{"id":"https://openalex.org/W4414415348","doi":"https://doi.org/10.1007/978-3-032-06004-4_20","title":"Enhancing 3D Medical Vision-Language Models with\u00a0Slice-Wise Visual Prompt","display_name":"Enhancing 3D Medical Vision-Language Models with\u00a0Slice-Wise Visual Prompt","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414415348","doi":"https://doi.org/10.1007/978-3-032-06004-4_20"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-032-06004-4_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-06004-4_20","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-06004-4_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-06004-4_20.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Soo Yong Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111274","display_name":"Modulim (United States)","ror":"https://ror.org/01zd81893","country_code":"US","type":"company","lineage":["https://openalex.org/I4210111274"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soo Yong Kim","raw_affiliation_strings":["HAE-RAE LAB, MODULABS, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"HAE-RAE LAB, MODULABS, Seoul, South Korea","institution_ids":["https://openalex.org/I4210111274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037191396","display_name":"Seunghyeok Hong","orcid":"https://orcid.org/0000-0003-4242-7638"},"institutions":[{"id":"https://openalex.org/I4210111274","display_name":"Modulim (United States)","ror":"https://ror.org/01zd81893","country_code":"US","type":"company","lineage":["https://openalex.org/I4210111274"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seunghyeok Hong","raw_affiliation_strings":["HAE-RAE LAB, MODULABS, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"HAE-RAE LAB, MODULABS, Seoul, South Korea","institution_ids":["https://openalex.org/I4210111274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210111274"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56627995,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"197","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9973999857902527,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9952999949455261,"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/focus","display_name":"Focus (optics)","score":0.6237999796867371},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.5950999855995178},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5480999946594238},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.39309999346733093},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36559998989105225},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.33239999413490295}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8870999813079834},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5393999814987183},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44429999589920044},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.39309999346733093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C2778105581","wikidata":"https://www.wikidata.org/wiki/Q1925316","display_name":"Meteor (satellite)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2858000099658966},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26159998774528503}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-032-06004-4_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-06004-4_20","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-06004-4_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1007/978-3-032-06004-4_20","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-032-06004-4_20","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-032-06004-4_20.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414415348.pdf","grobid_xml":"https://content.openalex.org/works/W4414415348.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2114063639","https://openalex.org/W2963351448","https://openalex.org/W4383218413","https://openalex.org/W4390873312","https://openalex.org/W4402716166","https://openalex.org/W4403805874","https://openalex.org/W4409180202","https://openalex.org/W4409247276","https://openalex.org/W4411119270","https://openalex.org/W4412378716","https://openalex.org/W4413145112","https://openalex.org/W4413887286"],"related_works":[],"abstract_inverted_index":{"3D":[0,31,116],"computed-tomography":[1],"(CT)":[2],"volumes":[3],"present":[4],"unique":[5],"challenges":[6],"for":[7,167],"multimodal":[8],"reasoning":[9],"because":[10],"vision\u2013language":[11],"models":[12],"(VLMs)":[13,59],"must":[14],"align":[15],"long":[16],"spatial\u2013temporal":[17],"contexts":[18],"with":[19,35,136],"radiological":[20],"text":[21],"while":[22,149],"remaining":[23],"memory-efficient.":[24],"Med3DVLM":[25],"recently":[26],"showed":[27],"that":[28,126],"a":[29,36,77,86,98],"dedicated":[30],"vision":[32],"encoder":[33],"combined":[34],"7B-parameter":[37],"language":[38],"decoder":[39],"can":[40],"reach":[41],"79.95%":[42],"closed-ended":[43,158],"accuracy":[44,159],"and":[45,79,122,134,160,164],"36.76%":[46],"METEOR":[47,165],"on":[48,64,119],"the":[49,53,65,103,107,115,120,127,142],"M3D":[50],"benchmark.":[51],"However,":[52],"attention":[54,72],"maps":[55],"in":[56,76],"Vision-Language":[57],"Models":[58],"often":[60],"fail":[61],"to":[62,106,110,141],"focus":[63],"areas":[66],"of":[67,129],"greatest":[68],"relevance,":[69],"instead":[70],"dispersing":[71],"across":[73],"multiple":[74],"regions":[75],"sparse":[78],"less":[80],"targeted":[81],"manner.":[82],"We":[83],"therefore":[84],"introduce":[85],"novel":[87],"slice-wise":[88],"visual\u2013instruction":[89],"prompting":[90],"scheme,":[91],"which":[92],"enhances":[93],"model":[94,146],"performance":[95],"by":[96],"overlaying":[97],"sub-voxel-thin,":[99],"colored":[100],"outline":[101],"around":[102],"anatomy":[104],"relevant":[105],"question,":[108],"applied":[109],"each":[111],"2D":[112],"slice":[113],"within":[114],"volume.":[117],"Experiments":[118],"RadGenome-ChestCT":[121],"PMC-VQA":[123],"corpora":[124],"show":[125],"group":[128],"Qwen":[130,145],"variants":[131],"(1.5B,":[132],"3B,":[133],"0.5B)":[135],"visual":[137],"prompts":[138],"performs":[139],"similarly":[140],"baseline":[143],"7B":[144],"without":[147],"prompts,":[148],"reducing":[150],"GPU":[151],"memory":[152],"usage.":[153],"Additionally,":[154],"prompt-guided":[155],"fine-tuning":[156],"improves":[157],"boosts":[161],"BLEU-4,":[162],"ROUGE-L,":[163],"scores":[166],"open-ended":[168],"VQA.":[169]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}