{"id":"https://openalex.org/W7160232905","doi":"https://doi.org/10.48550/arxiv.2605.01266","title":"Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation","display_name":"Exploring Prompt Alignment with Clinical Factors in Zero-Shot Segmentation VLMs for NSCLC Tumor Segmentation","publication_year":2026,"publication_date":"2026-05-02","ids":{"openalex":"https://openalex.org/W7160232905","doi":"https://doi.org/10.48550/arxiv.2605.01266"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.01266","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135331927","display_name":"Suraj Pai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pai, Suraj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120050330","display_name":"Thibault Heintz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heintz, Thibault","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093330644","display_name":"Cosmin Ciausu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ciausu, Cosmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041610524","display_name":"Marion Tonneau","orcid":"https://orcid.org/0000-0003-4776-115X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tonneau, Marion","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135305456","display_name":"Hugo JWL Aerts","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aerts, Hugo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123203336","display_name":"Raymond Mak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mak, Raymond","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T10862","display_name":"AI in cancer detection","score":0.32850000262260437,"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"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.32850000262260437,"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"}},{"id":"https://openalex.org/T10358","display_name":"Advanced Radiotherapy Techniques","score":0.15360000729560852,"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"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.14880000054836273,"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/segmentation","display_name":"Segmentation","score":0.6930000185966492},{"id":"https://openalex.org/keywords/contouring","display_name":"Contouring","score":0.5250999927520752},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.5206999778747559},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.447299987077713},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.39430001378059387},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.35910001397132874},{"id":"https://openalex.org/keywords/s\u00f8rensen\u2013dice-coefficient","display_name":"S\u00f8rensen\u2013Dice coefficient","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6930000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6061999797821045},{"id":"https://openalex.org/C2779104521","wikidata":"https://www.wikidata.org/wiki/Q23058469","display_name":"Contouring","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.5206999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4632999897003174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.447299987077713},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.39430001378059387},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.39079999923706055},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.35910001397132874},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.35269999504089355},{"id":"https://openalex.org/C40993552","wikidata":"https://www.wikidata.org/wiki/Q514654","display_name":"Gold standard (test)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C2776256026","wikidata":"https://www.wikidata.org/wiki/Q47912","display_name":"Lung cancer","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2986522900","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relationship","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.2888000011444092},{"id":"https://openalex.org/C3018028425","wikidata":"https://www.wikidata.org/wiki/Q15917291","display_name":"Tumor heterogeneity","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C2989005","wikidata":"https://www.wikidata.org/wiki/Q214963","display_name":"Nuclear medicine","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2524000108242035},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"vision-language":[1],"models":[2],"(VLMs)":[3],"offer":[4],"a":[5,45,173],"promptable":[6],"alternative":[7],"to":[8,119,158,162,223],"task-specific":[9],"training":[10],"for":[11,123],"gross":[12],"tumor":[13,49],"volume":[14],"(GTV)":[15],"delineation":[16],"in":[17,42],"non-small-cell":[18],"lung":[19],"cancer":[20],"(NSCLC),":[21],"but":[22,217],"the":[23,80,99,154,220],"prompt":[24,70,114,134,221],"dimensions":[25,222],"that":[26,95,153,207],"govern":[27],"their":[28],"spatial":[29,104],"behavior":[30],"remain":[31],"poorly":[32],"understood.":[33],"We":[34],"study":[35],"this":[36,166],"question":[37],"by":[38,215,219],"probing":[39],"alignment":[40],"directions":[41],"VoxTell":[43],"on":[44],"held-out":[46],"internal":[47],"NSCLC":[48],"dataset":[50],"through":[51],"sub-prompt":[52],"decomposition":[53],"into":[54],"diagnosis,":[55],"demographic,":[56],"staging,":[57],"anatomical,":[58],"generic,":[59],"and":[60,68,76,89,132,146,187],"irrelevant":[61,126],"controls;":[62],"attribute-wise":[63],"perturbation":[64],"robustness;":[65],"specificity":[66,115],"ladders;":[67],"cross-case":[69,133],"swaps,":[71],"while":[72,196],"benchmarking":[73],"against":[74],"fine-tuned":[75],"zero-shot":[77,201],"baselines":[78],"using":[79],"Dice":[81],"Similarity":[82],"Coefficient":[83],"(DSC)":[84],"with":[85],"Wilcoxon":[86],"signed-rank":[87],"tests":[88],"Benjamini-Hochberg":[90],"correction.":[91],"Alignment":[92],"analyses":[93],"revealed":[94],"anatomical":[96],"location":[97,109],"is":[98],"dominant":[100],"driver":[101],"of":[102,108,176],"VoxTell's":[103],"attention:":[105],"63.4":[106],"percent":[107],"perturbations":[110],"caused":[111],"catastrophic":[112],"drops,":[113],"improved":[116],"from":[117,180],"generic":[118],"full":[120],"descriptions":[121],"except":[122],"diagnosis-only":[124],"prompts,":[125],"prompts":[127],"correctly":[128],"yielded":[129],"zero":[130],"segmentation,":[131],"swaps":[135],"confirmed":[136],"patient-specific":[137],"conditioning":[138],"(matched":[139],"DSC":[140,175],"0.906":[141],"vs.":[142],"mismatched":[143],"0.406).":[144],"Histology":[145],"stage":[147],"substitutions":[148],"had":[149],"minimal":[150],"effect,":[151],"indicating":[152],"model":[155],"prioritizes":[156],"\"where":[157],"look\"":[159],"over":[160],"\"what":[161],"look":[163],"for.\"":[164],"In":[165],"context,":[167],"VoxTell,":[168],"operating":[169],"fully":[170],"zero-shot,":[171],"achieved":[172],"mean":[174],"0.613,":[177],"statistically":[178],"indistinguishable":[179],"nnUNet":[181],"(0.690,":[182],"adjusted":[183,192],"p":[184,193],"=":[185,194],"0.156)":[186],"Ahmed":[188],"et":[189],"al.":[190],"(0.675,":[191],"0.679),":[195],"significantly":[197],"outperforming":[198],"all":[199],"other":[200],"models.":[202],"Together,":[203],"these":[204],"findings":[205],"argue":[206],"segmentation":[208],"VLMs":[209],"should":[210],"be":[211],"evaluated":[212],"not":[213],"only":[214],"Dice,":[216],"also":[218],"which":[224],"they":[225],"align.":[226]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}