{"id":"https://openalex.org/W7160641086","doi":"https://doi.org/10.48550/arxiv.2605.05522","title":"Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images","display_name":"Tumor-aware augmentation with task-guided attention analysis improves rectal cancer segmentation from magnetic resonance images","publication_year":2026,"publication_date":"2026-05-06","ids":{"openalex":"https://openalex.org/W7160641086","doi":"https://doi.org/10.48550/arxiv.2605.05522"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.05522","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05522","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,"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.2605.05522","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080330227","display_name":"Aneesh Rangnekar","orcid":"https://orcid.org/0000-0002-0079-9495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rangnekar, Aneesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113770959","display_name":"Jo\u00e3o Miranda","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miranda, Joao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135668955","display_name":"Natally Horvat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Horvat, Natally","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073484838","display_name":"Stephanie Chahwan","orcid":"https://orcid.org/0009-0001-8932-2027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chahwan, Stephanie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135716216","display_name":"Samir Alrayess","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alrayess, Samir","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035396934","display_name":"Aditya Apte","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Apte, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061457064","display_name":"Aditi Iyer","orcid":"https://orcid.org/0000-0002-2369-8953"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iyer, Aditi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135711236","display_name":"Eve LoCastro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"LoCastro, Eve","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022514767","display_name":"R. Ravella","orcid":"https://orcid.org/0000-0003-0376-5554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ravella, Revathi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068823540","display_name":"Marc J. Gollub","orcid":"https://orcid.org/0000-0002-6008-0730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gollub, Marc J","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034605986","display_name":"Iva Petkovska","orcid":"https://orcid.org/0000-0002-4373-6494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Petkovska, Iva","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122756637","display_name":"Jesse Joshua Smith","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smith, Jesse Joshua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133848758","display_name":"Paul Romesser","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romesser, Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135641456","display_name":"Julio Garcia-Aguilar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garcia-Aguilar, Julio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135667190","display_name":"Harini Veeraraghavan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Veeraraghavan, Harini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135700920","display_name":"Joseph Deasy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deasy, Joseph O.","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/T11885","display_name":"MRI in cancer diagnosis","score":0.29319998621940613,"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/T11885","display_name":"MRI in cancer diagnosis","score":0.29319998621940613,"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":0.13410000503063202,"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/T10358","display_name":"Advanced Radiotherapy Techniques","score":0.12470000237226486,"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/robustness","display_name":"Robustness (evolution)","score":0.6901000142097473},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4846000075340271},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4740000069141388},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47049999237060547},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4156000018119812},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41119998693466187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3898000121116638},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3808000087738037}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7077999711036682},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6901000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6013000011444092},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4740000069141388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41119998693466187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C143409427","wikidata":"https://www.wikidata.org/wiki/Q161238","display_name":"Magnetic resonance imaging","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C51432778","wikidata":"https://www.wikidata.org/wiki/Q1259145","display_name":"Independent component analysis","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2993807640","wikidata":"https://www.wikidata.org/wiki/Q103709453","display_name":"Attention network","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C2780531524","wikidata":"https://www.wikidata.org/wiki/Q551540","display_name":"Ghosting","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.05522","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05522","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,"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.2605.05522","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.05522","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,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Although":[0],"self-supervised":[1],"pretraining":[2,19,90],"is":[3,210],"expected":[4],"to":[5,52,117,136,152,163,214,220],"learn":[6],"broadly":[7],"transferable":[8],"representations,":[9],"its":[10],"effectiveness":[11],"across":[12,222],"imaging":[13,223],"modalities":[14,224],"substantially":[15],"different":[16],"from":[17],"the":[18,186,194,212],"domain,":[20],"and":[21,57,75,92,112,158,182,189,225],"on":[22,31,171],"complex":[23],"tumor-segmentation":[24],"tasks,":[25],"remains":[26],"understudied.":[27],"Evaluating":[28],"CT-pretrained":[29,69],"transformers":[30,218],"MRI":[32,122,174],"rectal":[33,173],"cancer":[34],"segmentation,":[35],"we":[36,144],"identified":[37],"two":[38,67,146],"interacting":[39],"failure":[40],"modes":[41],"in":[42,89],"CT-to-MRI":[43,206],"transfer:":[44],"(a)":[45],"inefficient":[46],"token":[47,165],"usage":[48],"caused":[49],"by":[50],"zero-padding":[51],"match":[53],"pretrained":[54,217],"input":[55],"dimensions,":[56],"(b)":[58],"ineffective":[59],"feature":[60,119,130],"adaptation.":[61,123],"We":[62],"investigated":[63],"these":[64,86,142,169],"vulnerabilities":[65],"using":[66],"primary":[68,187],"hierarchical":[70],"shifted-window":[71],"transformer":[72],"backbones,":[73,192],"SMIT":[74,188],"Swin":[76,190],"UNETR,":[77],"together":[78],"with":[79,126,168,193],"VoCo":[80,196],"as":[81],"a":[82,148],"large-scale-pretrained":[83],"supporting":[84,195],"benchmark;":[85],"models":[87],"differ":[88],"objectives":[91],"datasets.":[93],"Mechanistic":[94],"analysis":[95],"leveraged":[96],"an":[97,102,159],"attention":[98,106],"dilution":[99],"index":[100],"(ADI),":[101],"entropy-based":[103],"metric":[104],"quantifying":[105],"diverted":[107],"toward":[108],"uninformative":[109],"padding":[110],"tokens,":[111],"centered":[113],"kernel":[114],"alignment":[115],"(CKA)":[116],"measure":[118],"reuse":[120,131],"during":[121],"ADI":[124],"increased":[125],"zero-padding,":[127],"while":[128],"high":[129],"did":[132],"not":[133],"necessarily":[134],"translate":[135],"improved":[137,203],"downstream":[138],"accuracy.":[139],"To":[140],"mitigate":[141],"issues,":[143],"introduced":[145],"interventions:":[147],"tumor-aware":[149],"augmentation":[150],"strategy":[151,162],"expand":[153],"tumor":[154],"appearance":[155],"heterogeneity":[156],"coverage,":[157],"anisotropic":[160],"cropping":[161],"restore":[164],"efficiency.":[166],"Fine-tuning":[167],"strategies":[170,230],"identical":[172],"datasets":[175],"yielded":[176],"detection":[177],"rates":[178],"of":[179],"91.1%":[180],"(225/247)":[181],"88.7%":[183],"(219/247)":[184],"for":[185],"UNETR":[191],"benchmark":[197],"reaching":[198],"90.3%":[199],"(223/247),":[200],"demonstrating":[201],"significantly":[202],"robustness":[204],"under":[205],"transfer.":[207],"This":[208],"study":[209],"among":[211],"first":[213],"examine":[215],"when":[216],"fail":[219],"transfer":[221,235],"demonstrates":[226],"how":[227],"targeted":[228],"mitigation":[229],"can":[231],"systematically":[232],"overcome":[233],"cross-modality":[234],"limitations.":[236]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-09T00:00:00"}