{"id":"https://openalex.org/W4392309196","doi":"https://doi.org/10.1109/jbhi.2024.3371894","title":"Memory Guided Transformer With Spatio-Semantic Visual Extractor for Medical Report Generation","display_name":"Memory Guided Transformer With Spatio-Semantic Visual Extractor for Medical Report Generation","publication_year":2024,"publication_date":"2024-02-29","ids":{"openalex":"https://openalex.org/W4392309196","doi":"https://doi.org/10.1109/jbhi.2024.3371894","pmid":"https://pubmed.ncbi.nlm.nih.gov/38421843"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2024.3371894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2024.3371894","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5036123482","display_name":"Peketi Divya","orcid":"https://orcid.org/0000-0001-9345-8931"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Peketi Divya","raw_affiliation_strings":["Department of Artificial Intelligence, Indian Institute of Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058255642","display_name":"Sravani Yenduri","orcid":"https://orcid.org/0000-0001-6651-4360"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yenduri Sravani","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044985749","display_name":"Chalavadi Vishnu","orcid":"https://orcid.org/0000-0001-9184-3545"},"institutions":[{"id":"https://openalex.org/I4210109292","display_name":"Indian Institute of Technology Tirupati","ror":"https://ror.org/01xtkxh20","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210109292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chalavadi Vishnu","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Tirupati, Tirupati, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Tirupati, Tirupati, India","institution_ids":["https://openalex.org/I4210109292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012566120","display_name":"C. Krishna Mohan","orcid":"https://orcid.org/0000-0002-7316-0836"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Krishna Mohan","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044216245","display_name":"Yen\u2010Wei Chen","orcid":"https://orcid.org/0000-0002-5952-0188"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yen Wei Chen","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Kyoto, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036123482"],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":9.4523,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.98688372,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"28","issue":"5","first_page":"3079","last_page":"3089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994000196456909,"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":0.9994000196456909,"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":0.996999979019165,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9887999892234802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7244547009468079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4778156578540802},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4388638734817505},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34950780868530273},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34810715913772583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244547009468079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4778156578540802},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4388638734817505},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34950780868530273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34810715913772583}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011873","descriptor_name":"Radiology Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011873","descriptor_name":"Radiology Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011873","descriptor_name":"Radiology Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011873","descriptor_name":"Radiology Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011873","descriptor_name":"Radiology Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2024.3371894","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2024.3371894","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:38421843","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38421843","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1905882502","https://openalex.org/W1915485278","https://openalex.org/W1987835821","https://openalex.org/W2062955551","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2124386111","https://openalex.org/W2152772232","https://openalex.org/W2194775991","https://openalex.org/W2302086703","https://openalex.org/W2549599535","https://openalex.org/W2565639579","https://openalex.org/W2575842049","https://openalex.org/W2601564443","https://openalex.org/W2605045867","https://openalex.org/W2745461083","https://openalex.org/W2754927243","https://openalex.org/W2770165365","https://openalex.org/W2776402438","https://openalex.org/W2798748179","https://openalex.org/W2949167374","https://openalex.org/W2950635152","https://openalex.org/W2963084599","https://openalex.org/W2963815618","https://openalex.org/W2963893037","https://openalex.org/W2963952323","https://openalex.org/W2964546107","https://openalex.org/W2966926453","https://openalex.org/W2978125519","https://openalex.org/W2979861699","https://openalex.org/W2984138079","https://openalex.org/W2986670728","https://openalex.org/W2995225687","https://openalex.org/W2997704374","https://openalex.org/W3027117989","https://openalex.org/W3034655362","https://openalex.org/W3035284526","https://openalex.org/W3083569822","https://openalex.org/W3093220398","https://openalex.org/W3094502228","https://openalex.org/W3098325931","https://openalex.org/W3104027471","https://openalex.org/W3104609094","https://openalex.org/W3173688449","https://openalex.org/W3174714208","https://openalex.org/W3177048142","https://openalex.org/W3181252431","https://openalex.org/W3208624098","https://openalex.org/W4281729070","https://openalex.org/W4287899420","https://openalex.org/W4293479414","https://openalex.org/W4311257611","https://openalex.org/W4311511277","https://openalex.org/W4385245566","https://openalex.org/W4388639270","https://openalex.org/W6618372016","https://openalex.org/W6620707391","https://openalex.org/W6677328238","https://openalex.org/W6682631176","https://openalex.org/W6683590716","https://openalex.org/W6751711410","https://openalex.org/W6766222867","https://openalex.org/W6772105051","https://openalex.org/W6784333009"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","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":{"Medicalimaging-based":[0],"report":[1,31,185],"writing":[2],"for":[3],"effective":[4],"diagnosis":[5],"in":[6,36,112,132],"radiology":[7,85,103,171,184],"is":[8,71],"time-consuming":[9],"and":[10,24,62,77,99,139,190],"can":[11],"be":[12],"error-prone":[13],"by":[14],"inexperienced":[15],"radiologists.":[16],"Automatic":[17],"reporting":[18],"helps":[19],"radiologists":[20],"avoid":[21],"missed":[22],"diagnoses":[23],"saves":[25],"valuable":[26],"time.":[27],"Recently,":[28],"transformer-based":[29],"medical":[30],"generation":[32],"has":[33],"become":[34],"prominent":[35],"capturing":[37],"long-term":[38],"dependencies":[39],"of":[40,55,65,84,110,125,147,170,175],"sequential":[41],"data":[42],"with":[43],"its":[44],"attention":[45],"mechanism.":[46],"Nevertheless,":[47],"input":[48],"features":[49],"obtained":[50],"from":[51,102],"traditional":[52],"visual":[53,92],"extractor":[54,93],"conventional":[56],"transformers":[57],"do":[58],"not":[59,79],"capture":[60,74,96],"spatial":[61,98],"semantic":[63,100,141,158],"information":[64,101],"an":[66],"image.":[67],"So,":[68],"the":[69,122,144],"transformer":[70],"unable":[72],"to":[73,95,134,154,166],"fine-grained":[75,168],"details":[76,169],"may":[78],"produce":[80],"detailed":[81],"descriptive":[82],"reports":[83],"images.":[86,104,172],"Therefore,":[87],"we":[88,106],"propose":[89],"a":[90],"spatio-semantic":[91],"(SSVE)":[94],"multi-scale":[97,157],"Here,":[105],"incorporate":[107],"two":[108,183],"types":[109],"networks":[111],"ResNet":[113,126],"101":[114,127],"backbone":[115,148],"architecture,":[116],"i.e.":[117],"(i)":[118],"deformable":[119,130],"network":[120,142,162],"at":[121,143],"intermediate":[123],"layer":[124,146],"that":[128],"utilizes":[129],"convolutions":[131,153],"order":[133],"obtain":[135],"spatially":[136],"invariant":[137],"features,":[138],"(ii)":[140],"final":[145],"architecture":[149],"which":[150],"uses":[151],"dilated":[152],"extract":[155],"rich":[156],"information.":[159],"Further,":[160],"these":[161],"representations":[163],"are":[164],"fused":[165],"encode":[167],"The":[173],"performance":[174],"our":[176],"proposed":[177],"model":[178],"outperforms":[179],"existing":[180],"works":[181],"on":[182],"datasets,":[186],"i.e.,":[187],"IU":[188],"X-ray":[189],"MIMIC-CXR.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":20}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}