{"id":"https://openalex.org/W7137986001","doi":"https://doi.org/10.1609/aaai.v40i11.37816","title":"RL-U2Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart Segmentation","display_name":"RL-U2Net: A Dual-Branch UNet with Reinforcement Learning-Assisted Multimodal Feature Fusion for Accurate 3D Whole-Heart Segmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137986001","doi":"https://doi.org/10.1609/aaai.v40i11.37816"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i11.37816","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37816","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37816/41778","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37816/41778","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102731854","display_name":"Jierui Qu","orcid":"https://orcid.org/0009-0001-2405-9942"},"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":true,"raw_author_name":"Jierui Qu","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129652326","display_name":"Jianchun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchun Zhao","raw_affiliation_strings":["Xi'an Jiaotong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102731854"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23247496,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"8640","last_page":"8648"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.3743000030517578,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.3743000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.34709998965263367,"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/T14510","display_name":"Medical Imaging and Analysis","score":0.03999999910593033,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7522000074386597},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.685699999332428},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6348999738693237},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5288000106811523},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4505999982357025},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4235999882221222},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3869999945163727}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7843999862670898},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7522000074386597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7490000128746033},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.685699999332428},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6348999738693237},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49950000643730164},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3345000147819519},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31949999928474426},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.2915000021457672},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.26010000705718994}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i11.37816","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37816","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37816/41778","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37816","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37816","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37816/41778","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.44026491045951843}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137986001.pdf","grobid_xml":"https://content.openalex.org/works/W7137986001.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Accurate":[0],"whole-heart":[1,102],"segmentation":[2,35,42,71,184],"is":[3],"a":[4,82,107,121,131,142],"critical":[5],"component":[6],"in":[7,117],"the":[8,65,126,175,182,189,197,217,222],"precise":[9,97],"diagnosis":[10],"and":[11,27,37,61,64,70,74,98,114,119,141,156,211,219],"interventional":[12],"planning":[13],"of":[14,67,207,221],"cardiovascular":[15],"diseases.":[16],"Integrating":[17],"complementary":[18],"information":[19],"from":[20,177],"modalities":[21,51,140],"such":[22],"as":[23],"computed":[24],"tomography":[25],"(CT)":[26],"magnetic":[28],"resonance":[29],"imaging":[30],"(MRI)":[31],"can":[32],"significantly":[33],"enhance":[34],"accuracy":[36],"robustness.":[38],"However,":[39],"existing":[40,201],"multi-modal":[41,100],"methods":[43],"face":[44],"several":[45],"limitations:":[46],"severe":[47],"spatial":[48],"inconsistency":[49],"between":[50,125,139],"hinders":[52],"effective":[53],"feature":[54,68,91],"fusion;":[55],"fusion":[56],"strategies":[57],"are":[58,72,162],"often":[59],"static":[60],"lack":[62],"adaptability;":[63],"processes":[66],"alignment":[69],"decoupled":[73],"inefficient.":[75],"To":[76],"address":[77],"these":[78],"challenges,":[79],"we":[80],"propose":[81],"dual-branch":[83,108],"U-Net":[84],"architecture":[85],"enhanced":[86],"by":[87],"reinforcement":[88,143],"learning":[89,144],"for":[90,96],"alignment,":[92],"termed":[93],"RL-U2Net,":[94],"designed":[95],"efficient":[99],"3D":[101],"segmentation.":[103],"The":[104,128,159],"model":[105],"employs":[106,130],"U-shaped":[109],"network":[110],"to":[111,135,180],"process":[112],"CT":[113,210],"MRI":[115],"patches":[116,179],"parallel,":[118],"introduces":[120],"novel":[122],"RL-XAlign":[123],"module":[124,129,173],"encoders.":[127],"cross\u2011modal":[132],"attention":[133],"mechanism":[134],"capture":[136],"semantic":[137],"correspondences":[138],"agent":[145],"learns":[146],"an":[147,170],"optimal":[148],"rotation":[149],"strategy":[150],"that":[151,196],"consistently":[152],"aligns":[153],"anatomical":[154],"pose":[155],"texture":[157],"features.":[158],"aligned":[160],"features":[161],"then":[163],"reconstructed":[164],"through":[165],"their":[166],"respective":[167],"decoders.":[168],"Finally,":[169],"ensemble\u2011learning\u2013based":[171],"decision":[172],"integrates":[174],"predictions":[176],"individual":[178],"produce":[181],"final":[183],"result.":[185],"Experimental":[186],"results":[187],"on":[188,209,213],"publicly":[190],"available":[191],"MM-WHS":[192],"2017":[193],"dataset":[194],"demonstrate":[195],"proposed":[198,223],"RL-U2Net":[199],"outperforms":[200],"state-of-the-art":[202],"methods,":[203],"achieving":[204],"Dice":[205],"coefficients":[206],"93.1%":[208],"87.0%":[212],"MRI,":[214],"thereby":[215],"validating":[216],"effectiveness":[218],"superiority":[220],"approach.":[224]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-03-18T00:00:00"}