{"id":"https://openalex.org/W7126026869","doi":"https://doi.org/10.1109/bibm66473.2025.11356577","title":"Reflect Then Reason: Iterative Reflection with Soft Reasoning Feature Enhancement for Medical Visual Question Answering","display_name":"Reflect Then Reason: Iterative Reflection with Soft Reasoning Feature Enhancement for Medical Visual Question Answering","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126026869","doi":"https://doi.org/10.1109/bibm66473.2025.11356577"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356577","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 Bioinformatics and Biomedicine (BIBM)","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/A5077023555","display_name":"Haoyang Chen","orcid":"https://orcid.org/0009-0004-4796-4218"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haoyang Chen","raw_affiliation_strings":["School of Computer Science, Nanjing University,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University,Nanjing,China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5077023555"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71988659,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2044","last_page":"2050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9943000078201294,"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":0.9943000078201294,"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":0.0012000000569969416,"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":0.00039999998989515007,"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/question-answering","display_name":"Question answering","score":0.7010999917984009},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.7010999917984009},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6942999958992004},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6096000075340271},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45739999413490295},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.397599995136261},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.3847000002861023},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.38089999556541443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347000241279602},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.7010999917984009},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6942999958992004},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6096000075340271},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849000215530396},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.397599995136261},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.36250001192092896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34389999508857727},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356577","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356577","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 Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8436071276664734,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2152772232","https://openalex.org/W2901466771","https://openalex.org/W3165058054","https://openalex.org/W4400128031","https://openalex.org/W4400376323","https://openalex.org/W4402774103","https://openalex.org/W4403054204","https://openalex.org/W4404509535","https://openalex.org/W4404782250","https://openalex.org/W4404782528","https://openalex.org/W4404783482","https://openalex.org/W4406260314","https://openalex.org/W4411120023","https://openalex.org/W4411120331","https://openalex.org/W4412944734","https://openalex.org/W4413147813","https://openalex.org/W4414314487"],"related_works":[],"abstract_inverted_index":{"The":[0],"medical":[1,15,79,203],"visual":[2,156],"question":[3],"answering":[4],"(Med-VQA)":[5],"assistant":[6],"shows":[7],"significant":[8],"practical":[9],"value":[10],"in":[11,54,78],"scenarios":[12],"such":[13],"as":[14],"education":[16],"and":[17,46,95,114,142,155,170,197],"public":[18],"health":[19],"services.":[20],"However,":[21],"current":[22],"studies":[23],"generally":[24],"rely":[25],"on":[26,88,111,173],"external":[27],"knowledge":[28],"bases":[29],"or":[30],"dataset":[31,167],"specific":[32],"fine-tuning":[33],"to":[34,42,49,92],"improve":[35],"answer":[36,118],"accuracy,":[37],"while":[38],"giving":[39],"insufficient":[40],"attention":[41],"leveraging":[43],"iterative":[44],"reflection":[45,151,171],"internal":[47],"features":[48,133],"stimulate":[50],"intrinsic":[51],"reasoning":[52,72,109,192],"capabilities":[53],"vision":[55,75],"language":[56,76],"models":[57,77,179],"for":[58,202],"Med-VQA.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"an":[65],"Analysis-Reflection":[66],"two-stage":[67],"framework,":[68],"which":[69],"boosts":[70],"the":[71,85,89,101,104,112,116,122,135,146,150,186,190,195,198],"ability":[73],"of":[74,107,200],"VQA":[80],"through":[81],"self-iterative":[82],"reflection.":[83],"First,":[84],"model":[86,102],"concentrates":[87],"image-question":[90],"pair":[91],"analyze":[93],"information":[94],"generate":[96],"a":[97,125,161],"preliminary":[98],"answer.":[99],"Then,":[100],"conducts":[103],"second":[105,147],"round":[106],"reflective":[108],"based":[110,172],"context,":[113],"outputs":[115],"final":[117],"with":[119,152,168,177],"explanations.":[120],"Importantly,":[121],"framework":[123,187],"incorporates":[124],"Soft":[126],"Reasoning":[127],"Feature":[128],"Enhancement":[129],"Module(SRFE)":[130],"that":[131,185],"distills":[132],"from":[134],"first":[136],"stage's":[137],"hidden":[138],"states":[139],"via":[140],"crossattention,":[141],"feeds":[143],"them":[144],"into":[145],"stage,":[148],"enriching":[149],"analysis-oriented":[153],"semantic":[154],"information.":[157],"We":[158],"also":[159],"build":[160],"<tex":[162],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[163],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathbf{1":[164],"4":[165],"k}$</tex>-sample":[166],"analysis":[169],"various":[174],"open-source":[175],"datasets":[176],"advanced":[178],"like":[180],"GPT-4o.":[181],"Experimental":[182],"results":[183],"demonstrate":[184],"effectively":[188],"enhances":[189],"model's":[191],"ability,":[193],"improving":[194],"accuracy":[196],"quality":[199],"explanations":[201],"VQA.":[204]},"counts_by_year":[],"updated_date":"2026-02-01T03:34:12.195049","created_date":"2026-01-30T00:00:00"}