{"id":"https://openalex.org/W7151831375","doi":"https://doi.org/10.48550/arxiv.2604.05515","title":"Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation","display_name":"Geometrical Cross-Attention and Nonvoid Voxelization for Efficient 3D Medical Image Segmentation","publication_year":2026,"publication_date":"2026-04-07","ids":{"openalex":"https://openalex.org/W7151831375","doi":"https://doi.org/10.48550/arxiv.2604.05515"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.05515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05515","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.05515","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133185592","display_name":"Chenxin Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Chenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016620741","display_name":"S. S. Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shoupeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111015515","display_name":"Haojiang Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Haojiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063057043","display_name":"Yiming Miao","orcid":"https://orcid.org/0000-0003-1580-9120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045371931","display_name":"Limei Peng","orcid":"https://orcid.org/0000-0001-9984-9861"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Limei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089628133","display_name":"Pin\u2010Han Ho","orcid":"https://orcid.org/0000-0002-0717-1481"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho, Pin-Han","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":0.8659999966621399,"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":0.8659999966621399,"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":0.039400000125169754,"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"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.017899999395012856,"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/segmentation","display_name":"Segmentation","score":0.7718999981880188},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.6013000011444092},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5629000067710876},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.5428000092506409},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5121999979019165},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5034000277519226},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.5006999969482422}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7718999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7630000114440918},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6934999823570251},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.6013000011444092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5968999862670898},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5629000067710876},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.5428000092506409},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5121999979019165},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.37529999017715454},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.05515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05515","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":"doi:10.48550/arxiv.2604.05515","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.05515","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"segmentation":[1,44,106,121,161],"of":[2,85],"3D":[3,42,87],"medical":[4,43],"scans":[5],"is":[6],"crucial":[7],"for":[8,210],"clinical":[9,211],"diagnostics":[10],"and":[11,24,30,60,79,123,130,155,181,194,196,204],"treatment":[12],"planning,":[13],"yet":[14],"existing":[15,169],"methods":[16,170],"often":[17],"fail":[18],"to":[19,138],"achieve":[20],"both":[21],"high":[22],"accuracy":[23,193],"computational":[25],"efficiency":[26],"across":[27,163,199],"diverse":[28,200],"anatomies":[29],"imaging":[31,205],"modalities.":[32],"To":[33],"address":[34],"these":[35],"challenges,":[36],"we":[37],"propose":[38],"GCNV-Net,":[39],"a":[40,48,55,125,131],"novel":[41],"framework":[45],"that":[46,189],"integrates":[47],"Tri-directional":[49],"Dynamic":[50],"Nonvoid":[51,61,109],"Voxel":[52],"Transformer":[53],"(3DNVT),":[54],"Geometrical":[56],"Cross-Attention":[57],"module":[58],"(GCA),":[59],"Voxelization.":[62],"The":[63,90],"3DNVT":[64],"dynamically":[65],"partitions":[66],"relevant":[67],"voxels":[68],"along":[69],"the":[70,76,167],"three":[71],"orthogonal":[72],"anatomical":[73,105],"planes,":[74,81],"namely":[75],"transverse,":[77],"sagittal,":[78],"coronal":[80],"enabling":[82],"effective":[83],"modeling":[84],"complex":[86],"spatial":[88],"dependencies.":[89],"GCA":[91],"mechanism":[92],"explicitly":[93],"incorporates":[94],"geometric":[95],"positional":[96],"information":[97],"during":[98],"multi-scale":[99],"feature":[100],"fusion,":[101],"significantly":[102],"enhancing":[103],"fine-grained":[104],"accuracy.":[107],"Meanwhile,":[108],"Voxelization":[110],"processes":[111],"only":[112],"informative":[113],"regions,":[114],"greatly":[115],"reducing":[116],"redundant":[117],"computation":[118],"without":[119],"compromising":[120],"quality,":[122],"achieves":[124,159],"56.13%":[126],"reduction":[127,133],"in":[128,134],"FLOPs":[129],"68.49%":[132],"inference":[135],"latency":[136],"compared":[137],"conventional":[139],"voxelization.":[140],"We":[141],"evaluate":[142],"GCNV-Net":[143,190],"on":[144,173,176,179,184],"multiple":[145],"widely":[146],"used":[147],"benchmarks:":[148],"BraTS2021,":[149],"ACDC,":[150],"MSD":[151,153],"Prostate,":[152],"Pancreas,":[154],"AMOS2022.":[156],"Our":[157],"method":[158],"state-of-the-art":[160],"performance":[162],"all":[164],"datasets,":[165],"outperforming":[166],"best":[168],"by":[171],"0.65%":[172],"Dice,":[174],"0.63%":[175],"IoU,":[177],"1%":[178],"NSD,":[180],"relatively":[182],"14.5%":[183],"HD95.":[185],"All":[186],"results":[187],"demonstrate":[188],"effectively":[191],"balances":[192],"efficiency,":[195],"its":[197],"robustness":[198],"organs,":[201],"disease":[202],"conditions,":[203],"modalities":[206],"highlights":[207],"strong":[208],"potential":[209],"deployment.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-09T00:00:00"}