{"id":"https://openalex.org/W4416112301","doi":"https://doi.org/10.48550/arxiv.2503.03942","title":"SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection","display_name":"SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection","publication_year":2025,"publication_date":"2025-03-05","ids":{"openalex":"https://openalex.org/W4416112301","doi":"https://doi.org/10.48550/arxiv.2503.03942"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.03942","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03942","pdf_url":"https://arxiv.org/pdf/2503.03942","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.03942","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074366315","display_name":"Devanish Narasimhasanth Kamtam","orcid":"https://orcid.org/0000-0001-9174-3405","observed_orcids":["https://orcid.org/0000-0001-9174-3405"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamtam, Devanish N.","raw_affiliation_strings":[". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087335190","display_name":"Joseph B. Shrager","orcid":"https://orcid.org/0000-0003-0859-0589","observed_orcids":["https://orcid.org/0000-0003-0859-0589"]},"institutions":[{"id":"https://openalex.org/I204866599","display_name":"VA Palo Alto Health Care System","ror":"https://ror.org/00nr17z89","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1322918889","https://openalex.org/I204866599","https://openalex.org/I2799886695","https://openalex.org/I4210125474"]},{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrager, Joseph B.","raw_affiliation_strings":[". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA",". Veterans Affairs Palo Alto Health Care System , Palo Alto , CA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"raw_affiliation_string":". Veterans Affairs Palo Alto Health Care System , Palo Alto , CA , USA","institution_ids":["https://openalex.org/I204866599"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015479552","display_name":"Satya Deepya Malla","orcid":"https://orcid.org/0009-0002-2587-6896","observed_orcids":["https://orcid.org/0009-0002-2587-6896"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malla, Satya Deepya","raw_affiliation_strings":[". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100354377","display_name":"Xiaohan Wang","orcid":"https://orcid.org/0000-0001-6206-7911","observed_orcids":["https://orcid.org/0000-0001-6206-7911"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xiaohan","raw_affiliation_strings":[". Department of Computer Science , Stanford University , Stanford , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Department of Computer Science , Stanford University , Stanford , California , USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086978737","display_name":"Nicole Lin","orcid":"https://orcid.org/0000-0002-2526-9079","observed_orcids":["https://orcid.org/0000-0002-2526-9079","https://orcid.org/0000-0002-7431-1018"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin, Nicole","raw_affiliation_strings":[". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Division of Thoracic Surgery , Department of Cardiothoracic Surgery , Stanford University School of Medicine , Stanford , California , USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049944132","display_name":"Juan J. Cardona","orcid":"https://orcid.org/0000-0002-4148-5687","observed_orcids":["https://orcid.org/0000-0002-4148-5687","https://orcid.org/0000-0002-6891-375X"]},"institutions":[{"id":"https://openalex.org/I4210137306","display_name":"Stanford Medicine","ror":"https://ror.org/03mtd9a03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cardona, Juan J.","raw_affiliation_strings":[". Department of Neurosurgery , Stanford University School of Medicine , Stanford , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Department of Neurosurgery , Stanford University School of Medicine , Stanford , California , USA","institution_ids":["https://openalex.org/I4210137306","https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081511803","display_name":"Serena Y. Yeung","orcid":"https://orcid.org/0000-0003-0529-0628","observed_orcids":["https://orcid.org/0000-0003-0529-0628"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yeung-Levy, Serena","raw_affiliation_strings":[". Department of Biomedical Data Science , Stanford University , Stanford , California , USA",". Department of Computer Science , Stanford University , Stanford , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Department of Biomedical Data Science , Stanford University , Stanford , California , USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":". Department of Computer Science , Stanford University , Stanford , California , USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103138600","display_name":"Clarence Hu","orcid":"https://orcid.org/0009-0004-3991-4480","observed_orcids":["https://orcid.org/0009-0004-3991-4480"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Clarence","raw_affiliation_strings":[". Hotpot.ai , Palo Alto , California , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Hotpot.ai , Palo Alto , California , USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.8916000127792358,"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":0.8916000127792358,"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/T10916","display_name":"Surgical Simulation and Training","score":0.051500000059604645,"subfield":{"id":"https://openalex.org/subfields/2746","display_name":"Surgery"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03830000013113022,"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":[{"id":"https://openalex.org/keywords/segment-anything-model-2","display_name":"Segment Anything Model 2","score":0.9769999980926514},{"id":"https://openalex.org/keywords/organ-segmentation","display_name":"organ segmentation","score":0.640999972820282},{"id":"https://openalex.org/keywords/zero-shot-segmentation","display_name":"zero-shot segmentation","score":0.7850000262260437},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/dataset-size","display_name":"dataset size","score":0.546999990940094},{"id":"https://openalex.org/keywords/automatic-annotation","display_name":"automatic annotation","score":0.4560000002384186},{"id":"https://openalex.org/keywords/surgical-scene-understanding","display_name":"surgical scene understanding","score":0.8360000252723694}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7860000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7379000186920166},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.6111000180244446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6033999919891357},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5428000092506409},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.5130000114440918},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4715999960899353},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4571000039577484},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.435699999332428},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43389999866485596},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.29089999198913574},{"id":"https://openalex.org/C2779370443","wikidata":"https://www.wikidata.org/wiki/Q1776627","display_name":"Surgical planning","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.03942","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03942","pdf_url":"https://arxiv.org/pdf/2503.03942","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.2503.03942","doi":"https://doi.org/10.48550/arxiv.2503.03942","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.03942","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:2503.03942","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.03942","pdf_url":"https://arxiv.org/pdf/2503.03942","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":[{"id":"https://metadata.un.org/sdg/3","score":0.46810001134872437,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416112301.pdf","grobid_xml":"https://content.openalex.org/works/W4416112301.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415203355","https://openalex.org/W7147427365","https://openalex.org/W4411844936","https://openalex.org/W4400904844","https://openalex.org/W4393159543","https://openalex.org/W4407568873","https://openalex.org/W7118022096","https://openalex.org/W4409224394","https://openalex.org/W7117962187","https://openalex.org/W4404970395"],"abstract_inverted_index":{"Background:":[0],"We":[1,25,53],"evaluate":[2,31],"SAM":[3,34,105,124,204],"2":[4,35,106,189,205],"for":[5,15,36,212,231],"surgical":[6,41,213,244],"scene":[7,214],"understanding":[8],"by":[9],"examining":[10],"its":[11],"semantic":[12],"segmentation":[13,112],"capabilities":[14],"organs/tissues":[16],"both":[17],"in":[18,40,111,173],"zero-shot":[19,208],"scenarios":[20],"and":[21,32,50,88,133,158,209],"after":[22],"fine-tuning.":[23],"Methods:":[24],"utilized":[26],"five":[27],"public":[28],"datasets":[29],"to":[30,46,59,64,121,131,139,192],"fine-tune":[33],"segmenting":[37],"anatomical":[38],"tissues":[39],"videos/images.":[42],"Fine-tuning":[43],"was":[44,80,152],"applied":[45],"the":[47,89,122,143,149,164,177,238],"image":[48],"encoder":[49],"mask":[51],"decoder.":[52],"limited":[54],"training":[55,134],"subsets":[56],"from":[57,129,137],"50":[58],"400":[60,159],"samples":[61,160],"per":[62,161],"class":[63],"better":[65],"model":[66,168],"real-world":[67],"constraints":[68],"with":[69,82,154,179],"data":[70,135],"acquisition.":[71],"The":[72],"impact":[73],"of":[74,146,176,182,201,224,240],"dataset":[75],"size":[76],"on":[77,148,198],"fine-tuning":[78],"performance":[79,211],"evaluated":[81],"weighted":[83],"mean":[84],"Dice":[85],"coefficient":[86],"(WMDC),":[87],"results":[90],"were":[91],"also":[92],"compared":[93,120],"against":[94],"previously":[95],"reported":[96],"state-of-the-art":[97],"(SOTA)":[98],"results.":[99],"Results:":[100],"SurgiSAM":[101,188],"2,":[102],"a":[103,115,180],"fine-tuned":[104,210],"model,":[107],"demonstrated":[108],"significant":[109],"improvements":[110],"performance,":[113],"achieving":[114,196],"17.9%":[116],"relative":[117],"WMDC":[118,145,181],"gain":[119],"baseline":[123],"2.":[125],"Increasing":[126],"prompt":[127,156],"points":[128,157],"1":[130],"10":[132,155],"scale":[136],"50/class":[138],"400/class":[140],"enhanced":[141],"performance;":[142],"best":[144],"0.92":[147],"validation":[150],"subset":[151],"achieved":[153],"class.":[162],"On":[163],"test":[165],"subset,":[166],"this":[167],"outperformed":[169],"prior":[170,217],"SOTA":[171,197,218],"methods":[172],"24/30":[174],"(80%)":[175],"classes":[178,223],"0.91":[183],"using":[184],"10-point":[185],"prompts.":[186],"Notably,":[187],"generalized":[190],"effectively":[191],"unseen":[193],"organ":[194,222],"classes,":[195],"7/9":[199],"(77.8%)":[200],"them.":[202],"Conclusion:":[203],"achieves":[206],"remarkable":[207],"segmentation,":[215],"surpassing":[216],"models":[219],"across":[220],"several":[221,243],"diverse":[225],"datasets.":[226],"This":[227],"suggests":[228],"immense":[229],"potential":[230],"enabling":[232],"automated/semi-automated":[233],"annotation":[234],"pipelines,":[235],"thereby":[236],"decreasing":[237],"burden":[239],"annotations":[241],"facilitating":[242],"applications.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2025-10-10T00:00:00"}