{"id":"https://openalex.org/W7141594626","doi":"https://doi.org/10.48550/arxiv.2603.24992","title":"C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D LGE-MRI","display_name":"C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D LGE-MRI","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141594626","doi":"https://doi.org/10.48550/arxiv.2603.24992"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24992","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.2603.24992","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120630851","display_name":"Yusri Al-Sanaani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Al-Sanaani, Yusri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078237944","display_name":"Rebecca E. Thornhill","orcid":"https://orcid.org/0000-0001-5308-5106"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thornhill, Rebecca","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012603099","display_name":"Sreeraman Rajan","orcid":"https://orcid.org/0000-0003-0153-6723"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajan, Sreeraman","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/T10821","display_name":"Cardiovascular Function and Risk Factors","score":0.22300000488758087,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"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/T10821","display_name":"Cardiovascular Function and Risk Factors","score":0.22300000488758087,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"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/T10372","display_name":"Cardiac Imaging and Diagnostics","score":0.18649999797344208,"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/T10065","display_name":"Atrial Fibrillation Management and Outcomes","score":0.18060000240802765,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"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/dice","display_name":"Dice","score":0.7919999957084656},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7407000064849854},{"id":"https://openalex.org/keywords/hausdorff-distance","display_name":"Hausdorff distance","score":0.5590999722480774},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.47029998898506165},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.367900013923645},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3598000109195709},{"id":"https://openalex.org/keywords/level-set","display_name":"Level set (data structures)","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.7919999957084656},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7407000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6786999702453613},{"id":"https://openalex.org/C141898687","wikidata":"https://www.wikidata.org/wiki/Q1501997","display_name":"Hausdorff distance","level":2,"score":0.5590999722480774},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5343999862670898},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47360000014305115},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C153008295","wikidata":"https://www.wikidata.org/wiki/Q6535093","display_name":"Level set (data structures)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C143409427","wikidata":"https://www.wikidata.org/wiki/Q161238","display_name":"Magnetic resonance imaging","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C185877587","wikidata":"https://www.wikidata.org/wiki/Q1757407","display_name":"Medial axis","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C523889960","wikidata":"https://www.wikidata.org/wiki/Q160695","display_name":"Torso","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24992","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.2603.24992","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24992","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":{"Accurate":[0],"segmentation":[1,98,215],"of":[2,187],"the":[3,29,75,79,93,113,179],"left":[4],"atrial":[5,84],"(LA)":[6],"wall":[7,17,97,128,214],"in":[8,216],"3D":[9,63,217],"late":[10],"gadolinium-enhanced":[11],"MRI":[12],"(LGE-MRI)":[13],"is":[14],"essential":[15],"for":[16,211],"thickness":[18],"mapping":[19],"and":[20,35,69,91,157],"fibrosis":[21],"quantification,":[22],"yet":[23],"it":[24],"remains":[25],"challenging":[26],"due":[27],"to":[28,57,77,95,104,134,144,154,167],"wall's":[30],"thin":[31,212],"geometry,":[32],"complex":[33],"anatomy,":[34],"low":[36],"contrast.":[37],"We":[38],"propose":[39],"C2W-Tune,":[40],"a":[41,48,62,66,100,185],"two-stage":[42],"cavity-to-wall":[43],"transfer":[44,205],"framework":[45],"that":[46,201],"leverages":[47],"high-accuracy":[49],"LA":[50,80,96,115,213],"cavity":[51,106],"model":[52],"as":[53],"an":[54,121],"anatomical":[55],"prior":[56],"improve":[58],"thin-wall":[59],"delineation.":[60],"Using":[61],"U-Net":[64],"with":[65,191,206],"ResNeXt":[67],"encoder":[68],"instance":[70],"normalization,":[71],"Stage":[72,86],"1":[73,139],"pre-trains":[74],"network":[76,94],"segment":[78],"cavity,":[81],"learning":[82],"robust":[83],"representations.":[85],"2":[87],"transfers":[88],"these":[89],"weights":[90],"adapts":[92],"using":[99,173],"progressive":[101],"layer-unfreezing":[102],"schedule":[103],"preserve":[105],"features":[107],"while":[108],"enabling":[109],"wall-specific":[110],"refinement.":[111],"On":[112],"2018":[114],"Segmentation":[116],"Challenge":[117],"dataset,":[118],"C2W-Tune":[119,183],"outperformed":[120],"architecture-matched":[122],"baseline":[123],"trained":[124],"from":[125,132,142,151,164,178],"scratch.":[126],"The":[127],"Dice":[129,137,186],"score":[130],"increased":[131,141],"0.623":[133],"0.814,":[135],"surface":[136,160],"at":[138],"mm":[140,153,166],"0.553":[143],"0.731,":[145],"95th-percentile":[146],"Hausdorff":[147],"distance":[148,161],"(HD95)":[149],"decreased":[150,163],"2.95":[152],"2.55":[155],"mm,":[156],"average":[158],"symmetric":[159],"(ASSD)":[162],"0.71":[165],"0.63":[168],"mm.":[169],"Under":[170],"reduced":[171],"supervision":[172],"70":[174],"training":[175,181],"volumes":[176],"sampled":[177],"same":[180],"set,":[182],"achieved":[184],"0.78,":[188],"remaining":[189],"competitive":[190],"recent":[192],"multi-class":[193],"bi-atrial":[194],"benchmarks,":[195],"typically":[196],"0.6-0.7.":[197],"These":[198],"results":[199],"show":[200],"anatomically":[202],"grounded":[203],"task":[204],"controlled":[207],"fine-tuning":[208],"improves":[209],"accuracy":[210],"LGE-MRI.":[218]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-28T00:00:00"}