{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T00:07:17Z","timestamp":1772842037491,"version":"3.50.1"},"reference-count":43,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Health and Medical Research Council of Australia","award":["2030157"],"award-info":[{"award-number":["2030157"]}]},{"name":"National Health and Medical Research Council of Australia","award":["DE20101297"],"award-info":[{"award-number":["DE20101297"]}]},{"name":"National Health and Medical Research Council of Australia","award":["DP230101628"],"award-info":[{"award-number":["DP230101628"]}]},{"name":"Australia Research Council","award":["2030157"],"award-info":[{"award-number":["2030157"]}]},{"name":"Australia Research Council","award":["DE20101297"],"award-info":[{"award-number":["DE20101297"]}]},{"name":"Australia Research Council","award":["DP230101628"],"award-info":[{"award-number":["DP230101628"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Phase images from gradient echo MRI sequences reflect underlying magnetic field inhomogeneities but are inherently wrapped within the range of \u2212\u03c0 to \u03c0, requiring phase unwrapping to recover the true phase. In this study, we present DIP-UP (Deep Image Prior for Unwrapping Phase), a framework designed to refine two pre-trained deep learning models for phase unwrapping: PHUnet3D and PhaseNet3D. We compared the DIP-refined models to their original versions, as well as to the conventional PRELUDE algorithm from FSL, using both simulated and in vivo brain data. Results demonstrate that DIP refinement improves unwrapping accuracy (achieving ~99%) and robustness to noise, surpassing the original networks and offering comparable performance to PRELUDE while being over three times faster. This framework shows strong potential for enhancing downstream MRI phase-based analyses.<\/jats:p>","DOI":"10.3390\/info16070592","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T11:26:37Z","timestamp":1752233197000},"page":"592","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DIP-UP: Deep Image Prior for Unwrapping Phase"],"prefix":"10.3390","volume":"16","author":[{"given":"Xuanyu","family":"Zhu","sequence":"first","affiliation":[{"name":"Innovation Academy for Precision Measurement Science and Technology, CAS, Wuhan 430071, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3846-0999","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha 410083, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Image X Institute, Sydney School of Health Sciences, The University of Sydney, Camperdown, Sydney, NSW 2006, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, St. Lucia, Brisbane, QLD 4072, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The University of Queensland, St. Lucia, Brisbane, QLD 4072, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3436-7831","authenticated-orcid":false,"given":"Hongfu","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Newcastle, Callaghan, Newcastle, NSW 2308, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhai, X., and Chen, Z. (2022). Proof of linear MRI phase imaging from an internal fieldmap. NMR Biomed., 35.","DOI":"10.1002\/nbm.4741"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1002\/mrm.27011","article-title":"General phase regularized reconstruction using phase cycling","volume":"80","author":"Ong","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Robinson, S.D., Bredies, K., Khabipova, D., Dymerska, B., Marques, J.P., and Schweser, F. (2017). An illustrated comparison of processing methods for MR phase imaging and QSM: Combining array coil signals and phase unwrapping. NMR Biomed., 30.","DOI":"10.1002\/nbm.3601"},{"key":"ref_4","first-page":"783","article-title":"One-dimensional Hilbert transform processing for N-dimensional phase unwrapping","volume":"5","author":"Hasan","year":"2006","journal-title":"WSEAS Trans. Circuits Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1002\/mrm.29465","article-title":"A method for measuring B0 field inhomogeneity using quantitative double-echo in steady-state","volume":"89","author":"Barbieri","year":"2023","journal-title":"Magn. Reson. Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2077","DOI":"10.1002\/mrm.27891","article-title":"Analysis of different phase unwrapping methods to optimize quantitative susceptibility mapping in the abdomen","volume":"82","author":"Bechler","year":"2019","journal-title":"Magn. Reson. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1002\/mrm.29265","article-title":"Deep learning\u2014Based quantitative susceptibility mapping (QSM) in the presence of fat using synthetically generated multi-echo phase training data","volume":"88","author":"Hanspach","year":"2022","journal-title":"Magn. Reson. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1109\/TMI.2002.803106","article-title":"Understanding phase maps in MRI: A new cutline phase unwrapping method","volume":"21","author":"Chavez","year":"2002","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"578","DOI":"10.1016\/j.zemedi.2022.08.001","article-title":"BFRnet: A deep learning-based MR background field removal method for QSM of the brain containing significant pathological susceptibility sources","volume":"33","author":"Zhu","year":"2022","journal-title":"Z. Med. Phys."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1151","DOI":"10.1002\/mrm.24765","article-title":"Background field removal using spherical mean value filtering and Tikhonov regularization","volume":"71","author":"Sun","year":"2014","journal-title":"Magn. Reson. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"119410","DOI":"10.1016\/j.neuroimage.2022.119410","article-title":"Instant tissue field and magnetic susceptibility mapping from MRI raw phase using Laplacian enhanced deep neural networks","volume":"259","author":"Gao","year":"2022","journal-title":"NeuroImage"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3103","DOI":"10.1002\/mrm.26989","article-title":"Phase processing for quantitative susceptibility mapping of regions with large susceptibility and lack of signal","volume":"79","author":"Fortier","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1550","DOI":"10.21037\/qims-22-525","article-title":"New 3D phase-unwrapping method based on voxel clustering and local polynomial modeling: Application to quantitative susceptibility mapping","volume":"13","author":"Cheng","year":"2023","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1002\/mrm.22074","article-title":"Reliable two-dimensional phase unwrapping method using region growing and local linear estimation","volume":"62","author":"Zhou","year":"2009","journal-title":"Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1662","DOI":"10.1002\/mrm.25279","article-title":"Robust phase unwrapping for MR temperature imaging using a magnitude-sorted list, multi-clustering algorithm","volume":"73","author":"Maier","year":"2015","journal-title":"Magn. Reson. Med."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1002\/jmri.25045","article-title":"Phase unwrapping in 4D MR flow with a 4D single-step laplacian algorithm","volume":"43","author":"Loecher","year":"2016","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1194","DOI":"10.1364\/OL.28.001194","article-title":"Fast phase unwrapping algorithm for interferometric applications","volume":"28","author":"Schofield","year":"2003","journal-title":"Opt. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1002\/mrm.10354","article-title":"Fast, automated, N-dimensional phase-unwrapping algorithm","volume":"49","author":"Jenkinson","year":"2003","journal-title":"Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1109\/TMI.2018.2884093","article-title":"SEGUE: A speedy region-growing algorithm for unwrapping estimated phase","volume":"38","author":"Karsa","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"6623","DOI":"10.1364\/AO.46.006623","article-title":"Fast and robust three-dimensional best path phase unwrapping algorithm","volume":"46","author":"Gdeisat","year":"2007","journal-title":"Appl. Opt."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"4582","DOI":"10.1364\/AO.48.004582","article-title":"Robust three-dimensional best-path phase-unwrapping algorithm that avoids singularity loops","volume":"48","author":"Gdeisat","year":"2009","journal-title":"Appl. Opt."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"V\u00e9ron, A.S., Lemaitre, C., Gautier, C., Lacroix, V., and Sagot, M.-F. (2011). Close 3D proximity of evolutionary breakpoints argues for the notion of spatial synteny. BMC Genom., 12.","DOI":"10.1186\/1471-2164-12-303"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"014001","DOI":"10.1117\/1.APN.1.1.014001","article-title":"Deep learning spatial phase unwrapping: A comparative review","volume":"1","author":"Wang","year":"2022","journal-title":"Adv. Photonics Nexus"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"111566","DOI":"10.1016\/j.measurement.2022.111566","article-title":"Two-dimensional phase unwrapping by a high-resolution deep learning network","volume":"200","author":"Huang","year":"2022","journal-title":"Measurement"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"23173","DOI":"10.1364\/OE.27.023173","article-title":"Rapid and robust two-dimensional phase unwrapping via deep learning","volume":"27","author":"Zhang","year":"2019","journal-title":"Opt. Express"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"15100","DOI":"10.1364\/OE.27.015100","article-title":"One-step robust deep learning phase unwrapping","volume":"27","author":"Wang","year":"2019","journal-title":"Opt. Express"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Gao, Y., Zhu, X., Moffat, B.A., Glarin, R., Wilman, A.H., Pike, G.B., Crozier, S., and Liu, F. (2021). xQSM: Quantitative susceptibility mapping with octave convolutional and noise-regularized neural networks. NMR Biomed., 34.","DOI":"10.1002\/nbm.4461"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.zemedi.2021.06.004","article-title":"Deep grey matter quantitative susceptibility mapping from small spatial coverages using deep learning","volume":"32","author":"Zhu","year":"2022","journal-title":"Z. F\u00fcr Med. Phys."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1109\/LSP.2018.2879184","article-title":"PhaseNet: A deep convolutional neural network for two-dimensional phase unwrapping","volume":"26","author":"Spoorthi","year":"2018","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"4862","DOI":"10.1109\/TIP.2020.2977213","article-title":"PhaseNet 2.0: Phase unwrapping of noisy data based on deep learning approach","volume":"29","author":"Spoorthi","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_31","first-page":"5221510","article-title":"PU-GAN: A one-step 2-D InSAR phase unwrapping based on conditional generative adversarial network","volume":"60","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1145\/3422622","article-title":"Generative adversarial networks","volume":"63","author":"Goodfellow","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3321","DOI":"10.1002\/mrm.28927","article-title":"The PHU-NET: A robust phase unwrapping method for MRI based on deep learning","volume":"86","author":"Zhou","year":"2021","journal-title":"Magn. Reson. Med."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Chen, Z., Quan, Y., and Ji, H. (2024, January 16\u201322). Unsupervised deep unrolling networks for phase unwrapping. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02379"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yin, W., Chen, Q., Feng, S., Tao, T., Huang, L., Trusiak, M., Asund, A., and Zuo, C. (2019). Temporal phase unwrapping using deep learning. Sci. Rep., 9.","DOI":"10.1117\/12.2537582"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"121962","DOI":"10.1016\/j.eswa.2023.121962","article-title":"Ic-gan: An improved conditional generative adversarial network for rgb-to-ir image translation with applications to forest fire monitoring","volume":"238","author":"Boroujeni","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_37","unstructured":"Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2018, January 18\u201323). Deep image prior. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"120583","DOI":"10.1016\/j.neuroimage.2024.120583","article-title":"Quantitative susceptibility mapping through model-based deep image prior (MoDIP)","volume":"291","author":"Xiong","year":"2024","journal-title":"NeuroImage"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"7025","DOI":"10.1109\/TIP.2021.3099956","article-title":"Robust phase unwrapping via deep image prior for quantitative phase imaging","volume":"30","author":"Yang","year":"2021","journal-title":"IEEE Trans. Image Process."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1002\/hbm.10062","article-title":"Fast robust automated brain extraction","volume":"17","author":"Smith","year":"2002","journal-title":"Hum. Brain Mapp."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1002\/mrm.21828","article-title":"Calculation of susceptibility through multiple orientation sampling (COSMOS): A method for conditioning the inverse problem from measured magnetic field map to susceptibility source image in MRI","volume":"61","author":"Liu","year":"2009","journal-title":"Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1002\/nbm.1670","article-title":"A novel background field removal method for MRI using projection onto dipole fields","volume":"24","author":"Liu","year":"2011","journal-title":"NMR Biomed."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Reddy, P.K., Sudarshan, V.P., Gubbi, J., and Pal, A. (2022, January 28\u201331). Structural-Mr Informed QSM Reconstruction Using Deep Image Prior. Proceedings of the 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), Kolkata, India.","DOI":"10.1109\/ISBI52829.2022.9761569"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/592\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:07:29Z","timestamp":1760033249000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/592"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,9]]},"references-count":43,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["info16070592"],"URL":"https:\/\/doi.org\/10.3390\/info16070592","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,9]]}}}