{"id":"https://openalex.org/W7133190258","doi":"https://doi.org/10.48550/arxiv.2602.23447","title":"SALIENT: Frequency-Aware Paired Diffusion for Controllable Long-Tail CT Detection","display_name":"SALIENT: Frequency-Aware Paired Diffusion for Controllable Long-Tail CT Detection","publication_year":2026,"publication_date":"2026-02-26","ids":{"openalex":"https://openalex.org/W7133190258","doi":"https://doi.org/10.48550/arxiv.2602.23447"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.23447","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.23447","pdf_url":"https://arxiv.org/pdf/2602.23447","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/2602.23447","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127811651","display_name":"Yifan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Yifan","raw_affiliation_strings":["Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]},{"raw_affiliation_string":"Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060693930","display_name":"Mehrdad Salimitari","orcid":"https://orcid.org/0000-0001-9243-9480","observed_orcids":["https://orcid.org/0000-0001-9243-9480"]},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salimitari, Mehrdad","raw_affiliation_strings":["Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]},{"raw_affiliation_string":"Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127829521","display_name":"Taiyu Zhang","orcid":"https://orcid.org/0009-0006-6346-9297","observed_orcids":["https://orcid.org/0009-0006-6346-9297"]},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Taiyu","raw_affiliation_strings":["Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]},{"raw_affiliation_string":"Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127824050","display_name":"Guang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Guang","raw_affiliation_strings":["Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049933355","display_name":"David Dreizin","orcid":"https://orcid.org/0000-0002-0176-0912","observed_orcids":["https://orcid.org/0000-0002-0176-0912"]},"institutions":[{"id":"https://openalex.org/I126744593","display_name":"University of Maryland, Baltimore","ror":"https://ror.org/04rq5mt64","country_code":"US","type":"education","lineage":["https://openalex.org/I126744593"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dreizin, David","raw_affiliation_strings":["Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]},{"raw_affiliation_string":"Trauma Radiology AI Laboratory (TRAIL) , Department of Radiology and Nuclear Medicine , University of Maryland School of Medicine","institution_ids":["https://openalex.org/I126744593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126744593"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.43630000948905945,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.43630000948905945,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2150000035762787,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.05990000069141388,"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/whole-body-ct","display_name":"whole-body CT","score":0.9419999718666077},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8289999961853027},{"id":"https://openalex.org/keywords/synthetic-data-augmentation","display_name":"synthetic data augmentation","score":0.7049999833106995},{"id":"https://openalex.org/keywords/diffusion-models","display_name":"diffusion models","score":0.7319999933242798}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.6801999807357788},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5680000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5467000007629395},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5015000104904175},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.4528000056743622},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4323999881744385},{"id":"https://openalex.org/C125245961","wikidata":"https://www.wikidata.org/wiki/Q221656","display_name":"Brightness","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3962000012397766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3716000020503998},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3682999908924103},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C186060115","wikidata":"https://www.wikidata.org/wiki/Q30336093","display_name":"Biological system","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C55128770","wikidata":"https://www.wikidata.org/wiki/Q5275440","display_name":"Diffusion map","level":4,"score":0.29249998927116394},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2992283565","wikidata":"https://www.wikidata.org/wiki/Q899360","display_name":"Diffusion imaging","level":4,"score":0.2728999853134155},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2653999924659729},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.23447","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.23447","pdf_url":"https://arxiv.org/pdf/2602.23447","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.2602.23447","doi":"https://doi.org/10.48550/arxiv.2602.23447","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.23447","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.23447","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.23447","pdf_url":"https://arxiv.org/pdf/2602.23447","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":[{"display_name":"Good health and well-being","score":0.504800021648407,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7133190258.pdf","grobid_xml":"https://content.openalex.org/works/W7133190258.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4385767742"],"related_works":["https://openalex.org/W7223050754","https://openalex.org/W4414350005","https://openalex.org/W7214153011","https://openalex.org/W4401476414","https://openalex.org/W7202397535","https://openalex.org/W7125919661","https://openalex.org/W4414377317","https://openalex.org/W4353004474","https://openalex.org/W4393118044","https://openalex.org/W7211907542"],"abstract_inverted_index":{"Detection":[0],"of":[1,72],"rare":[2],"lesions":[3],"in":[4,74,201],"whole-body":[5],"CT":[6,66,203],"is":[7,34],"fundamentally":[8],"limited":[9],"by":[10,136],"extreme":[11],"class":[12],"imbalance":[13],"and":[14,37,45,98,107,118,142,166],"low":[15,164],"target-to-volume":[16,167],"ratios,":[17],"producing":[18],"precision":[19,199],"collapse":[20],"despite":[21],"high":[22],"AUROC.":[23],"Synthetic":[24],"augmentation":[25,67,185],"with":[26],"diffusion":[27,33,57,80,194],"models":[28],"offers":[29],"promise,":[30],"yet":[31],"pixel-space":[32],"computationally":[35,197],"expensive,":[36],"existing":[38],"mask-conditioned":[39,55],"approaches":[40],"lack":[41],"controllable":[42,65],"attribute-level":[43],"regulation":[44],"paired":[46,61,123],"supervision":[47],"for":[48,64,126],"accountable":[49],"training.":[50],"We":[51],"introduce":[52],"SALIENT,":[53],"a":[54,119,149,183],"wavelet-domain":[56],"framework":[58],"that":[59,192],"synthesizes":[60],"lesion-masking":[62],"volumes":[63],"under":[68,187],"long-tail":[69,156,202],"regimes.":[70],"Instead":[71],"denoising":[73],"pixel":[75],"space,":[76],"SALIENT":[77,130,190],"performs":[78],"structured":[79],"over":[81],"discrete":[82],"wavelet":[83],"coefficients,":[84],"explicitly":[85],"separating":[86],"low-frequency":[87],"brightness":[88],"from":[89,173],"high-frequency":[90],"structural":[91],"detail.":[92],"Learnable":[93],"frequency-aware":[94,193],"objectives":[95],"disentangle":[96],"target":[97],"background":[99],"attributes":[100],"(structure,":[101],"contrast,":[102],"edge":[103],"fidelity),":[104],"enabling":[105],"interpretable":[106],"stable":[108],"optimization.":[109],"A":[110],"3D":[111],"VAE":[112],"generates":[113],"diverse":[114],"volumetric":[115],"lesion":[116],"masks,":[117],"semi-supervised":[120],"teacher":[121],"produces":[122],"slice-level":[124],"pseudo-labels":[125],"downstream":[127,151],"mask-guided":[128],"detection.":[129,204],"improves":[131,155],"generative":[132],"realism,":[133],"as":[134,177],"reflected":[135],"higher":[137],"MS-SSIM":[138],"(0.63":[139],"to":[140,146,175],"0.83)":[141],"lower":[143],"FID":[144],"(118.4":[145],"46.5).":[147],"In":[148],"separate":[150],"evaluation,":[152],"SALIENT-augmented":[153],"training":[154],"detection":[157],"performance,":[158],"yielding":[159],"disproportionate":[160],"AUPRC":[161],"gains":[162],"across":[163],"prevalences":[165],"ratios.":[168],"Optimal":[169],"synthetic":[170],"ratios":[171],"shift":[172],"2x":[174],"4x":[176],"labeled":[178],"seed":[179],"size":[180],"decreases,":[181],"indicating":[182],"seed-dependent":[184],"regime":[186],"low-label":[188],"conditions.":[189],"demonstrates":[191],"enables":[195],"controllable,":[196],"efficient":[198],"rescue":[200]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-03-03T00:00:00"}