{"id":"https://openalex.org/W7161752805","doi":"https://doi.org/10.1109/isbi61048.2026.11515689","title":"Learnable Hierarchical Visual Contexts for Tumor Segmentation in Computed Tomography Images","display_name":"Learnable Hierarchical Visual Contexts for Tumor Segmentation in Computed Tomography Images","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7161752805","doi":"https://doi.org/10.1109/isbi61048.2026.11515689"},"language":null,"primary_location":{"id":"doi:10.1109/isbi61048.2026.11515689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136606022","display_name":"Jue Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I1334819555","display_name":"Memorial Sloan Kettering Cancer Center","ror":"https://ror.org/02yrq0923","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1334819555"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jue Jiang","raw_affiliation_strings":["Memorial Sloan Kettering Cancer Center,Department of Medical Physics,New York,NY,USA,10065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Memorial Sloan Kettering Cancer Center,Department of Medical Physics,New York,NY,USA,10065","institution_ids":["https://openalex.org/I1334819555"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136522598","display_name":"Harini Veeraraghavan","orcid":null},"institutions":[{"id":"https://openalex.org/I1334819555","display_name":"Memorial Sloan Kettering Cancer Center","ror":"https://ror.org/02yrq0923","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1334819555"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harini Veeraraghavan","raw_affiliation_strings":["Memorial Sloan Kettering Cancer Center,Department of Medical Physics,New York,NY,USA,10065"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Memorial Sloan Kettering Cancer Center,Department of Medical Physics,New York,NY,USA,10065","institution_ids":["https://openalex.org/I1334819555"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5136606022"],"corresponding_institution_ids":["https://openalex.org/I1334819555"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.92868285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.4867999851703644,"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":0.4867999851703644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.10989999771118164,"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/T10862","display_name":"AI in cancer detection","score":0.0828000009059906,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computed-tomography","display_name":"Computed tomography","score":0.5989999771118164},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5454000234603882},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4027999937534332},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.350600004196167},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.33059999346733093},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.31940001249313354}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.657800018787384},{"id":"https://openalex.org/C544519230","wikidata":"https://www.wikidata.org/wiki/Q32566","display_name":"Computed tomography","level":2,"score":0.5989999771118164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5842999815940857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5551999807357788},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4027999937534332},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.350600004196167},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.2833000123500824},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2734000086784363}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isbi61048.2026.11515689","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8956205349","display_name":null,"funder_award_id":"R01CA258821","funder_id":"https://openalex.org/F4320337351","funder_display_name":"National Cancer Institute"}],"funders":[{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W3014974815","https://openalex.org/W3172681723","https://openalex.org/W4281400392","https://openalex.org/W4312349930","https://openalex.org/W4312428231","https://openalex.org/W4382998948","https://openalex.org/W4390873519","https://openalex.org/W4390889814","https://openalex.org/W4402727572","https://openalex.org/W4410838785","https://openalex.org/W4415538858","https://openalex.org/W4415799001"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"advances":[1],"in":[2,25],"deep":[3],"learning":[4,81],"(DL),":[5],"automated":[6],"tumor":[7,26,144],"segmentation":[8,93],"on":[9],"computed":[10],"tomography":[11],"(CT)":[12],"scans":[13],"remains":[14],"challenging":[15],"for":[16,44,91],"radiotherapy":[17],"applications":[18],"due":[19,21],"to":[20,22,63,76,115],"large":[23],"variability":[24],"shapes,":[27],"appearance,":[28],"and":[29,87,129,145,153],"diffuse":[30],"boundaries.":[31],"We":[32],"present":[33],"LeVal-learnable":[34],"visual":[35],"query":[36,57],"contexts":[37,54,60],"that":[38],"refines":[39],"attention":[40],"towards":[41],"tumor-relevant":[42],"regions":[43],"improved":[45],"segmentation.":[46,117],"LeVal":[47,118],"combines":[48],"task-agnostic":[49],"learnable":[50],"tokens":[51],"called":[52],"semantic":[53,107],"with":[55,106],"task-specific":[56],"tokens.":[58],"Semantic":[59],"cross":[61],"attend":[62],"multi-scale":[64],"features":[65],"of":[66],"a":[67],"3D":[68],"Swin":[69],"transformer":[70],"encoder,":[71],"which":[72,109],"are":[73,102],"jointly":[74],"subject":[75],"2-stage":[77],"pretraining:":[78],"(a)":[79],"self-supervised":[80],"(SSL)":[82],"using":[83],"14,000":[84],"unlabeled":[85],"CTs":[86],"(b),":[88],"supervised":[89],"pretraining":[90],"multi-organ":[92],"use":[94],"pseudo-contours":[95],"generated":[96],"by":[97],"bespoke":[98],"methods.":[99,136],"Task":[100],"queries":[101],"refined":[103],"through":[104,160],"crossattention":[105],"contexts,":[108],"then":[110],"modulate":[111],"the":[112],"decoder":[113],"output":[114],"generate":[116],"was":[119],"evaluated":[120],"across":[121],"four":[122],"public":[123],"datasets":[124],"involving":[125],"pancreas,":[126],"colon,":[127],"adrenal,":[128],"head-and-neck":[130],"cancers.":[131],"It":[132],"consistently":[133],"outperformed":[134],"existing":[135],"Leval":[137],"also":[138],"demonstrated":[139],"stronger":[140],"embedding":[141],"separation":[142],"between":[143],"surrounding":[146],"healthy":[147],"tissues,":[148],"indicating":[149],"better":[150],"discriminability.":[151],"Code":[152],"model":[154],"checkpoints":[155],"will":[156],"be":[157],"made":[158],"available":[159],"GitHub":[161],"upon":[162],"manuscript":[163],"acceptance.":[164]},"counts_by_year":[],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2026-05-21T00:00:00"}