{"id":"https://openalex.org/W7125893709","doi":"https://doi.org/10.1109/smc58881.2025.11343574","title":"MambaXray-CTL: Multi-Stage Contrastive Training for Medical Report Generation with a Mamba-Based Multi-Modal Large Model","display_name":"MambaXray-CTL: Multi-Stage Contrastive Training for Medical Report Generation with a Mamba-Based Multi-Modal Large Model","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125893709","doi":"https://doi.org/10.1109/smc58881.2025.11343574"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5121139768","display_name":"Wenbin Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbin Feng","raw_affiliation_strings":["Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075439339","display_name":"You L\u00fc","orcid":"https://orcid.org/0000-0002-7524-4179"},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Lu","raw_affiliation_strings":["Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124077529","display_name":"Xiaoqing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaoqing Li","raw_affiliation_strings":["National University of Singapore,Yong Loo Lin School of Medicine,Department of Surgery,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Yong Loo Lin School of Medicine,Department of Surgery,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124087881","display_name":"Shijie Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shijie Shi","raw_affiliation_strings":["Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044827259","display_name":"Yingjian Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjian Qi","raw_affiliation_strings":["Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Technology University,College of Big Data and Internet,Shenzhen,China","institution_ids":["https://openalex.org/I4210152380"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"424","last_page":"429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9391999840736389,"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":0.9391999840736389,"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":0.01209999993443489,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.008700000122189522,"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/workflow","display_name":"Workflow","score":0.6881999969482422},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.4977000057697296},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45329999923706055},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.3944000005722046},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.392300009727478},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3813999891281128},{"id":"https://openalex.org/keywords/medical-imaging","display_name":"Medical imaging","score":0.36480000615119934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7504000067710876},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6539000272750854},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5170000195503235},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4977000057697296},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3813999891281128},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.36480000615119934},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3379000127315521},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3287999927997589},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2678999900817871},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343574","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343574","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320325571","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2152772232","https://openalex.org/W3104609094","https://openalex.org/W3174714208","https://openalex.org/W3181252431","https://openalex.org/W4283821415","https://openalex.org/W4285531589","https://openalex.org/W4312420429","https://openalex.org/W4385570515","https://openalex.org/W4386076127","https://openalex.org/W4386076536","https://openalex.org/W4386573963","https://openalex.org/W4388713229","https://openalex.org/W4393159390","https://openalex.org/W4393160811","https://openalex.org/W4399527328","https://openalex.org/W4403071749","https://openalex.org/W4403088661","https://openalex.org/W4403089244","https://openalex.org/W4403089498","https://openalex.org/W4413147664"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,14,28,163],"artificial":[4],"intelligence":[5],"(AI)":[6],"is":[7],"revolutionizing":[8],"radiology,":[9],"particularly":[10,143],"in":[11,42,57,140,170],"the":[12,21,25,123,161],"automation":[13],"medical":[15,44,77],"report":[16,78],"generation.":[17],"AI-driven":[18],"systems":[19,176],"offer":[20],"potential":[22],"to":[23,135,153],"alleviate":[24],"increasing":[26],"workload":[27],"radiologists":[29],"while":[30,116,147],"improving":[31],"diagnostic":[32],"accuracy,":[33],"consistency,":[34],"and":[35,55,63,105,126,145,167,173],"overall":[36],"workflow":[37],"efficiency.":[38,119],"Despite":[39],"significant":[40],"progress":[41],"multi-modal":[43],"image":[45],"captioning,":[46],"existing":[47],"approaches":[48],"often":[49],"suffer":[50],"from":[51],"high":[52],"computational":[53,118],"costs":[54],"limitations":[56],"modeling":[58],"long-range":[59],"dependencies":[60],"between":[61],"visual":[62],"textual":[64],"features.":[65],"To":[66],"address":[67],"these":[68],"challenges,":[69],"we":[70],"propose":[71],"MambaXray-CTL,":[72],"a":[73,82,87,96],"novel":[74],"framework":[75],"for":[76,177],"generation":[79],"that":[80,130],"integrates":[81],"Mamba-based":[83],"vision":[84],"backbone":[85],"with":[86,108],"large":[88],"language":[89],"model":[90,111],"(LLM)":[91],"text":[92],"decoder.":[93],"By":[94],"leveraging":[95],"multi-stage":[97],"training":[98],"strategy\u2014including":[99],"autoregressive":[100],"pretraining,":[101],"image-text":[102],"contrastive":[103,109,168],"learning,":[104],"supervised":[106],"fine-tuning":[107],"regularization\u2014our":[110],"achieves":[112,132],"precise":[113],"visual-textual":[114],"alignment":[115],"maintaining":[117],"Experimental":[120],"results":[121],"on":[122],"IU":[124],"X-ray":[125],"CheXpertPlus":[127],"datasets":[128],"demonstrate":[129],"MambaXray-CTL":[131],"performance":[133],"comparable":[134],"or":[136],"surpassing":[137],"state-of-the-art":[138],"methods":[139],"key":[141],"metrics,":[142],"BLEU-4":[144],"CIDEr,":[146],"significantly":[148],"reducing":[149],"inference":[150],"cost":[151],"compared":[152],"Vision":[154],"Transformer":[155],"(ViT)-based":[156],"architectures.":[157],"These":[158],"findings":[159],"highlight":[160],"promise":[162],"state":[164],"space":[165],"models":[166],"learning":[169],"building":[171],"scalable":[172],"effective":[174],"vision-language":[175],"real-world":[178],"clinical":[179],"deployment.":[180]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}