{"id":"https://openalex.org/W4408355745","doi":"https://doi.org/10.1109/icassp49660.2025.10889731","title":"Enhancing 3D Medical Image Understanding with 2D Multimodal Large Language Models","display_name":"Enhancing 3D Medical Image Understanding with 2D Multimodal Large Language Models","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355745","doi":"https://doi.org/10.1109/icassp49660.2025.10889731"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5044183215","display_name":"Qiuhui Chen","orcid":"https://orcid.org/0000-0003-1823-2400"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuhui Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052046224","display_name":"Xiaolei Yao","orcid":"https://orcid.org/0000-0001-8186-5097"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuancheng Yao","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074501277","display_name":"Huping Ye","orcid":"https://orcid.org/0000-0002-9114-205X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huping Ye","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101931365","display_name":"Yi Hong","orcid":"https://orcid.org/0000-0002-9065-3691"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Hong","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.89094669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"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":0.9915000200271606,"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":0.9915000200271606,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.939300000667572,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9333999752998352,"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":0.6856058239936829},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4353088140487671},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.38638490438461304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3857539892196655},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37618327140808105},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35802268981933594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6856058239936829},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4353088140487671},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38638490438461304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3857539892196655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37618327140808105},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35802268981933594}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889731","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889731","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2124260444","https://openalex.org/W2150534249","https://openalex.org/W2194775991","https://openalex.org/W2291593693","https://openalex.org/W2792253967","https://openalex.org/W2902874468","https://openalex.org/W3002569343","https://openalex.org/W3014974815","https://openalex.org/W3096609285","https://openalex.org/W3170841864","https://openalex.org/W4212875960","https://openalex.org/W4312560592","https://openalex.org/W4312749457","https://openalex.org/W4313591097","https://openalex.org/W4319300504","https://openalex.org/W4384159609","https://openalex.org/W4385245566","https://openalex.org/W4385573131","https://openalex.org/W4386076097","https://openalex.org/W4386352556","https://openalex.org/W4387211540","https://openalex.org/W4403793633","https://openalex.org/W4405102058","https://openalex.org/W6633802082","https://openalex.org/W6750469568","https://openalex.org/W6761274798","https://openalex.org/W6784333009","https://openalex.org/W6790275670","https://openalex.org/W6791353385","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6849177959","https://openalex.org/W6851592950","https://openalex.org/W6853423225","https://openalex.org/W6857824944","https://openalex.org/W6858032187","https://openalex.org/W6858632107","https://openalex.org/W6863774206"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Understanding":[0],"medical":[1,26,106],"image":[2,40,59],"volumes":[3],"is":[4,118],"crucial":[5],"in":[6],"healthcare,":[7],"yet":[8],"most":[9],"current":[10],"models":[11,48],"for":[12,67],"classification":[13],"and":[14,74,87,94,113],"segmentation":[15],"often":[16],"focus":[17],"narrowly":[18],"on":[19,72],"task-specific":[20],"features":[21],"without":[22],"capturing":[23],"the":[24],"broader":[25],"context.":[27],"To":[28],"address":[29],"this,":[30],"we":[31],"introduce":[32],"Med3DInsight,":[33],"a":[34,51],"pre-training":[35],"framework":[36,98],"that":[37,78],"enhances":[38],"3D":[39,58,105],"understanding":[41],"by":[42],"leveraging":[43],"2D":[44,62],"multimodal":[45],"large":[46],"language":[47],"(MLLMs)":[49],"through":[50],"Plane-Slice-Aware":[52],"Transformer":[53],"(PSAT)":[54],"module.":[55],"Med3DInsight":[56,79],"connects":[57],"encoders":[60],"with":[61],"MLLMs,":[63],"enhancing":[64],"representation":[65],"learning":[66],"downstream":[68],"tasks.":[69],"Extensive":[70],"experiments":[71],"CT":[73],"MRI":[75],"datasets":[76],"demonstrate":[77],"achieves":[80],"state-of-the-art":[81],"performance,":[82],"surpassing":[83],"19":[84],"baseline":[85],"methods":[86],"proving":[88],"effective":[89],"across":[90],"diverse":[91],"imaging":[92,107],"modalities":[93],"anatomical":[95],"structures.":[96],"This":[97],"can":[99],"be":[100],"seamlessly":[101],"integrated":[102],"into":[103],"existing":[104],"networks,":[108],"significantly":[109],"boosting":[110],"their":[111],"performance":[112],"adaptability.":[114],"Our":[115],"source":[116],"code":[117],"publicly":[119],"available":[120],"at":[121],"https://github.com/Qybc/Med3DInsight.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}