{"id":"https://openalex.org/W4402952224","doi":"https://doi.org/10.48550/arxiv.2408.17421","title":"Generative AI Enables Medical Image Segmentation in Ultra Low-Data\n Regimes","display_name":"Generative AI Enables Medical Image Segmentation in Ultra Low-Data\n Regimes","publication_year":2024,"publication_date":"2024-08-30","ids":{"openalex":"https://openalex.org/W4402952224","doi":"https://doi.org/10.48550/arxiv.2408.17421"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.17421","pdf_url":"http://arxiv.org/pdf/2408.17421","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"posted-content","indexed_in":["arxiv"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2408.17421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032974264","display_name":"Zhaonian Zhang","orcid":"https://orcid.org/0000-0002-3166-215X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113407718","display_name":"Basu Jindal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jindal, Basu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014596965","display_name":"Ahmed M. Alaa","orcid":"https://orcid.org/0000-0001-9936-7141"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alaa, Ahmed","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043994887","display_name":"Robert N. Weinreb","orcid":"https://orcid.org/0000-0001-9553-3202"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weinreb, Robert","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053225296","display_name":"David O. Wilson","orcid":"https://orcid.org/0000-0002-2635-7468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wilson, David","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012450539","display_name":"Eran Segal","orcid":"https://orcid.org/0000-0002-6859-1164"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Segal, Eran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005779176","display_name":"James Zou","orcid":"https://orcid.org/0000-0001-8880-4764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, James","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083884675","display_name":"Pengtao Xie","orcid":"https://orcid.org/0000-0003-0521-174X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Pengtao","raw_affiliation_strings":[],"affiliations":[]}],"institution_assertions":[],"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":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":83},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.5869,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.5869,"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/T10862","display_name":"AI in cancer detection","score":0.5551,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.5049,"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"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6997259},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.64611113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6038118},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.52823114},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5212989},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.51875615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.491055}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.17421","pdf_url":"http://arxiv.org/pdf/2408.17421","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.17421","pdf_url":"http://arxiv.org/pdf/2408.17421","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390718435","https://openalex.org/W4390549206","https://openalex.org/W4383031710","https://openalex.org/W4379540039","https://openalex.org/W4237784285","https://openalex.org/W3211753092","https://openalex.org/W3137171911","https://openalex.org/W2380075625","https://openalex.org/W2374712251","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,33,90,115,133,156,169,190],"of":[2,67,154,196,230],"medical":[3,93,167,235],"images":[4,57],"is":[5,27,147],"pivotal":[6],"in":[7,20,103,175,199,234,238],"applications":[8],"like":[9],"disease":[10],"diagnosis":[11],"and":[12,45,92,114,171,183,202,228],"treatment":[13],"planning.":[14],"While":[15],"deep":[16,69,82,232],"learning":[17,70,83,233],"has":[18],"excelled":[19],"automating":[21],"this":[22],"task,":[23],"a":[24,80],"major":[25],"hurdle":[26],"the":[28,42,65,138,144,152,155,226],"need":[29],"for":[30,64,99,126],"numerous":[31],"annotated":[32,56],"masks,":[34],"which":[35,85],"are":[36,58],"resource-intensive":[37],"to":[38,41,51,135,150,188,209,218],"produce":[39],"due":[40],"required":[43],"expertise":[44],"time.":[46],"This":[47,130,222],"scenario":[48],"often":[49],"leads":[50],"ultra":[52],"low-data":[53],"regimes,":[54,178],"where":[55],"extremely":[59],"limited,":[60],"posing":[61],"significant":[62],"challenges":[63],"generalization":[66,162],"conventional":[68],"methods":[71,217],"on":[72,172],"test":[73],"images.":[74],"To":[75],"address":[76],"this,":[77],"we":[78],"introduce":[79],"generative":[81,108],"framework,":[84],"uniquely":[86],"generates":[87],"high-quality":[88],"paired":[89],"masks":[91],"images,":[94],"serving":[95],"as":[96,118],"auxiliary":[97],"data":[98,112,128,139,146,177,214,242],"training":[100,117,213],"robust":[101],"models":[102,109],"data-scarce":[104],"environments.":[105],"Unlike":[106],"traditional":[107],"that":[110,143],"treat":[111],"generation":[113,140],"model":[116],"separate":[119],"processes,":[120],"our":[121],"method":[122,159],"employs":[123],"multi-level":[124],"optimization":[125],"end-to-end":[127],"generation.":[129],"approach":[131],"allows":[132],"performance":[134,153,163,194],"directly":[136],"influence":[137],"process,":[141],"ensuring":[142],"generated":[145],"specifically":[148],"tailored":[149],"enhance":[151],"model.":[157],"Our":[158],"demonstrated":[160],"strong":[161],"across":[164],"9":[165],"diverse":[166],"image":[168],"tasks":[170],"16":[173],"datasets,":[174],"ultra-low":[176],"spanning":[179],"various":[180,189],"diseases,":[181],"organs,":[182],"imaging":[184],"modalities.":[185],"When":[186],"applied":[187],"models,":[191],"it":[192,206],"achieved":[193],"improvements":[195],"10-20\\%":[197],"(absolute),":[198],"both":[200],"same-domain":[201],"out-of-domain":[203],"scenarios.":[204],"Notably,":[205],"requires":[207],"8":[208],"20":[210],"times":[211],"less":[212],"than":[215],"existing":[216],"achieve":[219],"comparable":[220],"results.":[221],"advancement":[223],"significantly":[224],"improves":[225],"feasibility":[227],"cost-effectiveness":[229],"applying":[231],"imaging,":[236],"particularly":[237],"scenarios":[239],"with":[240],"limited":[241],"availability.":[243]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4402952224","counts_by_year":[],"updated_date":"2025-01-09T06:07:40.331789","created_date":"2024-09-29"}