{"id":"https://openalex.org/W7161776647","doi":"https://doi.org/10.1109/isbi61048.2026.11515779","title":"REAF: a Region-Enhanced Volume-Slice Hierarchical Attention Fusion Vision-Language Model for CT-Report Retrieval","display_name":"REAF: a Region-Enhanced Volume-Slice Hierarchical Attention Fusion Vision-Language Model for CT-Report Retrieval","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7161776647","doi":"https://doi.org/10.1109/isbi61048.2026.11515779"},"language":null,"primary_location":{"id":"doi:10.1109/isbi61048.2026.11515779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136611706","display_name":"Jinlong He","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong He","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136529566","display_name":"Kang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Li","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136601368","display_name":"Guotai Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guotai Wang","raw_affiliation_strings":["School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"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":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5978999733924866,"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":0.5978999733924866,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.18449999392032623,"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/T11894","display_name":"Radiology practices and education","score":0.025200000032782555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.36309999227523804},{"id":"https://openalex.org/keywords/sensor-fusion","display_name":"Sensor fusion","score":0.337799996137619},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.29820001125335693},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2842000126838684},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2612000107765198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781000256538391},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26739999651908875},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.24619999527931213}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isbi61048.2026.11515779","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi61048.2026.11515779","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5603717266","display_name":null,"funder_award_id":"2025ZNSFSC0455","funder_id":"https://openalex.org/F4320329861","funder_display_name":"Natural Science Foundation of Sichuan Province"}],"funders":[{"id":"https://openalex.org/F4320329861","display_name":"Natural Science Foundation of Sichuan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3046375318","https://openalex.org/W4401752980","https://openalex.org/W4402753586","https://openalex.org/W4408741960","https://openalex.org/W4410297574","https://openalex.org/W4412605353"],"related_works":[],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1],"between":[2],"3D":[3,94],"medical":[4],"images":[5],"and":[6,32,79,87,91,152,158,164,167,172],"radiological":[7],"reports":[8],"is":[9,104,183],"crucial":[10],"for":[11,161,178],"clinical":[12],"decision":[13],"support.":[14],"However,":[15],"existing":[16],"Vision-Language":[17],"Models":[18],"(VLMs)":[19],"struggle":[20],"to":[21,28,41],"adequately":[22],"represent":[23],"complex":[24],"volumetric":[25],"data,":[26],"failing":[27],"capture":[29],"complementary":[30],"global":[31],"local":[33],"features":[34,45,82],"simultaneously.":[35],"Moreover,":[36],"they":[37],"often":[38],"lack":[39],"mechanisms":[40],"weigh":[42],"clinically":[43],"salient":[44],"across":[46,83],"these":[47,53],"distinct":[48],"granularities":[49],"adaptively.":[50],"To":[51],"alleviate":[52],"limitations,":[54],"we":[55],"propose":[56],"a":[57],"Region-Enhanced":[58],"volume-slice":[59],"hierarchical":[60],"Attention":[61,73],"Fusion":[62,74],"(REAF)":[63],"method":[64],"that":[65,125],"includes":[66],"two":[67],"core":[68],"modules:":[69],"(1)":[70],"Layer-wise":[71],"Hierarchical":[72],"(LHAF),":[75],"which":[76,99],"effectively":[77],"extracts":[78],"fuses":[80],"data":[81],"the":[84,93,101,110,135],"volume-level":[85],"(global)":[86],"slice-level":[88],"(local)":[89],"hierarchy,":[90],"(2)":[92],"Regional":[95],"Saliency":[96],"Enhancer":[97],"(3D-RSE),":[98],"ensures":[100],"fusion":[102],"process":[103],"content-aware":[105],"by":[106],"dynamically":[107],"concentrating":[108],"on":[109,134,142],"most":[111],"informative":[112],"regions":[113],"at":[114,185],"each":[115],"level.":[116],"This":[117],"dual-module":[118],"approach":[119],"generates":[120],"more":[121],"focused":[122],"visual":[123],"representations":[124],"are":[126],"better":[127],"aligned":[128],"with":[129,145],"radiology":[130],"reports.":[131],"Trained":[132],"end-to-end":[133],"CT-RATE":[136],"dataset,":[137],"REAF":[138],"outperforms":[139],"previous":[140],"methods":[141],"image-text":[143],"retrieval,":[144,163],"improvements":[146],"of":[147],"5.15":[148],"percentage":[149],"points":[150],"(p.p.)":[151],"7.32":[153],"p.p.":[154,166,169],"in":[155,170],"Recall@50":[156],"(R@50)":[157],"Recall@100":[159],"(R@100)":[160],"report-to-volume":[162],"4.61":[165],"7.05":[168],"R@50":[171],"<tex":[173],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathrm{R}":[175],"@":[176],"100$</tex>":[177],"volume-to-report":[179],"retrieval.":[180],"The":[181],"code":[182],"available":[184],"https://github.com/HiLab-git/REAF.":[186]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-21T00:00:00"}