{"id":"https://openalex.org/W4415345095","doi":"https://doi.org/10.1145/3774521.3774546","title":"ChestGPT: Integrating Large Language Models and Vision Transformers for Disease Detection and Localization in Chest X-Rays","display_name":"ChestGPT: Integrating Large Language Models and Vision Transformers for Disease Detection and Localization in Chest X-Rays","publication_year":2025,"publication_date":"2025-12-17","ids":{"openalex":"https://openalex.org/W4415345095","doi":"https://doi.org/10.1145/3774521.3774546"},"language":"en","primary_location":{"id":"doi:10.1145/3774521.3774546","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774546","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774521.3774546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045267281","display_name":"Shehroz S. Khan","orcid":"https://orcid.org/0000-0002-1195-4999"},"institutions":[{"id":"https://openalex.org/I2803079837","display_name":"American University of the Middle East","ror":"https://ror.org/02gqgne03","country_code":"KW","type":"education","lineage":["https://openalex.org/I2803079837"]}],"countries":["KW"],"is_corresponding":false,"raw_author_name":"Shehroz S. Khan","raw_affiliation_strings":["College of Engineering and Technology, American University of the Middle East, Kuwait, Egaila, 54200, Kuwait"],"raw_orcid":"https://orcid.org/0000-0002-1195-4999","affiliations":[{"raw_affiliation_string":"College of Engineering and Technology, American University of the Middle East, Kuwait, Egaila, 54200, Kuwait","institution_ids":["https://openalex.org/I2803079837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120061374","display_name":"Petar Przulj","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Petar Przulj","raw_affiliation_strings":["University of Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0000-5326-8404","affiliations":[{"raw_affiliation_string":"University of Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042544444","display_name":"Ahmed Ashraf","orcid":"https://orcid.org/0000-0002-0463-4102"},"institutions":[{"id":"https://openalex.org/I46247651","display_name":"University of Manitoba","ror":"https://ror.org/02gfys938","country_code":"CA","type":"education","lineage":["https://openalex.org/I46247651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed Ashraf","raw_affiliation_strings":["University of Manitoba, Winnipeg, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0463-4102","affiliations":[{"raw_affiliation_string":"University of Manitoba, Winnipeg, Canada","institution_ids":["https://openalex.org/I46247651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101452473","display_name":"Ali Abedi","orcid":"https://orcid.org/0000-0002-7393-1362"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ali Abedi","raw_affiliation_strings":["University of Toronto, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-7393-1362","affiliations":[{"raw_affiliation_string":"University of Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51068436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9950000047683716,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9950000047683716,"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/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.9807000160217285,"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/T10202","display_name":"Lung Cancer Diagnosis and Treatment","score":0.9391000270843506,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"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/workload","display_name":"Workload","score":0.6312000155448914},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4336000084877014},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.43220001459121704},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.382099986076355},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.36899998784065247},{"id":"https://openalex.org/keywords/musculoskeletal-disease","display_name":"Musculoskeletal disease","score":0.3495999872684479},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.34689998626708984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6628000140190125},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6312000155448914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4909999966621399},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4336000084877014},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.43220001459121704},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.382099986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C3018805424","wikidata":"https://www.wikidata.org/wiki/Q4116663","display_name":"Musculoskeletal disease","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32510000467300415},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.323199987411499},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29760000109672546},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774521.3774546","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774546","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.03739","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.03739","pdf_url":"https://arxiv.org/pdf/2507.03739","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.03739","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.03739","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3774521.3774546","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774521.3774546","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Sixteen Indian Conference on Computer Vision, Graphics and Image Processing","raw_type":"proceedings-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":{"The":[0,120,157],"global":[1,162],"demand":[2],"for":[3,63,200],"radiologists":[4,21,202],"is":[5,22],"increasing":[6],"rapidly":[7],"due":[8],"to":[9,37,108,151,197,225],"a":[10,82,95],"growing":[11],"reliance":[12],"on":[13,166],"medical":[14],"imaging":[15],"services,":[16],"while":[17],"the":[18,60,100,104,136,167,185],"supply":[19],"of":[20,114,143,174,187,223],"not":[23],"keeping":[24],"pace.":[25],"Advances":[26],"in":[27,116,195],"computer":[28],"vision":[29,71],"and":[30,45,65,111,141,155,176,221],"image":[31],"processing":[32],"technologies":[33],"present":[34,93],"significant":[35],"potential":[36],"address":[38],"this":[39,90,206],"gap":[40],"by":[41,180,217],"enhancing":[42],"radiologists'":[43,215],"capabilities":[44],"improving":[46],"diagnostic":[47,228],"accuracy.":[48],"Large":[49],"language":[50],"models":[51],"(LLMs),":[52],"particularly":[53],"generative":[54],"pre-trained":[55],"transformers":[56,72],"(GPTs),":[57],"have":[58,74],"become":[59],"primary":[61],"approach":[62,146],"understanding":[64],"generating":[66,181],"textual":[67],"data.":[68],"In":[69,89],"parallel,":[70],"(ViTs)":[73],"proven":[75],"effective":[76],"at":[77],"converting":[78],"visual":[79],"data":[80],"into":[81,125,135],"format":[83],"that":[84,98,212],"LLMs":[85],"can":[86,213],"process":[87],"efficiently.":[88],"paper,":[91],"we":[92],"ChestGPT,":[94],"deep-learning":[96],"framework":[97,207],"integrates":[99],"EVA":[101],"ViT":[102,121],"with":[103,132,170],"Llama":[105],"2":[106],"LLM":[107],"classify":[109],"diseases":[110],"localize":[112],"regions":[113,186,222],"interest":[115,224],"chest":[117],"X-ray":[118,123],"images.":[119],"converts":[122],"images":[124],"tokens,":[126],"which":[127],"are":[128],"then":[129],"fed,":[130],"together":[131],"engineered":[133],"prompts,":[134,194,199],"LLM,":[137],"enabling":[138],"joint":[139],"classification":[140,164],"localization":[142],"diseases.":[144],"This":[145],"incorporates":[147],"transfer":[148],"learning":[149],"techniques":[150],"enhance":[152],"both":[153],"explainability":[154],"performance.":[156],"proposed":[158],"method":[159],"achieved":[160],"strong":[161],"disease":[163],"performance":[165],"VinDr-CXR":[168],"dataset,":[169],"an":[171,209],"F1":[172],"score":[173],"0.76,":[175],"successfully":[177],"localized":[178],"pathologies":[179],"bounding":[182],"boxes":[183],"around":[184],"interest.":[188],"We":[189],"also":[190],"outline":[191],"several":[192],"task-specific":[193],"addition":[196],"general-purpose":[198],"scenarios":[201],"might":[203],"encounter.":[204],"Overall,":[205],"offers":[208],"assistive":[210],"tool":[211],"lighten":[214],"workload":[216],"providing":[218],"preliminary":[219],"findings":[220],"facilitate":[226],"their":[227],"process.":[229]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-20T00:00:00"}