{"id":"https://openalex.org/W4288442702","doi":"https://doi.org/10.1007/s11548-022-02718-9","title":"SIG-Former: monocular surgical instruction generation with transformers","display_name":"SIG-Former: monocular surgical instruction generation with transformers","publication_year":2022,"publication_date":"2022-07-28","ids":{"openalex":"https://openalex.org/W4288442702","doi":"https://doi.org/10.1007/s11548-022-02718-9","pmid":"https://pubmed.ncbi.nlm.nih.gov/35900645"},"language":"en","primary_location":{"id":"doi:10.1007/s11548-022-02718-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11548-022-02718-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11548-022-02718-9.pdf","source":{"id":"https://openalex.org/S181408163","display_name":"International Journal of Computer Assisted Radiology and Surgery","issn_l":"1861-6410","issn":["1861-6410","1861-6429"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Assisted Radiology and Surgery","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11548-022-02718-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103033983","display_name":"Jinglu Zhang","orcid":"https://orcid.org/0000-0002-8708-9313"},"institutions":[{"id":"https://openalex.org/I9300472","display_name":"Bournemouth University","ror":"https://ror.org/05wwcw481","country_code":"GB","type":"education","lineage":["https://openalex.org/I9300472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jinglu Zhang","raw_affiliation_strings":["National Centre for Computer Animation, Bournemouth University, Bournemouth, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Centre for Computer Animation, Bournemouth University, Bournemouth, UK","institution_ids":["https://openalex.org/I9300472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051467266","display_name":"Yinyu Nie","orcid":"https://orcid.org/0000-0001-7023-6797"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yinyu Nie","raw_affiliation_strings":["Technical University of Munich, Munich, Germany. yinyu.nie@tum.de","Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7023-6797","affiliations":[{"raw_affiliation_string":"Technical University of Munich, Munich, Germany. yinyu.nie@tum.de","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052361049","display_name":"Jian Chang","orcid":"https://orcid.org/0000-0003-4118-147X"},"institutions":[{"id":"https://openalex.org/I9300472","display_name":"Bournemouth University","ror":"https://ror.org/05wwcw481","country_code":"GB","type":"education","lineage":["https://openalex.org/I9300472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jian Chang","raw_affiliation_strings":["National Centre for Computer Animation, Bournemouth University, Bournemouth, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Centre for Computer Animation, Bournemouth University, Bournemouth, UK","institution_ids":["https://openalex.org/I9300472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074858947","display_name":"Jianjun Zhang","orcid":"https://orcid.org/0000-0002-7069-5771"},"institutions":[{"id":"https://openalex.org/I9300472","display_name":"Bournemouth University","ror":"https://ror.org/05wwcw481","country_code":"GB","type":"education","lineage":["https://openalex.org/I9300472"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jian Jun Zhang","raw_affiliation_strings":["National Centre for Computer Animation, Bournemouth University, Bournemouth, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Centre for Computer Animation, Bournemouth University, Bournemouth, UK","institution_ids":["https://openalex.org/I9300472"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051467266"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":4390,"currency":"USD","value_usd":4390},"apc_paid":{"value":4390,"currency":"USD","value_usd":4390},"fwci":0.1619,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40138224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"17","issue":"12","first_page":"2203","last_page":"2210"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9384999871253967,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9384999871253967,"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":0.009600000455975533,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00839999970048666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5145158767700195}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5145158767700195}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000295","qualifier_name":"instrumentation","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D025321","descriptor_name":"Surgery, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":6,"locations":[{"id":"doi:10.1007/s11548-022-02718-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11548-022-02718-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11548-022-02718-9.pdf","source":{"id":"https://openalex.org/S181408163","display_name":"International Journal of Computer Assisted Radiology and Surgery","issn_l":"1861-6410","issn":["1861-6410","1861-6429"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Assisted Radiology and Surgery","raw_type":"journal-article"},{"id":"pmid:35900645","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35900645","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International journal of computer assisted radiology and surgery","raw_type":null},{"id":"pmh:oai:eprints.bournemouth.ac.uk:37330","is_oa":false,"landing_page_url":"https://eprints.bournemouth.ac.uk/37330/7/s11548-022-02718-9.pdf","pdf_url":"https://eprints.bournemouth.ac.uk/37330/7/s11548-022-02718-9.pdf","source":{"id":"https://openalex.org/S4306400187","display_name":"Bournemouth University Research Online (Bournemouth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9300472","host_organization_name":"Bournemouth University","host_organization_lineage":["https://openalex.org/I9300472"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9652298","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9652298","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Int J Comput Assist Radiol Surg","raw_type":"Text"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1763857","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1763857","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1796128","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1796128","pdf_url":null,"source":{"id":"https://openalex.org/S4306400453","display_name":"mediaTUM \u2013 the media and publications repository of the Technical University Munich (Technical University Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s11548-022-02718-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11548-022-02718-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11548-022-02718-9.pdf","source":{"id":"https://openalex.org/S181408163","display_name":"International Journal of Computer Assisted Radiology and Surgery","issn_l":"1861-6410","issn":["1861-6410","1861-6429"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Assisted Radiology and Surgery","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8600000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323383","display_name":"Technische Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/02kkvpp62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4288442702.pdf","grobid_xml":"https://content.openalex.org/works/W4288442702.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1895577753","https://openalex.org/W1956340063","https://openalex.org/W1987757040","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2266464013","https://openalex.org/W2506483933","https://openalex.org/W2614090717","https://openalex.org/W2747329762","https://openalex.org/W2770165365","https://openalex.org/W2901132985","https://openalex.org/W2912664121","https://openalex.org/W2963084599","https://openalex.org/W2980110287","https://openalex.org/W3034655362","https://openalex.org/W3092562667","https://openalex.org/W3098325931","https://openalex.org/W3104609094","https://openalex.org/W3203149165"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655"],"abstract_inverted_index":{"PURPOSE:":[0],"Automatic":[1],"surgical":[2,11,17,30,53,62,180],"instruction":[3,181],"generation":[4,49,182],"is":[5,168,183],"a":[6,47,61,75,111],"crucial":[7],"part":[8],"for":[9],"intra-operative":[10],"assistance.":[12],"However,":[13],"understanding":[14],"and":[15,32,38,92,103,152,159,176,200],"translating":[16],"activities":[18],"into":[19],"human-like":[20],"sentences":[21],"are":[22],"particularly":[23],"challenging":[24],"due":[25],"to":[26,51,84,116],"the":[27,33,98,119,150],"complexity":[28],"of":[29,170],"environment":[31],"modal":[34],"gap":[35],"between":[36,101,173],"images":[37],"natural":[39],"languages.":[40],"To":[41,96],"this":[42],"end,":[43],"we":[44,66,108],"introduce":[45],"SIG-Former,":[46],"transformer-backboned":[48],"network":[50],"predict":[52],"instructions":[54,199],"from":[55,139],"monocular":[56],"RGB":[57],"images.":[58,206],"METHODS:":[59],"Taking":[60],"image":[63],"as":[64],"input,":[65],"first":[67],"extract":[68],"its":[69,87,186],"visual":[70,88,174],"attentive":[71],"feature":[72,175],"map":[73],"with":[74],"fine-tuned":[76],"ResNet-101":[77],"model,":[78],"followed":[79],"by":[80],"transformer":[81],"attention":[82],"blocks":[83],"correspondingly":[85],"model":[86],"representation,":[89],"text":[90],"embedding":[91],"visual-textual":[93],"relational":[94],"feature.":[95],"tackle":[97],"loss-metric":[99],"inconsistency":[100],"training":[102],"inference":[104],"in":[105],"sequence":[106],"generation,":[107],"additionally":[109],"apply":[110],"self-critical":[112],"reinforcement":[113],"learning":[114],"approach":[115],"directly":[117],"optimize":[118],"CIDEr":[120],"score":[121],"after":[122],"regular":[123],"training.":[124],"RESULTS:":[125],"We":[126],"validate":[127],"our":[128,147],"proposed":[129],"method":[130,148],"on":[131,156,204],"DAISI":[132],"dataset,":[133,195],"which":[134],"contains":[135],"290":[136],"clinical":[137,194],"procedures":[138],"diverse":[140],"medical":[141,205],"subjects.":[142],"Extensive":[143],"experiments":[144,164],"demonstrate":[145,165],"that":[146,166],"outperforms":[149],"baselines":[151],"achieves":[153],"promising":[154],"performance":[155],"both":[157],"quantitative":[158],"qualitative":[160],"evaluations.":[161],"CONCLUSION:":[162],"Our":[163],"SIG-Former":[167],"capable":[169],"mapping":[171],"dependencies":[172],"textual":[177],"information.":[178],"Besides,":[179],"still":[184],"at":[185],"preliminary":[187],"stage.":[188],"Future":[189],"works":[190],"include":[191],"collecting":[192],"large":[193],"annotating":[196],"more":[197],"reference":[198],"preparing":[201],"pre-trained":[202],"models":[203]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
