{"id":"https://openalex.org/W7152408444","doi":"https://doi.org/10.3390/jimaging12040162","title":"D2MNet: Difference-Aware Decoupling and Multi-Prompt Learning for Medical Difference Visual Question Answering","display_name":"D2MNet: Difference-Aware Decoupling and Multi-Prompt Learning for Medical Difference Visual Question Answering","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152408444","doi":"https://doi.org/10.3390/jimaging12040162","pmid":"https://pubmed.ncbi.nlm.nih.gov/42042505"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging12040162","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12040162","pdf_url":"https://www.mdpi.com/2313-433X/12/4/162/pdf?version=1775791373","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/12/4/162/pdf?version=1775791373","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133297680","display_name":"Lingge Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I154893126","display_name":"Guizhou Normal University","ror":"https://ror.org/02x1pa065","country_code":"CN","type":"education","lineage":["https://openalex.org/I154893126"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingge Lai","raw_affiliation_strings":["School of Big Data and Computer Science, Guizhou Normal University, Guiyang 550025, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Big Data and Computer Science, Guizhou Normal University, Guiyang 550025, China","institution_ids":["https://openalex.org/I154893126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008194585","display_name":"Weihua Ou","orcid":null},"institutions":[{"id":"https://openalex.org/I154893126","display_name":"Guizhou Normal University","ror":"https://ror.org/02x1pa065","country_code":"CN","type":"education","lineage":["https://openalex.org/I154893126"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weihua Ou","raw_affiliation_strings":["School of Big Data and Computer Science, Guizhou Normal University, Guiyang 550025, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Big Data and Computer Science, Guizhou Normal University, Guiyang 550025, China","institution_ids":["https://openalex.org/I154893126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123534235","display_name":"Jianping Gou","orcid":null},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Gou","raw_affiliation_strings":["School of Computer and Information Sciences, Southwest University, Chongqing 400715, China"],"raw_orcid":"https://orcid.org/0000-0003-1413-0693","affiliations":[{"raw_affiliation_string":"School of Computer and Information Sciences, Southwest University, Chongqing 400715, China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100413271","display_name":"Zhonghua Liu","orcid":"https://orcid.org/0000-0001-9816-7471"},"institutions":[{"id":"https://openalex.org/I31847773","display_name":"Zhejiang Ocean University","ror":"https://ror.org/03mys6533","country_code":"CN","type":"education","lineage":["https://openalex.org/I31847773"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhonghua Liu","raw_affiliation_strings":["School of Information Engineering, Zhejiang Ocean University, Zhoushan 316022, China"],"raw_orcid":"https://orcid.org/0000-0001-9816-7471","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Zhejiang Ocean University, Zhoushan 316022, China","institution_ids":["https://openalex.org/I31847773"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008194585"],"corresponding_institution_ids":["https://openalex.org/I154893126"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41338952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"4","first_page":"162","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9884999990463257,"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":0.9884999990463257,"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":0.003000000026077032,"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":0.00279999990016222,"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/benchmark","display_name":"Benchmark (surveying)","score":0.6726999878883362},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6090999841690063},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.3750999867916107},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3709999918937683},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.358599990606308},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972999811172485},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6444000005722046},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6090999841690063},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48069998621940613},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3709999918937683},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.358599990606308},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C68060419","wikidata":"https://www.wikidata.org/wiki/Q40754","display_name":"Subtraction","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C3309909","wikidata":"https://www.wikidata.org/wiki/Q864155","display_name":"Binary decision diagram","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging12040162","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12040162","pdf_url":"https://www.mdpi.com/2313-433X/12/4/162/pdf?version=1775791373","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:42042505","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42042505","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":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:feb25621f5124f91b3f67bc1f4b63814","is_oa":true,"landing_page_url":"https://doaj.org/article/feb25621f5124f91b3f67bc1f4b63814","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 12, Iss 4, p 162 (2026)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13117283","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13117283/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging12040162","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging12040162","pdf_url":"https://www.mdpi.com/2313-433X/12/4/162/pdf?version=1775791373","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5694630742073059,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7784321418","display_name":null,"funder_award_id":"62262005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7152408444.pdf","grobid_xml":"https://content.openalex.org/works/W7152408444.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W1956340063","https://openalex.org/W2045768472","https://openalex.org/W2101105183","https://openalex.org/W2533800772","https://openalex.org/W2928537485","https://openalex.org/W2995225687","https://openalex.org/W3140300848","https://openalex.org/W3203255640","https://openalex.org/W4225739172","https://openalex.org/W4312310776","https://openalex.org/W4312982094","https://openalex.org/W4324382242","https://openalex.org/W4328120750","https://openalex.org/W4379879090","https://openalex.org/W4380993851","https://openalex.org/W4385245495","https://openalex.org/W4385348204","https://openalex.org/W4387211791","https://openalex.org/W4392902814","https://openalex.org/W4399492636","https://openalex.org/W4403088766","https://openalex.org/W4403089452","https://openalex.org/W4403109359","https://openalex.org/W4403619370","https://openalex.org/W4406421457","https://openalex.org/W4408492863","https://openalex.org/W4411191754","https://openalex.org/W4412887831","https://openalex.org/W4413145524","https://openalex.org/W4413447271"],"related_works":[],"abstract_inverted_index":{"Difference":[0],"visual":[1],"question":[2],"answering":[3],"(Diff-VQA)":[4],"aims":[5],"to":[6,28,48,102,123],"answer":[7,75,178],"questions":[8],"by":[9],"identifying":[10],"and":[11,40,43,61,89,107,116,127,170],"reasoning":[12,72],"about":[13],"differences":[14],"between":[15],"medical":[16,67,168,177],"images.":[17],"Existing":[18],"methods":[19],"often":[20],"rely":[21],"on":[22,131,166],"simple":[23],"feature":[24],"subtraction":[25],"or":[26],"fusion":[27],"model":[29],"image":[30],"differences,":[31],"while":[32],"overlooking":[33],"the":[34,120,132,147,153,160,163],"asymmetric":[35],"descriptive":[36],"requirements":[37],"of":[38,142,162],"changed":[39],"unchanged":[41],"cases":[42],"providing":[44],"limited":[45],"task-specific":[46],"guidance":[47],"pretrained":[49],"language":[50,121],"decoders.":[51],"To":[52],"address":[53],"these":[54],"limitations,":[55],"we":[56],"propose":[57],"D2MNet":[58,137],"(Difference-aware":[59],"Decoupling":[60],"Multi-prompt":[62],"Network),":[63],"a":[64,78,85,91,95,108,139],"framework":[65],"for":[66,174],"Diff-VQA":[68,169],"that":[69,136],"combines":[70],"change-aware":[71,93],"with":[73],"prompt-guided":[74],"generation.":[76,129,179],"Specifically,":[77],"Change":[79],"Analysis":[80],"Module":[81,97],"(CAM)":[82],"predicts":[83],"whether":[84],"change":[86],"is":[87],"present":[88],"produces":[90],"binary":[92],"prompt;":[94],"Difference-Aware":[96],"(DAM)":[98],"uses":[99],"dual":[100],"attention":[101],"capture":[103],"fine-grained":[104],"difference":[105],"features;":[106],"multi-prompt":[109],"learning":[110],"mechanism":[111],"(MLM)":[112],"injects":[113],"question-aware,":[114],"change-aware,":[115],"learnable":[117],"prompts":[118],"into":[119],"decoder":[122],"improve":[124],"contextual":[125],"alignment":[126],"response":[128],"Experiments":[130],"MIMIC-DiffVQA":[133],"benchmark":[134,167],"show":[135],"achieves":[138],"CIDEr":[140],"score":[141],"2.907":[143],"\u00b1":[144],"0.040,":[145],"outperforming":[146],"strongest":[148],"baseline,":[149],"ReAl":[150],"(2.409),":[151],"under":[152],"same":[154],"evaluation":[155],"setting.":[156],"These":[157],"results":[158],"demonstrate":[159],"effectiveness":[161],"proposed":[164],"design":[165],"suggest":[171],"its":[172],"potential":[173],"assisting":[175],"difference-aware":[176]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-04-10T00:00:00"}