{"id":"https://openalex.org/W7155039237","doi":"https://doi.org/10.48550/arxiv.2604.18145","title":"Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework","display_name":"Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7155039237","doi":"https://doi.org/10.48550/arxiv.2604.18145"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.18145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18145","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.18145","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134100052","display_name":"Cong Huy Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Cong Huy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134168868","display_name":"Son Dinh Nguyen","orcid":"https://orcid.org/0000-0001-6910-5714"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Son Dinh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134138084","display_name":"Guanlin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Guanlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134107577","display_name":"Tuan Dung Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Tuan Dung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134165130","display_name":"Aditya Narayan Sankaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sankaran, Aditya Narayan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134101047","display_name":"Mai Huy Thong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thong, Mai Huy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134144002","display_name":"Thanh Trung Nguyen","orcid":"https://orcid.org/0009-0003-4164-9033"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Thanh Trung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134171002","display_name":"Mai Hong Son","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Son, Mai Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014176390","display_name":"Reza Farahbakhsh","orcid":"https://orcid.org/0000-0003-3219-3700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farahbakhsh, Reza","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123932065","display_name":"Phi Le Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Phi Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5107205316","display_name":"No\u00ebl Crespi","orcid":"https://orcid.org/0000-0003-2962-192X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Crespi, Noel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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":0.1225999966263771,"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":0.1225999966263771,"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/T10028","display_name":"Topic Modeling","score":0.11379999667406082,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.11299999803304672,"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/workflow","display_name":"Workflow","score":0.7462999820709229},{"id":"https://openalex.org/keywords/region-of-interest","display_name":"Region of interest","score":0.5432999730110168},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5214999914169312},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.49570000171661377},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4821000099182129},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.46299999952316284},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4417000114917755},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.4113999903202057}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7462999820709229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7427999973297119},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5794000029563904},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4821000099182129},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.46299999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4417000114917755},{"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/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29330000281333923},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2784999907016754},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.27639999985694885},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C3019060180","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automated method","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.18145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18145","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.18145","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.18145","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":"Preprint"},"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":{"Automated":[0],"medical":[1],"report":[2],"generation":[3],"for":[4,26,72],"3D":[5,65],"PET/CT":[6,66,78],"imaging":[7],"is":[8],"fundamentally":[9],"challenged":[10],"by":[11,59,111,172],"the":[12,38,62,93,106],"high-dimensional":[13],"nature":[14],"of":[15,22,41,45,95],"volumetric":[16],"data":[17],"and":[18,80,143,153,176,193,198],"a":[19,73,101,182],"critical":[20],"scarcity":[21],"annotated":[23,83],"datasets,":[24],"particularly":[25],"low-resource":[27,74],"languages.":[28],"Current":[29],"black-box":[30],"methods":[31],"map":[32],"whole":[33],"volumes":[34],"to":[35,48,91,116],"reports,":[36],"ignoring":[37],"clinical":[39,88,131,137,187,191],"workflow":[40,110],"analyzing":[42],"localized":[43,130],"Regions":[44],"Interest":[46],"(RoIs)":[47],"derive":[49],"diagnostic":[50,109],"conclusions.":[51],"In":[52],"this":[53,57,96],"paper,":[54],"we":[55,98,134],"bridge":[56],"gap":[58],"introducing":[60],"VietPET-RoI,":[61],"first":[63],"large-scale":[64],"dataset":[67,199],"with":[68,86],"fine-grained":[69],"RoI":[70,120,141,144,150],"annotation":[71],"language,":[75],"comprising":[76],"600":[77],"samples":[79],"1,960":[81],"manually":[82],"RoIs,":[84],"paired":[85],"corresponding":[87],"reports.":[89],"Furthermore,":[90],"demonstrate":[92],"utility":[94],"dataset,":[97],"propose":[99],"HiRRA,":[100],"novel":[102],"framework":[103,165],"that":[104,147,163],"mimics":[105],"professional":[107],"radiologist":[108],"employing":[112],"graph-based":[113],"relational":[114],"modules":[115],"capture":[117],"dependencies":[118],"between":[119],"attributes.":[121],"This":[122],"approach":[123],"shifts":[124],"from":[125],"global":[126],"pattern":[127],"matching":[128],"toward":[129],"findings.":[132],"Additionally,":[133],"introduce":[135],"new":[136],"evaluation":[138,161],"metrics,":[139,188],"namely":[140],"Coverage":[142],"Quality":[145],"Index,":[146],"measure":[148],"both":[149],"localization":[151],"accuracy":[152],"attribute":[154],"description":[155],"fidelity":[156],"using":[157],"LLM-based":[158],"extraction.":[159],"Extensive":[160],"demonstrates":[162],"our":[164],"achieves":[166],"SOTA":[167],"performance,":[168],"surpassing":[169],"existing":[170],"models":[171],"19.7%":[173],"in":[174,178,186],"BLEU":[175],"4.7%":[177],"ROUGE-L,":[179],"while":[180],"achieving":[181],"remarkable":[183],"45.8%":[184],"improvement":[185],"indicating":[189],"enhanced":[190],"reliability":[192],"reduced":[194],"hallucination.":[195],"Our":[196],"code":[197],"are":[200],"available":[201],"on":[202],"GitHub.":[203]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-22T00:00:00"}