{"id":"https://openalex.org/W4414876833","doi":"https://doi.org/10.1109/wacv61042.2026.00790","title":"SurgXBench: Explainable Vision-Language Model Benchmark for Surgery","display_name":"SurgXBench: Explainable Vision-Language Model Benchmark for Surgery","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4414876833","doi":"https://doi.org/10.1109/wacv61042.2026.00790"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.10764","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiajun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Cheng","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xianwu Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianwu Zhao","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101864950","display_name":"Sainan Liu","orcid":"https://orcid.org/0000-0001-5371-7441"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sainan Liu","raw_affiliation_strings":["Intel Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024845005","display_name":"Xiaofan Yu","orcid":"https://orcid.org/0000-0002-9638-6184"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaofan Yu","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101802296","display_name":"Ravi Prakash","orcid":"https://orcid.org/0000-0003-4604-1759"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ravi Prakash","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058802367","display_name":"Patrick J. Codd","orcid":"https://orcid.org/0000-0003-2939-849X"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick J. Codd","raw_affiliation_strings":["Duke University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022615394","display_name":"Jonathan E. Katz","orcid":"https://orcid.org/0000-0001-8175-790X"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Elliott Katz","raw_affiliation_strings":["University of Miami"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Miami","institution_ids":["https://openalex.org/I145608581"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101725654","display_name":"Shan Lin","orcid":"https://orcid.org/0000-0003-4868-0650"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shan Lin","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"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":"8188","last_page":"8198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9154999852180481,"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":0.9154999852180481,"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/T10552","display_name":"Colorectal Cancer Screening and Detection","score":0.9151999950408936,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.7382000088691711},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.5942999720573425},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.558899998664856},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5220000147819519},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4781000018119812},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4717000126838684},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4672999978065491},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.45019999146461487}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7382000088691711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6263999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011000275611877},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5220000147819519},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4781000018119812},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4672999978065491},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45899999141693115},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.45019999146461487},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42289999127388},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3912999927997589},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38589999079704285},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3467999994754791},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2818000018596649},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00790","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00790","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.10764","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.10764","pdf_url":"https://arxiv.org/pdf/2505.10764","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.10764","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.10764","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.10764","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.10764","pdf_url":"https://arxiv.org/pdf/2505.10764","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Innovations":[0],"in":[1,51,174,181],"digital":[2],"intelligence":[3],"are":[4],"transforming":[5],"robotic":[6,59],"surgery":[7],"through":[8],"more":[9],"informed":[10],"decision-making.":[11],"Real-time":[12],"awareness":[13],"of":[14,28,94],"surgical":[15,62,148,175],"instrument":[16,105],"presence":[17],"and":[18,38,66,83,106,120,171],"actions":[19],"(e.g.,":[20],"cutting":[21],"tissue)":[22],"is":[23,179],"essential,":[24],"yet":[25],"despite":[26,150],"decades":[27],"research,":[29],"most":[30],"machine":[31],"learning":[32],"models":[33,68],"rely":[34,154],"on":[35,98,155],"small":[36],"datasets":[37,103],"still":[39],"struggle":[40],"to":[41,78,116,140],"generalize.":[42],"Recently,":[43],"Vision-Language":[44],"Models":[45],"(VLMs)":[46],"have":[47],"achieved":[48],"transformative":[49],"advances":[50],"multimodal":[52],"reasoning,":[53],"suggesting":[54],"strong":[55],"potential":[56],"for":[57,75,104,131,168],"intelligent":[58],"surgery.":[60],"However,":[61],"VLMs":[63,97],"remain":[64],"underexplored,":[65],"existing":[67],"show":[69],"limited":[70],"performance,":[71],"underscoring":[72],"the":[73,91,166],"need":[74,167],"systematic":[76],"benchmarks":[77],"assess":[79],"their":[80],"capabilities,":[81],"limitations,":[82],"future":[84],"development.":[85],"To":[86],"this":[87],"end,":[88],"we":[89,112],"benchmark":[90],"zero-shot":[92],"performance":[93],"several":[95],"advanced":[96],"two":[99],"public":[100,183],"robotic-assisted":[101],"laparoscopic":[102],"action":[107],"classification.":[108],"Beyond":[109],"standard":[110,142],"evaluation,":[111],"integrate":[113],"explainable":[114],"AI":[115],"visualize":[117],"VLM":[118],"attention":[119],"uncover":[121],"causal":[122],"explanations":[123],"behind":[124],"predictions,":[125],"providing":[126],"a":[127],"previously":[128],"underexplored":[129],"perspective":[130],"assessing":[132],"model":[133],"reliability.":[134],"We":[135],"also":[136],"propose":[137],"explainability-based":[138],"metrics":[139],"complement":[141],"evaluations.":[143],"Our":[144],"analysis":[145],"reveals":[146],"that":[147],"VLMs,":[149],"domain-specific":[151],"training,":[152],"often":[153],"weak":[156],"contextual":[157],"cues":[158],"rather":[159],"than":[160],"clinically":[161],"meaningful":[162],"visual":[163,170],"evidence,":[164],"highlighting":[165],"stronger":[169],"reasoning":[172],"supervision":[173],"applications.":[176],"The":[177],"code":[178],"provided":[180],"our":[182],"repository":[184],"at:":[185],"https://github.com/jiajun344/SurgXBench-Explainable-Vision-Language-Model-Benchmark-for-Surgery.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}