{"id":"https://openalex.org/W4410296683","doi":"https://doi.org/10.1109/isbi60581.2025.10981029","title":"Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding","display_name":"Parameter-Efficient Fine-Tuning Medical Multimodal Large Language Models for Medical Visual Grounding","publication_year":2025,"publication_date":"2025-04-14","ids":{"openalex":"https://openalex.org/W4410296683","doi":"https://doi.org/10.1109/isbi60581.2025.10981029"},"language":"en","primary_location":{"id":"doi:10.1109/isbi60581.2025.10981029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi60581.2025.10981029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 22nd 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/A5101400989","display_name":"Jinlong He","orcid":"https://orcid.org/0009-0009-8891-554X"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinlong He","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339791","display_name":"Pengfei Li","orcid":"https://orcid.org/0009-0009-4234-1579"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Li","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109282686","display_name":"Gang Liu","orcid":"https://orcid.org/0000-0002-7032-8429"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Liu","raw_affiliation_strings":["College of Computer Science and Technology, Harbin Engineering University,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Harbin Engineering University,China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006400852","display_name":"Shenjun Zhong","orcid":"https://orcid.org/0000-0001-6542-649X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shenjun Zhong","raw_affiliation_strings":["Monash University,Monash Biomedical Imaging,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Monash Biomedical Imaging,Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9614999890327454,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9614999890327454,"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/T10862","display_name":"AI in cancer detection","score":0.9049000144004822,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9038000106811523,"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/computer-science","display_name":"Computer science","score":0.7207035422325134},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.5847084522247314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4161113202571869},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.36093854904174805},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3414866328239441},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12864255905151367},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12615838646888733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7207035422325134},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.5847084522247314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4161113202571869},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36093854904174805},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3414866328239441},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12864255905151367},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12615838646888733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isbi60581.2025.10981029","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isbi60581.2025.10981029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G5231731687","display_name":null,"funder_award_id":"KYWZ120240601","funder_id":"https://openalex.org/F4320321939","funder_display_name":"Harbin Engineering University"}],"funders":[{"id":"https://openalex.org/F4320321939","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3201906559","https://openalex.org/W4312533035","https://openalex.org/W4386076522","https://openalex.org/W4386352883","https://openalex.org/W4387211307","https://openalex.org/W4401750339"],"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":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"inherit":[5],"the":[6,26,34,37,42,51,59,97,130,133],"superior":[7],"text":[8,112],"understanding":[9],"capabilities":[10,16],"of":[11,29,53,62,132],"LLMs":[12],"and":[13,41,152],"extend":[14],"these":[15],"to":[17,50,58,71],"multimodal":[18,30],"scenarios.":[19],"These":[20],"models":[21,122],"achieve":[22],"excellent":[23],"results":[24],"in":[25,33,74,91,106],"general":[27],"domain":[28],"tasks.":[31],"However,":[32],"medical":[35,46,54,88,92,98,107,118,144],"domain,":[36],"substantial":[38],"training":[39],"costs":[40],"requirement":[43],"for":[44,80,123,143],"extensive":[45],"data":[47],"pose":[48],"challenges":[49],"development":[52],"MLLMs.":[55,81],"Furthermore,":[56],"due":[57],"free-text":[60],"form":[61,77],"answers,":[63],"tasks":[64],"such":[65],"as":[66],"visual":[67,93,145],"grounding":[68,94,100],"that":[69],"need":[70],"produce":[72],"output":[73],"a":[75,139],"prescribed":[76],"become":[78],"difficult":[79],"So":[82],"far,":[83],"there":[84],"have":[85],"been":[86],"no":[87],"MLLMs":[89],"works":[90],"area.":[95],"For":[96],"vision":[99],"task,":[101],"which":[102],"involves":[103],"identifying":[104],"locations":[105],"images":[108],"based":[109],"on":[110,138],"short":[111],"descriptions,":[113],"we":[114,135],"propose":[115],"Parameter-efficient":[116],"Fine-tuning":[117],"multi-modal":[119],"large":[120],"language":[121],"Medcial":[124],"Visual":[125],"Grounding":[126],"(PFMVG).":[127],"To":[128],"validate":[129],"performance":[131],"model,":[134],"evaluate":[136],"it":[137,148],"public":[140],"benchmark":[141],"dataset":[142],"grounding,":[146],"where":[147],"achieves":[149],"competitive":[150],"results,":[151],"significantly":[153],"outperforming":[154],"GPT-4v.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}