{"id":"https://openalex.org/W7138960925","doi":"https://doi.org/10.48550/arxiv.2603.17576","title":"LoGSAM: Parameter-Efficient Cross-Modal Grounding for MRI Segmentation","display_name":"LoGSAM: Parameter-Efficient Cross-Modal Grounding for MRI Segmentation","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7138960925","doi":"https://doi.org/10.48550/arxiv.2603.17576"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.17576","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17576","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.17576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045251923","display_name":"Mohammad Robaitul Islam Bhuiyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Bhuiyan, Mohammad Robaitul Islam","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011959519","display_name":"Sheethal Bhat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bhat, Sheethal","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119682377","display_name":"Melika Qahqaie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qahqaie, Melika","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065772285","display_name":"Tri-Thien Nguyen","orcid":"https://orcid.org/0009-0007-0974-3299"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Tri-Thien","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130061528","display_name":"Paula Andrea P\u00e9rez Toro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Perez-Toro, Paula Andrea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130025760","display_name":"Tomas Arias Vergara","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arias-Vergara, Tomas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129857389","display_name":"Andreas Maier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maier, Andreas","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5045251923"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.17170000076293945,"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":0.17170000076293945,"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":0.1525000035762787,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.08460000157356262,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7522000074386597},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.621999979019165},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.5223000049591064},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.5033000111579895},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.47850000858306885},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.45010000467300415},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4205000102519989},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.4113999903202057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7993000149726868},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7522000074386597},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6601999998092651},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.621999979019165},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.5033000111579895},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4205000102519989},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C143409427","wikidata":"https://www.wikidata.org/wiki/Q161238","display_name":"Magnetic resonance imaging","level":2,"score":0.38670000433921814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3693999946117401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26669999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.17576","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17576","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.17576","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17576","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":"article"},"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":{"Precise":[0],"localization":[1,59,90],"and":[2,17,30,60,67],"delineation":[3],"of":[4,37,106,152,185],"brain":[5],"tumors":[6],"using":[7,69,104,164],"Magnetic":[8],"Resonance":[9],"Imaging":[10],"(MRI)":[11],"are":[12,31,125],"essential":[13],"for":[14,57,129],"planning":[15],"therapy":[16],"guiding":[18],"surgical":[19],"decisions.":[20],"However,":[21],"most":[22],"existing":[23],"approaches":[24],"rely":[25],"on":[26,144,154,171],"task-specific":[27],"supervised":[28],"models":[29,196],"constrained":[32],"by":[33,76,191],"the":[34,107,141,161,183],"limited":[35],"availability":[36],"annotated":[38],"data.":[39],"To":[40],"address":[41],"this,":[42],"we":[43,159],"propose":[44],"LoGSAM,":[45],"a":[46,70,92,148,168,187],"parameter-efficient,":[47],"detection-driven":[48],"framework":[49],"that":[50],"transforms":[51],"radiologist":[52,170],"dictation":[53],"into":[54],"text":[55],"prompts":[56,86,128],"foundation-model-based":[58],"segmentation.":[61],"Radiologist":[62],"speech":[63],"is":[64],"first":[65],"transcribed":[66],"translated":[68],"pretrained":[71,118,194],"Whisper":[72],"ASR":[73],"model,":[74,96],"followed":[75],"negation-aware":[77],"clinical":[78],"NLP":[79],"to":[80,131],"extract":[81],"tumor-specific":[82],"textual":[83],"prompts.":[84],"These":[85,180],"guide":[87],"text-conditioned":[88],"tumor":[89,134],"via":[91],"LoRA-adapted":[93],"vision-language":[94],"detection":[95],"Grounding":[97],"DINO":[98],"(GDINO).":[99],"The":[100,121],"LoRA":[101],"adaptation":[102,115],"updates":[103],"5%":[105],"model":[108],"parameters,":[109],"thereby":[110],"enabling":[111],"computationally":[112],"efficient":[113],"domain":[114],"while":[116],"preserving":[117],"cross-modal":[119],"knowledge.":[120],"predicted":[122],"bounding":[123],"boxes":[124],"used":[126],"as":[127],"MedSAM":[130,143],"generate":[132],"pixel-level":[133],"masks":[135],"without":[136],"any":[137],"additional":[138],"fine-tuning.":[139],"Conditioning":[140],"frozen":[142],"LoGSAM-derived":[145],"priors":[146],"yields":[147],"state-of-the-art":[149],"dice":[150],"score":[151],"80.32%":[153],"BRISC":[155],"2025.":[156],"In":[157],"addition,":[158],"evaluate":[160],"full":[162],"pipeline":[163,190],"German":[165],"dictations":[166],"from":[167],"board-certified":[169],"12":[172],"unseen":[173],"MRI":[174],"scans,":[175],"achieving":[176],"91.7%":[177],"case-level":[178],"accuracy.":[179],"results":[181],"highlight":[182],"feasibility":[184],"constructing":[186],"modular,":[188],"speech-to-segmentation":[189],"intelligently":[192],"leveraging":[193],"foundation":[195],"with":[197],"minimal":[198],"parameter":[199],"updates.":[200]},"counts_by_year":[],"updated_date":"2026-03-31T06:02:25.137627","created_date":"2026-03-20T00:00:00"}