{"id":"https://openalex.org/W7214995149","doi":"https://doi.org/10.48550/arxiv.2609.37350","title":"PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning","display_name":"PCaPaint: Prostate Cancer Inpainting by Mitigating Shortcut Learning","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214995149","doi":"https://doi.org/10.48550/arxiv.2609.37350"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37350","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37350","pdf_url":"https://arxiv.org/pdf/2609.37350","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/2609.37350","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040407089","display_name":"Levente Lippenszky","orcid":"https://orcid.org/0009-0000-7835-2071","observed_orcids":["https://orcid.org/0009-0000-7835-2071"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lippenszky, Levente","raw_affiliation_strings":["GE HealthCare"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE HealthCare","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029334093","display_name":"Hongxu Yang","orcid":"https://orcid.org/0000-0003-2447-094X","observed_orcids":["https://orcid.org/0000-0003-2447-094X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Hongxu","raw_affiliation_strings":["GE HealthCare"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE HealthCare","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153603567","display_name":"Marcell D\u00f6m\u00f6t\u00f6r","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D\u00f6m\u00f6t\u00f6r, Marcell","raw_affiliation_strings":["GE HealthCare"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE HealthCare","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106870970","display_name":"Kriszti\u00e1n Ko\u00f3s","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koos, Krisztian","raw_affiliation_strings":["GE HealthCare"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE HealthCare","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019706167","display_name":"L\u00e1szl\u00f3 Rusk\u00f3","orcid":"https://orcid.org/0009-0003-5073-8978","observed_orcids":["https://orcid.org/0009-0003-5073-8978"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rusk\u00f3, L\u00e1szl\u00f3","raw_affiliation_strings":["GE HealthCare"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GE HealthCare","institution_ids":[]}]}],"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":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":0.5264000296592712,"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":0.5264000296592712,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.25119999051094055,"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":0.0966000035405159,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/prostate-cancer","display_name":"prostate cancer","score":0.9440000057220459},{"id":"https://openalex.org/keywords/shortcut-learning","display_name":"shortcut learning","score":0.9319999814033508},{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.9850000143051147},{"id":"https://openalex.org/keywords/synthetic-mri","display_name":"synthetic MRI","score":0.5559999942779541},{"id":"https://openalex.org/keywords/t2-weighted-mri","display_name":"T2-weighted MRI","score":0.8149999976158142},{"id":"https://openalex.org/keywords/diffusion-weighted-imaging","display_name":"diffusion-weighted imaging","score":0.8960000276565552},{"id":"https://openalex.org/keywords/apparent-diffusion-coefficient","display_name":"apparent diffusion coefficient","score":0.8069999814033508},{"id":"https://openalex.org/keywords/patient-level-classification","display_name":"patient-level classification","score":0.8040000200271606},{"id":"https://openalex.org/keywords/lesion-detection","display_name":"lesion detection","score":0.7630000114440918},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.5860000252723694}],"concepts":[{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.9341999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6679999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6434999704360962},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.48730000853538513},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C2780192828","wikidata":"https://www.wikidata.org/wiki/Q181257","display_name":"Prostate cancer","level":3,"score":0.4675000011920929},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37709999084472656},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35370001196861267},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2781156865","wikidata":"https://www.wikidata.org/wiki/Q827023","display_name":"Lesion","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2849999964237213},{"id":"https://openalex.org/C2776235491","wikidata":"https://www.wikidata.org/wiki/Q9625","display_name":"Prostate","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26829999685287476}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37350","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37350","pdf_url":"https://arxiv.org/pdf/2609.37350","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.2609.37350","doi":"https://doi.org/10.48550/arxiv.2609.37350","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37350","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:2609.37350","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37350","pdf_url":"https://arxiv.org/pdf/2609.37350","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":[{"score":0.8560000061988831,"display_name":"Good health and well-being","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/W7214995149.pdf","grobid_xml":"https://content.openalex.org/works/W7214995149.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W3092442149","https://openalex.org/W4308610041","https://openalex.org/W4393118044","https://openalex.org/W4393565022","https://openalex.org/W4416101707","https://openalex.org/W7148259318"],"related_works":["https://openalex.org/W2978997284","https://openalex.org/W4414478495","https://openalex.org/W7129374858","https://openalex.org/W4403204330","https://openalex.org/W4416101707","https://openalex.org/W2741685120","https://openalex.org/W4416184368","https://openalex.org/W4406540446","https://openalex.org/W7117972608","https://openalex.org/W3148171260"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,13],"AI":[3],"systems":[4],"for":[5,26,122],"tumor-specific":[6],"applications":[7],"is":[8,104],"limited":[9],"by":[10,57],"the":[11,53,59,101,126,129,162],"scarcity":[12],"labeled":[14],"data.":[15,34],"Synthetic":[16],"tumor":[17,89,187],"inpainting":[18,71,188],"offers":[19],"a":[20,68,93,118,135,183],"promising":[21],"approach":[22],"but":[23],"faces":[24],"challenges":[25],"prostate":[27,69,170],"cancer":[28,70],"MRI":[29],"which":[30,100,140],"contains":[31],"high-resolution":[32],"multi-sequence":[33,136],"Although":[35],"methods":[36],"leveraging":[37],"latent":[38,137],"diffusion":[39],"models":[40],"(LDMs)":[41],"enable":[42],"large-volume":[43],"synthesis,":[44],"they":[45],"are":[46,146],"prone":[47],"to":[48,152],"shortcut":[49,84],"learning,":[50],"simply":[51],"reproducing":[52],"condition":[54,102],"image":[55,103,197],"created":[56],"masking":[58],"lesion":[60,130,171],"region.":[61,131],"In":[62,114],"this":[63,79],"work,":[64],"we":[65,91,110,116,133],"introduce":[66,134],"PCaPaint,":[67],"method":[72,180,189],"based":[73],"on":[74],"LDMs":[75],"that":[76,86,124,161],"explicitly":[77],"addresses":[78],"failure":[80],"mode.":[81],"To":[82],"overcome":[83],"learning":[85],"compromises":[87],"synthetic":[88,164,196],"texture,":[90],"propose":[92,117],"simple":[94],"yet":[95],"efficient":[96],"conditioning":[97],"strategy":[98],"in":[99,139,169,191,195],"filled":[105],"with":[106],"Gaussian":[107],"noise,":[108],"and":[109,143,175,194],"provide":[111],"theoretical":[112],"justification.":[113],"addition,":[115],"novel":[119],"training":[120],"objective":[121],"LDM":[123],"emphasizes":[125],"error":[127],"within":[128],"Furthermore,":[132,178],"design,":[138],"T2w":[141],"scans":[142,145],"DWI&ADC":[144],"compressed":[147],"using":[148],"two":[149],"separate":[150],"autoencoders":[151],"preserve":[153],"their":[154],"distinct":[155],"frequency":[156],"characteristics.":[157],"Extensive":[158],"experiments":[159],"demonstrate":[160],"generated":[163],"data":[165],"improves":[166],"downstream":[167,192],"performance":[168,193],"segmentation,":[172],"patient-level":[173],"classification":[174],"lesion-level":[176],"detection.":[177],"our":[179],"significantly":[181],"outperforms":[182],"recent":[184],"state-of-the-art":[185],"LDM-based":[186],"both":[190],"quality.":[198]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}