{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:02:18Z","timestamp":1792785738093,"version":"4.5.0"},"reference-count":43,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Danmarks Frie Forskningsfond","award":["10.46540\/3165-00237B"],"award-info":[{"award-number":["10.46540\/3165-00237B"]}],"id":[{"id":"https:\/\/ror.org\/05svhj534","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objectives.<\/jats:italic>\n                    Cone-beam computed tomography (CBCT) is widely used in dental and maxillofacial imaging, but low-dose acquisition introduces strong, spatially varying noise that degrades soft-tissue visibility and obscures fine anatomical structures. Classical denoising methods struggle to suppress noise in CBCT while preserving edges. Although deep learning (DL)-based approaches offer high-fidelity restoration, their use in CBCT denoising is limited by the scarcity of high-resolution CBCT data for supervised training. This study aims to develop an efficient DL framework for high-quality CBCT denoising that effectively suppresses noise while preserving fine anatomical structures and maintaining computational efficiency for practical clinical deployment.\n                    <jats:italic>Approach.<\/jats:italic>\n                    To achieve this objective, we propose a novel Hybrid Attention Residual U-Net (HARU-Net) for high-quality denoising of CBCT data, trained on a cadaver dataset of human hemimandibles acquired using a high-resolution protocol of the 3D Accuitomo 170 (J. Morita, Kyoto, Japan) CBCT system. The novel contribution of this approach is the integration of three complementary architectural components: (i) a hybrid attention transformer block embedded within each skip connection to selectively emphasize salient anatomical features, (ii) a residual hybrid attention transformer group at the bottleneck to strengthen global contextual modeling and long-range feature interactions, and (iii) residual learning convolutional blocks to facilitate deeper, more stable feature extraction throughout the network.\n                    <jats:italic>Results.<\/jats:italic>\n                    HARU-Net\n                    <jats:sup>1<\/jats:sup>\n                    <jats:fn id=\"bpexae9c46fn2\">\n                      <jats:label>1<\/jats:label>\n                      <jats:p>\n                        <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/DrKay87\/HARU-Net-Hybrid-Attention-Residual-U-Net-for-Denoising-in-Cone-Beam-Computed-Tomography\">https:\/\/github.com\/DrKay87\/HARU-Net\u2013Hybrid-Attention-Residual-U-Net-for-Denoising-in-Cone-Beam-Computed-Tomography<\/jats:ext-link>\n                        .\n                      <\/jats:p>\n                    <\/jats:fn>\n                    consistently outperforms state-of-the-art methods achieving the highest peak signal-to-noise ratio (37.52 dB), the second-highest SSIM (0.9557), and the lowest GMSD (0.1084). Compared with transformer-based methods, the proposed network achieves superior denoising performance while maintaining substantially lower computational complexity.\n                    <jats:italic>Conclusion.<\/jats:italic>\n                    The proposed HARU-Net provides an effective balance between noise suppression, anatomical structure preservation, and computational efficiency. These characteristics make it a promising and practical solution for improving image quality and supporting reliable diagnosis in low-dose CBCT imaging.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae9c46","type":"journal-article","created":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T22:48:18Z","timestamp":1787266098000},"page":"055016","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HARU-Net: hybrid attention residual U-Net for edge-preserving denoising in cone-beam computed tomography"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8286-6139","authenticated-orcid":true,"given":"Khuram","family":"Naveed","sequence":"first","affiliation":[{"name":"Aarhus University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9462-7546","authenticated-orcid":true,"given":"Ruben","family":"Pauwels","sequence":"additional","affiliation":[{"name":"Aarhus University"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]}],"member":"266","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"bpexae9c46bib1","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1016\/j.cden.2008.05.005","type":"journal-article","volume":"52","author":"Scarfe","year":"2008","journal-title":"Dent. Clin. North Am."},{"key":"bpexae9c46bib2","doi-asserted-by":"publisher","DOI":"10.1259\/dmfr.20140224","type":"journal-article","volume":"44","author":"Pauwels","year":"2015","journal-title":"Dentomaxillofac. Radiol."},{"key":"bpexae9c46bib3","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1016\/j.ejrad.2010.11.028","type":"journal-article","volume":"81","author":"Pauwels","year":"2012","journal-title":"Eur. J. Radiol."},{"key":"bpexae9c46bib4","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1259\/dmfr\/30642039","type":"journal-article","volume":"40","author":"Schulze","year":"2011","journal-title":"Dentomaxillofac. Radiol."},{"key":"bpexae9c46bib5","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.radonc.2021.07.027","type":"journal-article","volume":"163","author":"Bryce-Atkinson","year":"2021","journal-title":"Radiother. Oncol."},{"key":"bpexae9c46bib6","doi-asserted-by":"publisher","first-page":"213","DOI":"10.2967\/jnmt.106.037846","type":"journal-article","volume":"35","author":"Goldman","year":"2007","journal-title":"J. Nucl. Med. Technol."},{"key":"bpexae9c46bib7","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.oooo.2015.10.017","type":"journal-article","volume":"121","author":"Pauwels","year":"2016","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"bpexae9c46bib8","doi-asserted-by":"publisher","first-page":"R63","DOI":"10.1088\/0031-9155\/58\/12\/R63","type":"journal-article","volume":"58","author":"Nuyts","year":"2013","journal-title":"Phys. Med. Biol."},{"key":"bpexae9c46bib9","author":"Kalender","year":"2011","type":"book"},{"key":"bpexae9c46bib10","doi-asserted-by":"publisher","first-page":"428","DOI":"10.4103\/jiaomr.jiaomr_142_22","type":"journal-article","volume":"34","author":"Mahesh","year":"2022","journal-title":"J. Indian Acad. Oral Med. Radiol."},{"key":"bpexae9c46bib11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.14428\/nemesis.v11i1.54393","type":"journal-article","volume":"11","author":"Olszewski","year":"2020","journal-title":"Nemesis. Negat. Eff. Med. Sci. Oral Maxillofac. Surg."},{"key":"bpexae9c46bib12","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2026.111126","type":"journal-article","volume":"127","author":"Naveed","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae9c46bib13","doi-asserted-by":"publisher","first-page":"164344","DOI":"10.1109\/ACCESS.2019.2953259","type":"journal-article","volume":"7","author":"Khawaja","year":"2019","journal-title":"IEEE Access"},{"key":"bpexae9c46bib14","doi-asserted-by":"publisher","first-page":"114","DOI":"10.3390\/diagnostics11010114","type":"journal-article","volume":"11","author":"Naveed","year":"2021","journal-title":"Diagnostics"},{"key":"bpexae9c46bib15","doi-asserted-by":"publisher","first-page":"206","DOI":"10.3390\/s19010206","type":"journal-article","volume":"19","author":"Naveed","year":"2019","journal-title":"Sensors"},{"key":"bpexae9c46bib16","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/ICASSPW62465.2024.10627237","type":"conference-proceedings","article-title":"Low dose CBCT denoising using a 3D u-net","author":"Yunker","year":"2024"},{"key":"bpexae9c46bib17","doi-asserted-by":"publisher","first-page":"9844","DOI":"10.21037\/qims-24-1902","type":"journal-article","volume":"15","author":"Zhao","year":"2025","journal-title":"Quant. Imaging Med. Surgery"},{"key":"bpexae9c46bib18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdent.2026.106385","type":"journal-article","volume":"167","author":"Naveed","year":"2026","journal-title":"J. Dent."},{"key":"bpexae9c46bib19","doi-asserted-by":"publisher","first-page":"4214","DOI":"10.3390\/jcm14124214","type":"journal-article","volume":"14","author":"Wajer","year":"2025","journal-title":"J. Clin. Med."},{"key":"bpexae9c46bib20","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.ejmp.2021.07.007","type":"journal-article","volume":"88","author":"Kaasalainen","year":"2021","journal-title":"Phys. Medica"},{"key":"bpexae9c46bib21","article-title":"Advancing the frontiers of deep learning for low-dose 3d cone-beam ct reconstruction","author":"Biguri","year":"2023","type":"other"},{"key":"bpexae9c46bib22","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/embc46164.2021.9629859","type":"conference-proceedings","article-title":"Self-supervised projection denoising for low-dose cone-beam ct 2021","author":"Choi","year":"2021"},{"key":"bpexae9c46bib23","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1117\/12.2652826","type":"book","volume":"12463","author":"Yun","year":"2023"},{"key":"bpexae9c46bib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.109221","type":"journal-article","volume":"183","author":"Zanini","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"bpexae9c46bib25","author":"Chen","year":"2023","type":"preprint"},{"key":"bpexae9c46bib26","doi-asserted-by":"publisher","first-page":"1833","DOI":"10.1109\/ICCVW54120.2021.00210","type":"conference-proceedings","author":"Liang","year":"2021"},{"key":"bpexae9c46bib27","doi-asserted-by":"publisher","first-page":"17683","DOI":"10.1109\/CVPR52688.2022.01716","type":"conference-proceedings","article-title":"Uformer: a general u-shaped transformer for image restoration","author":"Wang","year":"2022"},{"key":"bpexae9c46bib28","author":"Kak","year":"2001","type":"book"},{"key":"bpexae9c46bib29","doi-asserted-by":"publisher","first-page":"2225","DOI":"10.5120\/12675-9373","type":"journal-article","volume":"22245782","author":"Ajala Funmilola","year":"2012","journal-title":"J. Inf. Eng. Appl."},{"key":"bpexae9c46bib30","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/0734-189X(85)90016-7","type":"journal-article","volume":"30","author":"Suzuki","year":"1985","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"bpexae9c46bib31","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/S0734-189X(85)90153-7","type":"journal-article","volume":"29","author":"Haralick","year":"1985","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"bpexae9c46bib32","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.1109\/ICCV48922.2021.00986","type":"conference-proceedings","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"bpexae9c46bib33","volume":"vol 30","author":"Vaswani","year":"2017","type":"other"},{"key":"bpexae9c46bib34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","type":"conference-proceedings","article-title":"CBAM: Convolutional Block Attention Module","volume":"Vol 6","author":"Woo","year":"2018"},{"key":"bpexae9c46bib35","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","type":"journal-article","article-title":"Attention mechanisms in computer vision: a survey","volume":"8","author":"Guo","year":"2022","journal-title":"Comp. Visual Media"},{"key":"bpexae9c46bib36","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1111\/iej.13115","type":"journal-article","volume":"52","author":"Patel","year":"2019","journal-title":"Int. Endod. J."},{"key":"bpexae9c46bib37","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.5395\/rde.2024.49.e1","type":"journal-article","volume":"49","author":"R\u00edos-Osorio","year":"2023","journal-title":"Restor. Dent. Endod."},{"key":"bpexae9c46bib38","doi-asserted-by":"publisher","DOI":"10.1259\/dmfr.20150078","type":"journal-article","volume":"44","author":"Pauwels","year":"2015","journal-title":"Dentomaxillofac. Radiol."},{"key":"bpexae9c46bib39","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/797286","type":"journal-article","volume":"2013","author":"Camilo","year":"2013","journal-title":"Case Rep. Dent."},{"key":"bpexae9c46bib40","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1007\/s44445-025-00077-0","type":"journal-article","volume":"10","author":"Chung","year":"2024","journal-title":"Heliyon"},{"key":"bpexae9c46bib41","doi-asserted-by":"publisher","first-page":"20","DOI":"10.5856\/JKDS.2019.12.1.20","type":"journal-article","volume":"12","author":"Lee","year":"2019","journal-title":"J. Korean Dental Sci."},{"key":"bpexae9c46bib42","doi-asserted-by":"publisher","first-page":"567","DOI":"10.4329\/wjr.v6.i8.567","type":"journal-article","volume":"6","author":"Bag","year":"2014","journal-title":"World J. Radiol."},{"key":"bpexae9c46bib43","doi-asserted-by":"publisher","DOI":"10.1259\/dmfr.20180044","type":"journal-article","volume":"48","author":"Zhu","year":"2019","journal-title":"Dentomaxillofac. Radiol."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T06:44:44Z","timestamp":1789627484000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae9c46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,9,17]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae9c46","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2057-1976\/AE9C46\/v2\/decision1","asserted-by":"object"}]},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]},"assertion":[{"value":"HARU-Net: hybrid attention residual U-Net for edge-preserving denoising in cone-beam computed tomography","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-03-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-20","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-17","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}