{"id":"https://openalex.org/W4402915770","doi":"https://doi.org/10.1109/icip51287.2024.10647584","title":"M3T: Multi-Modal Medical Transformer To Bridge Clinical Context With Visual Insights For Retinal Image Medical Description Generation","display_name":"M3T: Multi-Modal Medical Transformer To Bridge Clinical Context With Visual Insights For Retinal Image Medical Description Generation","publication_year":2024,"publication_date":"2024-09-27","ids":{"openalex":"https://openalex.org/W4402915770","doi":"https://doi.org/10.1109/icip51287.2024.10647584"},"language":"en","primary_location":{"id":"doi:10.1109/icip51287.2024.10647584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"article","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/A5027212073","display_name":"Nagur Shareef Shaik","orcid":"https://orcid.org/0000-0002-2432-7409"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nagur Shareef Shaik","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,GA,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,GA,United States","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015473698","display_name":"Teja Krishna Cherukuri","orcid":"https://orcid.org/0000-0002-4952-728X"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teja Krishna Cherukuri","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,GA,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,GA,United States","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068927047","display_name":"Dong Hye Ye","orcid":"https://orcid.org/0000-0002-9186-4095"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Hye Ye","raw_affiliation_strings":["Georgia State University,Department of Computer Science,Atlanta,GA,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia State University,Department of Computer Science,Atlanta,GA,United States","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027212073"],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":null,"apc_paid":null,"fwci":1.9167,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8642125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3037","last_page":"3043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11438","display_name":"Retinal Imaging and Analysis","score":0.9850000143051147,"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":0.9850000143051147,"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/T10862","display_name":"AI in cancer detection","score":0.9498999714851379,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9072999954223633,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.67689049243927},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5757741332054138},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5009291172027588},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4317573308944702},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4269565939903259},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4139874577522278},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15037819743156433},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.11087068915367126},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1102539598941803},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.0916580855846405},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06775709986686707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67689049243927},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5757741332054138},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5009291172027588},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4317573308944702},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4269565939903259},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4139874577522278},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15037819743156433},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.11087068915367126},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1102539598941803},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0916580855846405},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06775709986686707},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip51287.2024.10647584","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip51287.2024.10647584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1902237438","https://openalex.org/W2127322315","https://openalex.org/W3034781633","https://openalex.org/W3119639728","https://openalex.org/W3124433782","https://openalex.org/W3194346615","https://openalex.org/W3196479518","https://openalex.org/W3206004033","https://openalex.org/W4200226120","https://openalex.org/W4213210229","https://openalex.org/W4220862900","https://openalex.org/W4296139711","https://openalex.org/W4319300591","https://openalex.org/W4385245566","https://openalex.org/W4386076127","https://openalex.org/W4391873005","https://openalex.org/W6763643401","https://openalex.org/W6791353385"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Automated":[0],"retinal":[1,22,90],"image":[2,23],"medical":[3,10,87],"description":[4],"generation":[5,82],"is":[6],"crucial":[7],"for":[8,89],"streamlining":[9],"diagnosis":[11],"and":[12,31,75,85],"treatment":[13],"planning.":[14],"Existing":[15],"challenges":[16],"include":[17],"the":[18,32,45,81,95,99,115],"reliance":[19],"on":[20,66,94],"learned":[21],"representations,":[24],"difficulties":[25],"in":[26,37,103,112],"handling":[27],"multiple":[28],"imaging":[29],"modalities,":[30,79],"lack":[33],"of":[34,83,101],"clinical":[35],"context":[36],"visual":[38,57],"representations.":[39],"Addressing":[40],"these":[41],"issues,":[42],"we":[43],"propose":[44],"Multi-Modal":[46],"Medical":[47],"Transformer":[48],"(M3T),":[49],"a":[50,108],"novel":[51],"deep":[52],"learning":[53],"architecture":[54],"that":[55],"integrates":[56],"representations":[58],"with":[59],"diagnostic":[60],"keywords.":[61],"Unlike":[62],"previous":[63],"studies":[64,93],"focusing":[65],"specific":[67],"aspects,":[68],"our":[69],"approach":[70],"efficiently":[71],"learns":[72],"contextual":[73],"information":[74],"semantics":[76],"from":[77],"both":[78],"enabling":[80],"precise":[84],"coherent":[86],"descriptions":[88],"images.":[91],"Experimental":[92],"DeepEyeNet":[96],"dataset":[97],"validate":[98],"success":[100],"M3T":[102],"meeting":[104],"ophthalmologists\u2019":[105],"standards,":[106],"demonstrating":[107],"substantial":[109],"13.5%":[110],"improvement":[111],"BLEU@4":[113],"over":[114],"best-performing":[116],"baseline":[117],"model.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-26T08:31:28.666265","created_date":"2025-10-10T00:00:00"}