{"id":"https://openalex.org/W7117576868","doi":"https://doi.org/10.48550/arxiv.2512.21984","title":"A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentation","display_name":"A Lightweight Multi-Scale Attention Framework for Real-Time Spinal Endoscopic Instance Segmentation","publication_year":2025,"publication_date":"2025-12-26","ids":{"openalex":"https://openalex.org/W7117576868","doi":"https://doi.org/10.48550/arxiv.2512.21984"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.21984","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.21984","pdf_url":"https://arxiv.org/pdf/2512.21984","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/2512.21984","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121592299","display_name":"Qi Lai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121530322","display_name":"JunYan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, JunYan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cai, Qiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121562375","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-7275-4846","observed_orcids":["https://orcid.org/0000-0001-7275-4846"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121525906","display_name":"Tao Yan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056242195","display_name":"Xiaokun Liang","orcid":"https://orcid.org/0000-0002-1207-5726","observed_orcids":["https://orcid.org/0000-0002-1207-5726"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, XiaoKun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":false,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8554999828338623,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.8554999828338623,"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":0.10679999738931656,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spinal-endoscopy","display_name":"spinal endoscopy","score":0.9390000104904175},{"id":"https://openalex.org/keywords/instance-segmentation","display_name":"instance segmentation","score":0.7950000166893005},{"id":"https://openalex.org/keywords/real-time-segmentation","display_name":"real-time segmentation","score":0.7699999809265137},{"id":"https://openalex.org/keywords/lightweight-neural-networks","display_name":"lightweight neural networks","score":0.6970000267028809},{"id":"https://openalex.org/keywords/multiscale-attention","display_name":"multi-scale attention","score":0.996999979019165},{"id":"https://openalex.org/keywords/repvit","display_name":"RepViT","score":0.7929999828338623},{"id":"https://openalex.org/keywords/feature-fusion","display_name":"feature fusion","score":0.7649999856948853},{"id":"https://openalex.org/keywords/ligamentum-flavum","display_name":"ligamentum flavum","score":0.8529999852180481},{"id":"https://openalex.org/keywords/nerve-segmentation","display_name":"nerve segmentation","score":0.6629999876022339}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7771999835968018},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.656499981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.638700008392334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5559999942779541},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4763000011444092},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44830000400543213},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4350999891757965},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4291999936103821},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.384799987077713},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.32109999656677246},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.30149999260902405},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.28360000252723694},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27900001406669617},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.27619999647140503},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.21984","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.21984","pdf_url":"https://arxiv.org/pdf/2512.21984","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.2512.21984","doi":"https://doi.org/10.48550/arxiv.2512.21984","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.21984","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":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:2512.21984","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.21984","pdf_url":"https://arxiv.org/pdf/2512.21984","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":0.4000000059604645,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Real-time":[0],"instance":[1,159,189],"segmentation":[2,190],"for":[3,8,101,161],"spinal":[4],"endoscopy":[5],"is":[6,18,37,173],"important":[7],"identifying":[9],"and":[10,32,50,52,72,108,116,137,142,167,184,196,199,209],"protecting":[11],"critical":[12],"anatomy":[13],"during":[14],"surgery,":[15],"but":[16],"it":[17,200],"difficult":[19],"because":[20],"of":[21,25],"the":[22,45,149],"narrow":[23],"field":[24],"view,":[26],"specular":[27],"highlights,":[28],"smoke/bleeding,":[29],"unclear":[30],"boundaries,":[31],"large":[33],"scale":[34],"changes.":[35],"Deployment":[36],"also":[38,147],"constrained":[39],"by":[40],"limited":[41],"surgical":[42],"hardware,":[43],"so":[44],"model":[46],"must":[47],"balance":[48],"accuracy":[49],"speed":[51],"remain":[53],"stable":[54],"under":[55],"small-batch":[56],"(even":[57],"batch-1)":[58],"training.":[59],"We":[60,146],"propose":[61],"LMSF-A,":[62],"a":[63,77,97,128,204],"lightweight":[64],"multi-scale":[65,88],"attention":[66,89],"framework":[67],"co-designed":[68],"across":[69],"backbone,":[70],"neck,":[71],"head.":[73],"The":[74,103,125],"backbone":[75],"uses":[76],"C2f-Pro":[78],"module":[79],"that":[80,171],"combines":[81],"RepViT-style":[82],"re-parameterized":[83],"convolution":[84],"(RVB)":[85],"with":[86,134,158],"efficient":[87],"(EMA),":[90],"enabling":[91],"multi-branch":[92],"training":[93],"while":[94],"collapsing":[95],"into":[96],"single":[98],"fast":[99],"path":[100],"inference.":[102],"neck":[104],"improves":[105],"cross-scale":[106],"consistency":[107],"boundary":[109],"detail":[110],"using":[111],"Scale-Sequence":[112],"Feature":[113,118],"Fusion":[114],"(SSFF)":[115],"Triple":[117],"Encoding":[119],"(TFE),":[120],"which":[121],"strengthens":[122],"high-resolution":[123],"features.":[124],"head":[126],"adopts":[127],"Lightweight":[129],"Multi-task":[130],"Shared":[131],"Head":[132],"(LMSH)":[133],"shared":[135],"convolutions":[136],"GroupNorm":[138],"to":[139,203],"reduce":[140],"parameters":[141,195],"support":[143],"batch-1":[144],"stability.":[145],"release":[148],"clinically":[150],"reviewed":[151],"PELD":[152],"dataset":[153],"(61":[154],"patients,":[155],"610":[156],"images)":[157],"masks":[160],"adipose":[162],"tissue,":[163],"bone,":[164],"ligamentum":[165],"flavum,":[166],"nerve.":[168],"Experiments":[169],"show":[170],"LMSF-A":[172],"highly":[174],"competitive":[175],"(or":[176],"even":[177],"better":[178],"than)":[179],"in":[180],"all":[181],"evaluation":[182],"metrics":[183],"much":[185],"lighter":[186],"than":[187],"most":[188],"methods":[191],"requiring":[192],"only":[193],"1.8M":[194],"8.8":[197],"GFLOPs,":[198],"generalizes":[201],"well":[202],"public":[205],"teeth":[206],"benchmark.":[207],"Code":[208],"dataset:":[210],"https://github.com/hhwmortal/PELD-Instance-segmentation.":[211]},"counts_by_year":[],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-12-30T00:00:00"}