{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:28:52Z","timestamp":1792787332402,"version":"4.5.0"},"reference-count":49,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"name":"COCHE"},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["MHP\/054\/22"],"award-info":[{"award-number":["MHP\/054\/22"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010428","name":"Innovation and Technology Fund","doi-asserted-by":"publisher","award":["LU BGR105824"],"award-info":[{"award-number":["LU BGR105824"]}],"id":[{"id":"10.13039\/501100010428","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NORCE","id":[{"id":"https:\/\/ror.org\/02gagpf75","id-type":"ROR","asserted-by":"crossref"}]},{"name":"RGC-GRF","award":["11309925"],"award-info":[{"award-number":["11309925"]}]},{"name":"Hong Kong Research Grants Council","award":["CityU11309922"],"award-info":[{"award-number":["CityU11309922"]}]},{"name":"Hong Kong Research Grants Council","award":["LU13300125"],"award-info":[{"award-number":["LU13300125"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Imaging Sci."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>Blood flow imaging provides important information for hemodynamic behavior within the vascular system and plays an essential role in medical diagnosis and treatment planning. However, obtaining high-quality flow images remains a significant challenge.\u00a0In this work, we address the problem of denoising flow images that may suffer from artifacts due to short acquisition times or device-induced errors. We formulate this task as an optimization problem, where the objective is to minimize the discrepancy between the modeled velocity field, constrained to satisfy the Navier\u2013Stokes equations, and the observed noisy velocity data.\u00a0To solve this problem, we decompose it into two subproblems:\u00a0a fluid subproblem and a geometry subproblem.\u00a0The fluid subproblem leverages a physics-informed neural network (PINN) to reconstruct the velocity field from noisy observations, assuming a fixed domain.\u00a0The geometry subproblem aims to infer the underlying flow region by optimizing a quasi-conformal mapping that deforms a reference domain.\u00a0These two subproblems are solved in an alternating Gauss\u2013Seidel fashion, iteratively refining both the velocity field and the domain. Upon convergence, the framework yields a high-quality reconstruction of the flow image.\u00a0We validate the proposed method through experiments on synthetic flow data in a converging channel geometry under varying levels of Gaussian noise and on real-life flow data in an aortic geometry with signal-dependent noise.\u00a0The results demonstrate the effectiveness and robustness of the approach.\u00a0Additionally, ablation studies are conducted to assess the influence of key hyperparameters.<\/jats:p>","DOI":"10.1137\/26m1838593","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T07:00:46Z","timestamp":1789628446000},"page":"2087-2122","source":"Crossref","is-referenced-by-count":0,"title":["Coupled Reconstruction of 2D Blood Flow and Vessel Geometry from Noisy Images via Physics-Informed Neural Networks and Quasi-conformal Mapping"],"prefix":"10.1137","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9465-0132","authenticated-orcid":true,"given":"Han","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Mathematics, City University of Hong Kong and Hong Kong Centre for Cerebro-Cardiovascular Health Engineering, Hong Kong, China."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3359-9104","authenticated-orcid":true,"given":"Xue-Cheng","family":"Tai","sequence":"additional","affiliation":[{"name":"Norwegian Research Centre (NORCE), 5008 Bergen, Norway."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Michel","family":"Morel","sequence":"additional","affiliation":[{"name":"Division of Industrial Data Science."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0910-4685","authenticated-orcid":true,"given":"Raymond H.","family":"Chan","sequence":"additional","affiliation":[{"name":"Department of Operations and Risk Management and the School of Data Science, Lingnan University and Hong Kong Centre for Cerebro-cardiovascular Health Engineering, Hong Kong, China."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/abced8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ad1133"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/20M138569X"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ac6971"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00466-008-0315-x"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2012.08.033"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007979827043"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0551-y"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57784-1_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/090772836"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2005.11.011"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0045-7825(01)00302-4"},{"key":"ref14","unstructured":"N. Freidoonimehr, M. Arjomandi, A. Zander, and R. Chin, SimVascular Clinical Test Cases: Aortofemoral normal - \\(2\\), 2025, https:\/\/simvascular.github.io\/clinical\/aortofemoral2.html."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1063\/5.0054312"},{"key":"ref16","doi-asserted-by":"crossref","unstructured":"P. Getreuer, M. Tong, and L. A. Vese, A variational model for the restoration of MR images corrupted by blur and Rician noise, in Proceedings of the International Symposium on Visual Computing, Springer, 2011, pp. 686\u2013698.","DOI":"10.1007\/978-3-642-24028-7_63"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/080725891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2015.08.006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/040612336"},{"key":"ref20","unstructured":"D. Kingma and J. Ba, Adam:\u00a0A method for stochastic optimization, in Proceedings of the 3rd International Conference on Learning Representation, ICLR 2015, San Diego, CA, 2015. Available at https:\/\/arxiv.org\/abs\/1412.6980."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/jfm.2022.503"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/ad9cb7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2012.l-bm3d"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-016-0175-z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/14098435X"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.23632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-016-0675-3"},{"key":"ref28","volume-title":"Diffusion Generated Motion by Mean Curvature","author":"Merriman B.","year":"1992"},{"key":"ref29","volume-title":"Algorithms for Image Processing and Computer Vision","author":"Parker J. R.","year":"2010"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(72)90065-4"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199606273342604"},{"key":"ref32","first-page":"3","volume":"12","author":"Quarteroni A.","year":"2004","journal-title":"Handbook of Numerical Analysis"},{"key":"ref33","volume-title":"The Navier-Stokes Equations:\u00a0An Elementary Functional Analytic Approach","author":"Sohr H.","year":"2001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.taml.2020.01.031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-0208(08)72402-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-016-1762-8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1063\/5.0078143"},{"key":"ref38","first-page":"19707","volume":"25","author":"Wang S.","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-017-0629-y"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.02.002"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2022.3225188"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5201\/ipol.2011.ys-dct"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-021-01433-y"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/23M1622696"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2025.107378"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/25M1731162"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128124"},{"key":"ref48","first-page":"235","volume":"93","author":"Zhang H.","year":"2024","journal-title":"Acta Math. Univ. Comenian."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2839891"}],"container-title":["SIAM Journal on Imaging Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/26M1838593","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T07:00:51Z","timestamp":1789628451000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/26M1838593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":49,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1137\/26M1838593"],"URL":"https:\/\/doi.org\/10.1137\/26m1838593","relation":{},"ISSN":["1936-4954"],"issn-type":[{"value":"1936-4954","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]}}}