{"id":"https://openalex.org/W7171434890","doi":"https://doi.org/10.48550/arxiv.2607.22293","title":"RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understanding","display_name":"RadSight: Towards Perceptually Reliable Multimodal Radiology Image Understanding","publication_year":2026,"publication_date":"2026-07-24","ids":{"openalex":"https://openalex.org/W7171434890","doi":"https://doi.org/10.48550/arxiv.2607.22293"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.22293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.22293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.22293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113205793","display_name":"JianQin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jianqin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143726640","display_name":"Weiwei Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Weiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143673583","display_name":"Wanxing Chang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Wanxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143699426","display_name":"Ruifeng Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Ruifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143727931","display_name":"Bowen Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025166983","display_name":"Zhilin Zheng","orcid":"https://orcid.org/0000-0002-2439-9162"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Zhilin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143704323","display_name":"Xianjie Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xianjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143740235","display_name":"Ling Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143695762","display_name":"Peng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143675470","display_name":"Jianpeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianpeng","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":0.38440001010894775,"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":0.38440001010894775,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.195700004696846,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.11050000041723251,"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/medical-imaging","display_name":"Medical imaging","score":0.522599995136261},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.42179998755455017},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.41589999198913574},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.40130001306533813},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3792000114917755},{"id":"https://openalex.org/keywords/traverse","display_name":"Traverse","score":0.3732999861240387},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3643999993801117},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.34689998626708984},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.34209999442100525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6944000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5963000059127808},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.42179998755455017},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C176809094","wikidata":"https://www.wikidata.org/wiki/Q15401496","display_name":"Traverse","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36730000376701355},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.30660000443458557},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C44210515","wikidata":"https://www.wikidata.org/wiki/Q16968978","display_name":"Bespoke","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.22293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.22293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.22293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.22293","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.8151945471763611,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Medical":[0],"multimodal":[1],"large":[2],"language":[3],"models":[4],"(MLLMs)":[5],"are":[6],"increasingly":[7],"expected":[8],"to":[9,41,94,110],"perform":[10],"complex":[11],"image":[12,161],"understanding":[13,162],"tasks,":[14],"yet":[15],"their":[16],"reliability":[17],"is":[18,124,180,233],"often":[19],"compromised":[20],"by":[21,137],"frequent":[22],"errors":[23],"in":[24,114,126,132,208],"visual":[25,43,116,134,171,231],"interpretation.":[26,177],"To":[27],"systematically":[28],"trace":[29],"these":[30],"failures,":[31],"we":[32,139],"traverse":[33],"the":[34,92,97,120],"hierarchy":[35],"from":[36],"high-level":[37],"clinical":[38,112,173,212,239],"tasks":[39],"down":[40],"fundamental":[42],"perception.":[44,135],"We":[45],"therefore":[46],"introduce":[47],"Perception-Bench,":[48,193],"a":[49,127,142,147,164,234],"large-scale":[50],"benchmark":[51],"comprising":[52],"1.13":[53],"million":[54,185],"samples":[55],"that":[56,88,119,152,228],"assesses":[57],"medical":[58,160,224],"MLLMs":[59,90,198],"across":[60,199],"six":[61,201],"dimensions:":[62],"attribute":[63],"judgment,":[64],"spatial":[65,67,156,209],"grounding,":[66],"understanding,":[68],"disease":[69],"prediction,":[70],"anomaly":[71],"detection,":[72],"and":[73,79,106,175,211,222,242],"report":[74],"generation,":[75],"spanning":[76],"both":[77],"2D":[78,221],"3D":[80,223],"radiology":[81],"images.":[82],"Our":[83],"analysis":[84],"on":[85,182,219],"Perception-Bench":[86],"reveals":[87,118],"existing":[89,197],"lack":[91],"ability":[93],"capture":[95],"even":[96],"most":[98],"basic":[99],"lesion":[100],"attributes,":[101],"such":[102],"as":[103,163],"location,":[104],"size,":[105],"density.":[107],"This":[108],"inability":[109],"ground":[111],"outputs":[113],"primary":[115],"evidence":[117],"models'":[121],"diagnostic":[122,176],"unreliability":[123],"rooted":[125],"critical":[128,235],"but":[129],"overlooked":[130],"bottleneck":[131],"low-level":[133,230],"Motivated":[136],"this,":[138],"propose":[140],"RadSight,":[141],"perception-driven":[143],"MLLM":[144],"built":[145],"upon":[146],"dual":[148],"2D/3D":[149],"encoder":[150],"architecture":[151],"preserves":[153],"native":[154],"imaging":[155],"structures.":[157],"RadSight":[158,194],"formulates":[159],"four-stage":[165],"progressive":[166,189],"process:":[167],"visual-language":[168],"alignment,":[169],"fine-grained":[170],"perception,":[172],"diagnosis,":[174],"The":[178],"model":[179,243],"trained":[181],"an":[183],"8.37":[184],"perception-oriented":[186],"corpus":[187],"using":[188],"curriculum":[190],"learning.":[191],"On":[192],"consistently":[195],"outperforms":[196],"all":[200],"evaluation":[202],"dimensions,":[203],"with":[204],"particularly":[205],"strong":[206],"gains":[207],"grounding":[210],"diagnosis.":[213],"It":[214],"also":[215],"achieves":[216],"consistent":[217],"improvements":[218],"public":[220],"benchmarks,":[225],"further":[226],"demonstrating":[227],"robust":[229],"perception":[232],"foundation":[236],"for":[237],"reliable":[238],"understanding.":[240],"Code":[241],"will":[244],"be":[245],"publicly":[246],"available.":[247]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-28T00:00:00"}