07761","doi":"https://doi.org/10.48550/arxiv.2210.07761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2210.07761","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2210.07761","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2210.07761","pdf_url":"https://arxiv.org/pdf/2210.07761","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6240000128746033,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4306706459.pdf","grobid_xml":"https://content.openalex.org/works/W4306706459.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W4321232185"],"related_works":["https://openalex.org/W4320536052","https://openalex.org/W4306815056","https://openalex.org/W4294753700","https://openalex.org/W4319338997","https://openalex.org/W4322718437","https://openalex.org/W4296414789","https://openalex.org/W7162104769","https://openalex.org/W4387075122","https://openalex.org/W4416791380","https://openalex.org/W4386977833"],"abstract_inverted_index":{"Numerous":[0],"oncology":[1],"indications":[2],"have":[3,58],"extensively":[4],"quantified":[5],"metabolically":[6,36],"active":[7,37],"tumors":[8,99],"using":[9,44,130],"positron":[10],"emission":[11,19],"tomography":[12,16,20],"(PET)":[13],"and":[14,28,34,110,120,141,178,192],"computed":[15],"(CT).":[17],"F-fluorodeoxyglucose-positron":[18],"(FDG-PET)":[21],"is":[22,53,205,217],"frequently":[23],"utilized":[24,193],"in":[25,50,63,195],"clinical":[26,29],"practice":[27],"drug":[30],"research":[31],"to":[32,72,85,148,206],"detect":[33],"measure":[35],"malignancies.":[38],"The":[39,202],"assessment":[40],"of":[41,76,94,108,134,187,212],"tumor":[42,48,112],"burden":[43],"manual":[45],"or":[46],"computer-assisted":[47],"segmentation":[49,113,156],"FDG-PET":[51],"images":[52],"widespread.":[54],"Deep":[55],"learning":[56,80],"algorithms":[57],"also":[59,159],"produced":[60],"effective":[61],"solutions":[62],"this":[64,87,124],"area.":[65],"However,":[66],"there":[67],"may":[68],"be":[69,236],"a":[70,77,105,131,198],"need":[71],"improve":[73,127,207,230],"the":[74,83,91,128,145,174,210,215,220,226],"performance":[75,208],"pre-trained":[78,199],"deep":[79],"network":[81,129],"without":[82],"opportunity":[84],"modify":[86],"network.":[88],"We":[89,103,138,158],"investigate":[90],"potential":[92],"benefits":[93],"test-time":[95,190],"augmentation":[96,154,169,191],"for":[97,189],"segmenting":[98],"from":[100],"PET-CT":[101],"pairings.":[102],"applied":[104],"new":[106],"framework":[107],"multilevel":[109],"multimodal":[111],"techniques":[114],"that":[115,163],"can":[116,229],"simultaneously":[117],"consider":[118],"PET":[119],"CT":[121],"data.":[122],"In":[123],"study,":[125],"we":[126,182],"learnable":[132],"composition":[133],"test":[135,152,167],"time":[136,153,168,211],"augmentations.":[137],"trained":[139,176],"U-Net":[140,177],"Swin":[142,179],"U-Netr":[143,180],"on":[144,225],"training":[146],"database":[147],"determine":[149],"how":[150],"different":[151],"improved":[155],"performance.":[157],"developed":[160],"an":[161,165,184],"algorithm":[162],"finds":[164],"optimal":[166,185],"contribution":[170],"coefficient":[171],"set.":[172],"Using":[173],"newly":[175],"results,":[181],"defined":[183],"set":[186],"coefficients":[188],"them":[194],"combination":[196],"with":[197,222],"fixed":[200],"nnU-Net.":[201],"ultimate":[203],"idea":[204],"at":[209,238],"testing":[213],"when":[214],"model":[216],"fixed.":[218],"Averaging":[219],"predictions":[221],"varying":[223],"ratios":[224],"augmented":[227],"data":[228],"prediction":[231],"accuracy.":[232],"Our":[233],"code":[234],"will":[235],"available":[237],"\\url{https://github.com/sepidehamiri/pet\\_seg\\_unet}":[239]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2022-10-19T00:00:00"}