{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T10:32:34Z","timestamp":1787567554574,"version":"build-2736575974"},"reference-count":40,"publisher":"IOP Publishing","issue":"16","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC2412100"],"award-info":[{"award-number":["2023YFC2412100"]}]},{"name":"Key Research and Development Programme of Heilongjiang Province","award":["JD24A001"],"award-info":[{"award-number":["JD24A001"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,8,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . Point spread function (PSF) and clutter noise are primary causes of ultrasound quality degradation. Physical deconvolution can reduce PSF effects but is sensitive to high-frequency noise, whereas deep learning often requires large labeled datasets and may introduce non-physical artifacts. Therefore, this study aims to develop an unsupervised and physically interpretable framework for robust and effective ultrasound image reconstruction.\n                    <jats:italic>Approach<\/jats:italic>\n                    . We propose an unsupervised physics-informed deconvolution network framework (UPIDN) that bridges the strengths of physical modeling and deep learning. Specifically, the degradation model is embedded into the network, and physical deconvolution provides stable low-frequency inversion guidance. Meanwhile, the structural prior capability of the deep image prior is exploited to compensate for the ill-posedness of high-frequency detail recovery. Additionally, we perform a cepstral domain transformation on radio-frequency data to decouple the embedded PSF information, providing the network with a physically consistent and data-adaptive initialization strategy. Meanwhile, considering the ultrasound noise characteristics, a dual-wavelet noise preprocessing scheme is designed to guide the prediction to focus more on the correct generation direction.\n                    <jats:italic>Main results<\/jats:italic>\n                    . Experiments demonstrate that UPIDN outperforms other state-of-the-art methods, achieving superior contrast and resolution while clearly measuring vessel\u2013muscle interface that is difficult to discern in input delay-and-sum results.\n                    <jats:italic>Significance<\/jats:italic>\n                    . UPIDN provides a reliable approach for high-quality ultrasound reconstruction without paired training data and offers a potential solution for ultrasound imaging scenarios where data availability and physical fidelity are critical.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ae9689","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:23:56Z","timestamp":1787563436000},"page":"165020","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An unsupervised physics-informed neural deconvolution framework for ultrasound imaging"],"prefix":"10.1088","volume":"71","author":[{"given":"Xiangyu","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0773-8871","authenticated-orcid":true,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9465-5064","authenticated-orcid":true,"given":"Lizheng","family":"Zu","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Shenzhen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8620-9854","authenticated-orcid":true,"given":"Yi","family":"Shen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"key":"pmbae9689bib1","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1007\/s00330-019-06491-3","type":"journal-article","article-title":"Qualitative and quantitative comparison of image quality between single-shot echo-planar and interleaved multi-shot echo-planar diffusion-weighted imaging in female pelvis","volume":"30","author":"An","year":"2020","journal-title":"Eur. Radiol."},{"key":"pmbae9689bib2","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.1109\/TUFFC.2024.3448209","type":"journal-article","article-title":"Denoising plane-wave ultrasound images using diffusion probabilistic models","volume":"71","author":"Asgariandehkordi","year":"2024","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib3","article-title":"Lightweight physics-informed zero-shot ultrasound plane-wave denoising","author":"Asgariandehkordi","year":"2025","type":"preprint"},{"key":"pmbae9689bib4","first-page":"524","type":"journal-article","article-title":"Noise2Self: blind denoising by self-supervision","volume":"97","author":"Batson","year":"2019","journal-title":"Proc. Mach. Learn. Res."},{"key":"pmbae9689bib5","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1109\/TMI.2015.2493241","type":"journal-article","article-title":"Compressive deconvolution in medical ultrasound imaging","volume":"35","author":"Chen","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae9689bib6","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1093\/biomet\/81.3.425","type":"journal-article","article-title":"Ideal spatial adaptation by wavelet shrinkage","volume":"81","author":"Donoho","year":"1994","journal-title":"Biometrika"},{"key":"pmbae9689bib7","first-page":"11026","type":"conference-proceedings","article-title":"Double-DIP: unsupervised image decomposition via coupled deep image priors","author":"Gandelsman","year":"2019"},{"key":"pmbae9689bib8","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1080\/10618600.1998.10474789","type":"journal-article","article-title":"Wavelet shrinkage denoising using the non-negative garrote","volume":"7","author":"Gao","year":"1998","journal-title":"J. Comput. Graph. Stat."},{"key":"pmbae9689bib9","doi-asserted-by":"publisher","first-page":"9197","DOI":"10.1109\/TCI.2023.3248945","type":"journal-article","article-title":"A unifying approach to inverse problems of ultrasound beamforming and deconvolution","volume":"9","author":"Goudarzi","year":"2023","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"pmbae9689bib10","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1109\/TUFFC.2020.3028166","type":"journal-article","article-title":"Ultrasound image deconvolution using fundamental and harmonic images","volume":"68","author":"Hourani","year":"2021","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib11","first-page":"14776","type":"conference-proceedings","article-title":"Neighbor2Neighbor: self-supervised denoising from single noisy images","author":"Huang","year":"2021"},{"key":"pmbae9689bib12","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/BF02520003","type":"journal-article","article-title":"Field: a program for simulating ultrasound systems","volume":"34","author":"Jensen","year":"1996","journal-title":"Med. Biol. Eng. Comput."},{"key":"pmbae9689bib13","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1177\/016173469301500204","type":"journal-article","article-title":"Deconvolution of in-vivo ultrasound B-mode images","volume":"15","author":"Jensen","year":"1993","journal-title":"Ultrason. Imaging"},{"key":"pmbae9689bib14","first-page":"2129","type":"conference-proceedings","article-title":"Noise2Void\u2014learning denoising from single noisy images","author":"Krull","year":"2019"},{"key":"pmbae9689bib15","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.1109\/TUFFC.2022.3193640","type":"journal-article","article-title":"Speckle reduction via deep content-aware image prior for precise breast tumor segmentation in an ultrasound image","volume":"69","author":"Lee","year":"2022","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102653","type":"journal-article","article-title":"Coronary artery calcification segmentation with sparse annotations in intravascular OCT: leveraging self-supervised learning and consistency regularization","volume":"125","author":"Li","year":"2025a","journal-title":"Comput. Med. Imaging Graph."},{"key":"pmbae9689bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103755","type":"journal-article","article-title":"Speckle2Self: self-supervised ultrasound speckle reduction without clean data","volume":"106","author":"Li","year":"2025b","journal-title":"Med. Image Anal."},{"key":"pmbae9689bib18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107860","type":"journal-article","article-title":"Deconvolution based on sparsity and continuity improves the quality of ultrasound image","volume":"169","author":"Li","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"pmbae9689bib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2026.120591","type":"journal-article","article-title":"A two-step reconstruction framework for rapid enhancement of ultrasound image quality","volume":"267","author":"Li","year":"2026","journal-title":"Measurement"},{"key":"pmbae9689bib20","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad4086","type":"journal-article","article-title":"Super-resolution reconstruction of ultrasound image using a modified diffusion model","volume":"69","author":"Liu","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbae9689bib21","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1109\/TMI.2018.2809641","type":"journal-article","article-title":"Deep neural networks for ultrasound beamforming","volume":"37","author":"Luchies","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae9689bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2022.109074","type":"journal-article","article-title":"Ultrasonic C-scan image restoration method using the Richardson\u2013Lucy algorithm and a flaw measurement model","volume":"200","author":"Lyu","year":"2022","journal-title":"Appl. Acoust"},{"key":"pmbae9689bib23","first-page":"14018","type":"conference-proceedings","article-title":"Zero-shot Noise2Noise: efficient image denoising without any data","author":"Mansour","year":"2023"},{"key":"pmbae9689bib24","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2004.838326","type":"journal-article","article-title":"A novel approach to the 2D blind deconvolution problem in medical ultrasound","volume":"24","author":"Michailovich","year":"2005","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae9689bib25","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1109\/TUFFC.2017.2685198","type":"journal-article","article-title":"Ultrasound pixel-based beamforming with phase alignments of focused beams","volume":"64","author":"Nguyen","year":"2017","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib26","first-page":"8024","type":"journal-article","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"pmbae9689bib27","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1109\/TUFFC.2021.3131383","type":"journal-article","article-title":"CNN-based image reconstruction method for ultrafast ultrasound imaging","volume":"69","author":"Perdios","year":"2022","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib28","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acac5d","type":"journal-article","article-title":"Adaptive noise reduction for power Doppler imaging using SVD filtering in the channel domain and coherence weighting of pixels","volume":"68","author":"Pialot","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbae9689bib29","first-page":"3341","type":"conference-proceedings","article-title":"Neural blind deconvolution using deep priors","author":"Ren","year":"2020"},{"key":"pmbae9689bib30","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1109\/TUFFC.2019.2956855","type":"journal-article","article-title":"The generalized contrast-to-noise ratio: a formal definition for lesion detectability","volume":"67","author":"Rodriguez-Molares","year":"2020","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib31","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1109\/TUFFC.2023.3289157","type":"journal-article","article-title":"Methods for enhancing the robustness of the generalized contrast-to-noise ratio","volume":"70","author":"Schlunk","year":"2023","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib32","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad997f","type":"journal-article","article-title":"RADD-CycleGAN: unsupervised reconstruction of high-quality ultrasound image based on CycleGAN with residual attention and dual-domain discrimination","volume":"69","author":"Si","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbae9689bib33","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acd236","type":"journal-article","article-title":"Constrained CycleGAN for effective generation of ultrasound sector images of improved spatial resolution","volume":"68","author":"Sun","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbae9689bib34","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1109\/58.935701","type":"journal-article","article-title":"Two-dimensional noise-robust blind deconvolution of ultrasound images","volume":"48","author":"Taxt","year":"2001","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib35","first-page":"9446","type":"conference-proceedings","article-title":"Deep image prior","author":"Ulyanov","year":"2018"},{"key":"pmbae9689bib36","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad29bb","type":"journal-article","article-title":"Coupling speckle noise suppression with image classification for deep-learning-aided ultrasound diagnosis Phys","volume":"69","author":"Wang","year":"2024","journal-title":"Med. Biol."},{"key":"pmbae9689bib37","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1109\/TUFFC.2012.2187","type":"journal-article","article-title":"A blind deconvolution approach to ultrasound imaging","volume":"59","author":"Yu","year":"2012","journal-title":"IEEE Trans. Ultrason. Ferroelectr. Freq. Control"},{"key":"pmbae9689bib38","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acdd4d","type":"journal-article","article-title":"Multibeam minimum variance beamforming for ring-array ultrasound imaging","volume":"68","author":"Zhang","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbae9689bib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102018","type":"journal-article","article-title":"Ultrasound image reconstruction from plane-wave radio-frequency data by self-supervised deep neural network","volume":"70","author":"Zhang","year":"2021","journal-title":"Med. Image Anal."},{"key":"pmbae9689bib40","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1109\/TBME.2019.2912986","type":"journal-article","article-title":"Image quality improvement of hand-held ultrasound devices with a two-stage generative adversarial network","volume":"67","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae9689","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae9689\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae9689\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae9689\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:23:58Z","timestamp":1787563438000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae9689"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":40,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8,24]]},"published-print":{"date-parts":[[2026,8,28]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae9689","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"An unsupervised physics-informed neural deconvolution framework for ultrasound imaging","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-03-26","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}