{"id":"https://openalex.org/W6966668208","doi":"https://doi.org/10.48550/arxiv.2503.07094","title":"A Novel Ophthalmic Benchmark for Evaluating Multimodal Large Language Models with Fundus Photographs and OCT Images","display_name":"A Novel Ophthalmic Benchmark for Evaluating Multimodal Large Language Models with Fundus Photographs and OCT Images","publication_year":2025,"publication_date":"2025-03-10","ids":{"openalex":"https://openalex.org/W6966668208","doi":"https://doi.org/10.48550/arxiv.2503.07094"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2503.07094","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.07094","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.2503.07094","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Liang, Xiaoyi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liang, Xiaoyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bian, Mouxiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bian, Mouxiao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Moxin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Moxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Lihao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lihao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"He, Junjun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Junjun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xu, Jie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Li, Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Lin","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":true,"primary_topic":{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.8195000290870667,"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"}},"topics":[{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.8195000290870667,"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"}},{"id":"https://openalex.org/T10170","display_name":"Retinal Diseases and Treatments","score":0.06520000100135803,"subfield":{"id":"https://openalex.org/subfields/2731","display_name":"Ophthalmology"},"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/T10862","display_name":"AI in cancer detection","score":0.014100000262260437,"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/optical-coherence-tomography","display_name":"Optical coherence tomography","score":0.6171000003814697},{"id":"https://openalex.org/keywords/fundus","display_name":"Fundus (uterus)","score":0.5806000232696533},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5555999875068665},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.4268999993801117},{"id":"https://openalex.org/keywords/diabetic-retinopathy","display_name":"Diabetic retinopathy","score":0.41350001096725464},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3774999976158142},{"id":"https://openalex.org/keywords/medical-diagnosis","display_name":"Medical diagnosis","score":0.3596999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711999773979187},{"id":"https://openalex.org/C2778818243","wikidata":"https://www.wikidata.org/wiki/Q899552","display_name":"Optical coherence tomography","level":2,"score":0.6171000003814697},{"id":"https://openalex.org/C2776391266","wikidata":"https://www.wikidata.org/wiki/Q9612","display_name":"Fundus (uterus)","level":2,"score":0.5806000232696533},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194000005722046},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C2779829184","wikidata":"https://www.wikidata.org/wiki/Q631361","display_name":"Diabetic retinopathy","level":3,"score":0.41350001096725464},{"id":"https://openalex.org/C119767625","wikidata":"https://www.wikidata.org/wiki/Q618211","display_name":"Optometry","level":1,"score":0.3919000029563904},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C19527891","wikidata":"https://www.wikidata.org/wiki/Q1120908","display_name":"Medical physics","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35929998755455017},{"id":"https://openalex.org/C2776474195","wikidata":"https://www.wikidata.org/wiki/Q1144413","display_name":"Fundus photography","level":4,"score":0.34540000557899475},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3253999948501587},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C163763905","wikidata":"https://www.wikidata.org/wiki/Q17075943","display_name":"Precision medicine","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2503.07094","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.07094","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.2503.07094","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.07094","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,39],"recent":[1],"years,":[2],"large":[3,20],"language":[4,21],"models":[5,22,28,161,216],"(LLMs)":[6],"have":[7,42],"demonstrated":[8],"remarkable":[9],"potential":[10,225],"across":[11,156],"various":[12],"medical":[13,37],"applications.":[14],"Building":[15],"on":[16],"this":[17],"foundation,":[18],"multimodal":[19],"(MLLMs)":[23],"integrate":[24],"LLMs":[25,41],"with":[26,177],"visual":[27],"to":[29,67,110,204,226],"process":[30],"diverse":[31,94],"inputs,":[32],"including":[33,179],"clinical":[34,73],"data":[35],"and":[36,56,97,114,127,135,149,171,182,188,217,230],"images.":[38,81,138],"ophthalmology,":[40],"been":[43],"explored":[44],"for":[45,191],"analyzing":[46],"optical":[47],"coherence":[48],"tomography":[49],"(OCT)":[50],"reports,":[51],"assisting":[52],"in":[53,76,118,153,164,186],"disease":[54],"classification,":[55],"even":[57],"predicting":[58],"treatment":[59],"outcomes.":[60],"However,":[61],"existing":[62],"MLLM":[63],"benchmarks":[64,203],"often":[65],"fail":[66],"capture":[68],"the":[69,77,104,189,197],"complexities":[70],"of":[71,79,93,107,131,199,210],"real-world":[72],"practice,":[74],"particularly":[75],"analysis":[78],"OCT":[80,95,112,137],"Many":[82],"suffer":[83],"from":[84],"limitations":[85],"such":[86,167],"as":[87,168],"small":[88],"sample":[89],"sizes,":[90],"a":[91,140,206],"lack":[92],"datasets,":[96],"insufficient":[98],"expert":[99,128],"validation.":[100],"These":[101],"shortcomings":[102],"hinder":[103],"accurate":[105,208],"assessment":[106,209],"MLLMs'":[108,211],"ability":[109],"interpret":[111],"scans":[113],"their":[115,219,224],"broader":[116],"applicability":[117],"ophthalmology.":[119],"Our":[120,194],"dataset,":[121],"curated":[122],"through":[123],"rigorous":[124],"quality":[125],"control":[126],"annotation,":[129],"consists":[130],"439":[132],"fundus":[133],"images":[134],"75":[136],"Using":[139],"standardized":[141],"API-based":[142],"framework,":[143],"we":[144,221],"assessed":[145],"seven":[146],"mainstream":[147],"MLLMs":[148],"observed":[150],"significant":[151],"variability":[152],"diagnostic":[154],"accuracy":[155],"different":[157],"diseases.":[158],"While":[159],"some":[160],"performed":[162],"well":[163],"diagnosing":[165],"conditions":[166],"diabetic":[169],"retinopathy":[170],"age-related":[172],"macular":[173],"degeneration,":[174],"they":[175],"struggled":[176],"others,":[178],"choroidal":[180],"neovascularization":[181],"myopia,":[183],"highlighting":[184],"inconsistencies":[185],"performance":[187],"need":[190],"further":[192],"refinement.":[193],"findings":[195],"emphasize":[196],"importance":[198],"developing":[200],"clinically":[201],"relevant":[202],"provide":[205],"more":[207],"capabilities.":[212],"By":[213],"refining":[214],"these":[215],"expanding":[218],"scope,":[220],"can":[222],"enhance":[223],"transform":[227],"ophthalmic":[228],"diagnosis":[229],"treatment.":[231]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}