{"authors":[{"id":"orcid_______::1d93aefdb3e8f1023e1ab44fee56d8c3","fullName":"Patryk Rygiel","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid","value":"0009-0003-8539-5581"},"provenance":null}},{"id":null,"fullName":"Julian Suk","name":null,"surname":null,"rank":2,"pid":null},{"id":null,"fullName":"Kak Khee Yeung","name":null,"surname":null,"rank":3,"pid":null},{"id":"orcid_______::02f5d5e47ae05c3e5dedf9e42458dfdc","fullName":"Christoph Brune","name":null,"surname":null,"rank":4,"pid":{"id":{"scheme":"orcid","value":"0000-0003-0145-5069"},"provenance":null}},{"id":"orcid_______::baaea28d0395c5f0f2ab2a0c42a8da86","fullName":"Jelmer M. Wolterink","name":"Jelmer M.","surname":"Wolterink","rank":5,"pid":{"id":{"scheme":"orcid","value":"0000-0001-5505-475x"},"provenance":null}}],"openAccessColor":null,"publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"eng","label":"English"},"countries":[{"code":"NL","label":"Netherlands","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Vision and Pattern Recognition (cs.CV)"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Vision and Pattern Recognition"},"provenance":null},{"subject":{"scheme":"keyword","value":"cs.CV"},"provenance":null}],"mainTitle":"Active Learning for Deep Learning-Based Hemodynamic Parameter Estimation","subTitle":null,"descriptions":["Hemodynamic parameters such as pressure and wall shear stress play an important role in diagnosis, prognosis, and treatment planning in cardiovascular diseases. These parameters can be accurately computed using computational fluid dynamics (CFD), but CFD is computationally intensive. Hence, deep learning methods have been adopted as a surrogate to rapidly estimate CFD outcomes. A drawback of such data-driven models is the need for time-consuming reference CFD simulations for training. In this work, we introduce an active learning framework to reduce the number of CFD simulations required for the training of surrogate models, lowering the barriers to their deployment in new applications. We propose three distinct querying strategies to determine for which unlabeled samples CFD simulations should be obtained. These querying strategies are based on geometrical variance, ensemble uncertainty, and adherence to the physics governing fluid dynamics. We benchmark these methods on velocity field estimation in synthetic coronary artery bifurcations and find that they allow for substantial reductions in annotation cost. Notably, we find that our strategies reduce the number of samples required by up to 50% and make the trained models more robust to difficult cases. Our results show that active learning is a feasible strategy to increase the potential of deep learning-based CFD surrogates."],"publicationDate":"2026-01-01","publisher":"Springer Nature Switzerland","embargoEndDate":"2025-03-01","sources":["Crossref","Lecture Notes in Computer Science ISBN: 9783032177339"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":null,"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::518cb278bc18cc2ca8a55d2e44824e9b","originalIds":["10.1007/978-3-032-17734-6_11","50|doiboost____|9fb173607eac05bb0452b3329c5bf119","50|datacite____::518cb278bc18cc2ca8a55d2e44824e9b","10.48550/arxiv.2503.03453","oai:arXiv.org:2503.03453","50|od________18::90d23c811cd9e9ab02439a30db7ac7b9","50|dblp________::184badf4df9859a6fd346713ac38e8a7","oai:ris.utwente.nl:openaire_cris_publications/9274070d-3553-4be5-8dc7-981cb0e0eb78","50|dris___02403::3cce8da50c2a6888061cc680ea8520b6"],"pids":[{"scheme":"doi","value":"10.1007/978-3-032-17734-6_11"},{"scheme":"doi","value":"10.48550/arxiv.2503.03453"},{"scheme":"arXiv","value":"2503.03453"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":0.0,"influence":2.1746283E-9,"popularity":2.6085654E-9,"impulse":0.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C5"}},"projects":[{"id":"corda_____he::44f5b75ec6f43c71ccc69802554add40","code":"101080947","acronym":"VASCUL-AID","title":"DEVELOPING TRUSTWORTHY ARTIFICIAL INTELLIGENCE (AI)-DRIVEN TOOLS TO PREDICT VASCULAR DISEASE RISK AND PROGRESSION","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101080947"}]}],"organizations":[{"legalName":"University of Twente","acronym":"University of Twente","id":"openorgs____::604881198363fedbb5d5478f465305f2","pids":[{"scheme":"OrgRef","value":"101629"},{"scheme":"mag_id","value":"94624287"},{"scheme":"FundRef","value":"501100009404"},{"scheme":"fundref","value":"501100009404"},{"scheme":"PIC","value":"999900833"},{"scheme":"fundref","value":"501100001834"},{"scheme":"FundRef","value":"501100001834"},{"scheme":"wikidata","value":"Q1547084"},{"scheme":"PIC","value":"999660661"},{"scheme":"fundref","value":"501100007661"},{"scheme":"Wikidata","value":"Q1547084"},{"scheme":"ROR","value":"https://ror.org/006hf6230"},{"scheme":"OrgReg","value":"NL0005"},{"scheme":"GRID","value":"grid.6214.1"},{"scheme":"FundRef","value":"501100007661"},{"scheme":"ISNI","value":"0000000403998953"}],"countries":[{"code":"NL","label":"Netherlands"}],"websiteurl":"http://www.utwente.nl/en/"},{"legalName":"Amsterdam University Medical Centers","acronym":"Amsterdam UMC","id":"openorgs____::2ce10b2528220091bd0363c1e39394c1","pids":[{"scheme":"ISNI","value":"0000000468803010"},{"scheme":"GRID","value":"grid.509540.d"},{"scheme":"FundRef","value":"100019573"},{"scheme":"ROR","value":"https://ror.org/05grdyy37"},{"scheme":"Wikidata","value":"Q56682938"},{"scheme":"wikidata","value":"Q56682938"},{"scheme":"fundref","value":"100019573"}],"countries":[{"code":"NL","label":"Netherlands"}],"websiteurl":"https://www.amsterdamumc.org/"},{"legalName":"Amsterdam Cardiovascular Sciences","acronym":"ACS","id":"pending_org_::0d03cfc852be363150c40dca4d2298fc","pids":[{"scheme":"FundRef","value":"100019741"},{"scheme":"ROR","value":"https://ror.org/05c9qnd49"},{"scheme":"ISNI","value":"0000000485174260"},{"scheme":"fundref","value":"100019741"}],"countries":[{"code":"NL","label":"Netherlands"}],"websiteurl":"https://www.amsterdamumc.org/en/research/institutes/amsterdam-cardiovascular-sciences.htm"},{"legalName":"Academic Medical Center - University of Amsterdam","acronym":"Amsterdam UMC","id":"openorgs____::01717f42bf8b3d8e3acf57fbb09ba6ac","pids":[{"scheme":"PIC","value":"998732274"},{"scheme":"RingGold","value":"RingGold:509921"},{"scheme":"ROR","value":"https://ror.org/03t4gr691"},{"scheme":"ISNI","value":"0000000093650969"}],"countries":[{"code":"NL","label":"Netherlands"}],"websiteurl":"http://www.amc.nl"}],"communities":[{"code":"netherlands","label":"Netherlands Research Portal","provenance":null}],"collectedFrom":[{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},{"key":"eurocrisdris::5183b3da90ba1f87fd0673a4ca0bfa39","value":"University of Twente Research Information "}],"instances":[{"pids":[{"scheme":"doi","value":"10.1007/978-3-032-17734-6_11"}],"license":"Springer Nature TDM","accessRight":{"code":"c_14cb","label":"CLOSED","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Part of book or chapter of book","urls":["https://doi.org/10.1007/978-3-032-17734-6_11"],"publicationDate":"2026-01-01","refereed":"peerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2503.03453"}],"license":"CC BY","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2503.03453"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"pids":[{"scheme":"arXiv","value":"2503.03453"}],"accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Preprint","urls":["http://arxiv.org/abs/2503.03453"],"publicationDate":"2025-03-05","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},"collectedFrom":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.48550/arxiv.2503.03453"}],"type":"Preprint","urls":["https://dblp.org/rec/journals/corr/abs-2503-03453.html","https://doi.org/10.48550/arXiv.2503.03453"],"publicationDate":"2025-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"},"collectedFrom":{"key":"openaire____::d8b68cc0a53121f6f896883a7d60c1db","value":"DBLP"}},{"alternateIdentifiers":[{"scheme":"doi","value":"10.48550/arxiv.2503.03453"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Research","urls":["https://research.utwente.nl/en/publications/9274070d-3553-4be5-8dc7-981cb0e0eb78","https://doi.org/10.48550/arXiv.2503.03453"],"publicationDate":"2025-03-05","refereed":"nonPeerReviewed","hostedBy":{"key":"eurocrisdris::5183b3da90ba1f87fd0673a4ca0bfa39","value":"University of Twente Research Information "},"collectedFrom":{"key":"eurocrisdris::5183b3da90ba1f87fd0673a4ca0bfa39","value":"University of Twente Research Information "}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::44f5b75ec6f43c71ccc69802554add40","relatedRecordType":"project","relationProvenance":"iis","trust":"0.897"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"DEVELOPING TRUSTWORTHY ARTIFICIAL INTELLIGENCE (AI)-DRIVEN TOOLS TO PREDICT VASCULAR DISEASE RISK AND PROGRESSION","code":"101080947","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-AG","description":"HORIZON Action Grant Budget-Based","name":"HORIZON-AG"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2023-05-01","endDate":"2029-04-30"}],"otherTitles":null,"green":true,"inDiamondJournal":false,"isGreen":true,"isInDiamondJournal":false}