{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:09:23Z","timestamp":1792782563085,"version":"4.5.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Karolinska Institute","id":[{"id":"https:\/\/ror.org\/056d84691","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neuroradiology"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Deep learning (DL) denoising may improve cone-beam CT (CBCT) image quality for point-of-care stroke assessment in the interventional suite. The purpose of this study was to evaluate the impact of a DL-based denoising algorithm on objective and subjective image quality in brain CBCT using both standard circular and advanced dual-axis trajectories.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 20 noncontrast brain CBCT acquisitions (Karolinska: 10 standard circular; St Michael's: 10 dual-axis). A DL-based denoising algorithm was applied at three strengths (Minimal, Medium, High) and compared to standard images with no additional denoising. Objective metrics (noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), artifact indices) were measured using standardized ROIs. Six experts rated subjective image quality on 5-point Likert scales. Paired tests with Bonferroni correction were used for comparisons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      High-level DL denoising significantly improved all objective metrics (noise, SNR, CNR, artifact indices) for both thin and thick slices (all\n                      <jats:italic>p<\/jats:italic>\n                      &lt;.001). It doubled gray\u2013white matter CNR (thin slices: 2.31 vs. 1.08), reduced noise, and improved subcalvarial and posterior fossa artifact indices. Subjectively, high-level denoising yielded higher median ratings for noise, texture, sharpness, brain parenchyma visualization, CSF spaces, and confidence in assessing ischemia and hemorrhage (all\n                      <jats:italic>p<\/jats:italic>\n                      &lt;.001). Improvements were consistent for both acquisition techniques, and perceived artifact severity did not differ (\n                      <jats:italic>p<\/jats:italic>\n                      &gt;.99). Inter-reader agreement was substantial.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The DL-based denoising algorithm significantly improved objective and subjective brain CBCT image-quality; no difference in perceived artifact severity was detected. These findings support further evaluation of deep learning-enhanced CBCT denoising for brain imaging in the interventional suite.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00234-026-04148-9","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T06:38:15Z","timestamp":1787553495000},"page":"3083-3091","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Brain cone-beam CT image quality improvement using a deep-learning-based denoising method: a multicenter retrospective study"],"prefix":"10.1007","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9690-0286","authenticated-orcid":false,"given":"Fredrik","family":"St\u00e5hl","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicole M.","family":"Cancelliere","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jens","family":"Kolloch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shobhit","family":"Mathur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ibrahim Abdulaziz","family":"Almulhim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Janot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vamsi","family":"Gontu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolas D.","family":"Schnellb\u00e4cher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marijke","family":"van Vlimmeren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Hummel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vitor M.","family":"Pereira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Falk Delgado","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,24]]},"reference":[{"issue":"Suppl 2","key":"4148_CR1","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s00062-015-0423-x","volume":"25","author":"A Doerfler","year":"2015","unstructured":"Doerfler A, Golitz P, Engelhorn T, Kloska S, Struffert T (2015) Flat-Panel Computed Tomography (DYNA-CT) in Neuroradiology. From High-Resolution Imaging of Implants to One-Stop-Shopping for Acute Stroke. Clin Neuroradiol 25(Suppl 2):291\u2013297. https:\/\/doi.org\/10.1007\/s00062-015-0423-x","journal-title":"Clin Neuroradiol"},{"issue":"11","key":"4148_CR2","doi-asserted-by":"publisher","first-page":"3152","DOI":"10.1161\/strokeaha.117.018077","volume":"48","author":"MN Psychogios","year":"2017","unstructured":"Psychogios MN, Behme D, Schregel K, Tsogkas I, Maier IL, Leyhe JR et al (2017) One-Stop Management of Acute Stroke Patients: Minimizing Door-to-Reperfusion Times. Stroke 48(11):3152\u20133155. https:\/\/doi.org\/10.1161\/strokeaha.117.018077","journal-title":"Stroke"},{"key":"4148_CR3","doi-asserted-by":"publisher","unstructured":"Eckert M, Golitz P, Lucking H, Struffert T, Knossalla F, Doerfler A (2017) Optimized flat-detector CT in stroke imaging: ready for first-line use? Cerebrovasc Dis (Basel, Switzerland) 43(1\u20132):9\u201316. https:\/\/doi.org\/10.1159\/000450727","DOI":"10.1159\/000450727"},{"key":"4148_CR4","doi-asserted-by":"publisher","unstructured":"Psychogios MN, Buhk JH, Schramm P, Xyda A, Mohr A, Knauth M (2010) Feasibility of angiographic CT in peri-interventional diagnostic imaging: a comparative study with multidetector CT. AJNR Am J Neuroradiol 31(7):1226-31. https:\/\/doi.org\/10.3174\/ajnr.A2086","DOI":"10.3174\/ajnr.A2086"},{"issue":"5","key":"4148_CR5","doi-asserted-by":"publisher","first-page":"881","DOI":"10.3174\/ajnr.A5595","volume":"39","author":"IL Maier","year":"2018","unstructured":"Maier IL, Leyhe JR, Tsogkas I, Behme D, Schregel K, Knauth M et al (2018) Diagnosing Early Ischemic Changes with the Latest-Generation Flat Detector CT: A Comparative Study with Multidetector CT. AJNR Am J Neuroradiol 39(5):881\u2013886. https:\/\/doi.org\/10.3174\/ajnr.A5595","journal-title":"AJNR Am J Neuroradiol"},{"key":"4148_CR6","doi-asserted-by":"publisher","first-page":"109645","DOI":"10.1016\/j.ejrad.2021.109645","volume":"138","author":"P Nicholson","year":"2021","unstructured":"Nicholson P, Cancelliere NM, Bracken J, Hummel E, van Nijnatten F, Withagen P et al (2021) Novel flat-panel cone-beam CT compared to multi-detector CT for assessment of acute ischemic stroke: A prospective study. Eur J Radiol 138:109645. https:\/\/doi.org\/10.1016\/j.ejrad.2021.109645","journal-title":"Eur J Radiol"},{"issue":"4","key":"4148_CR7","doi-asserted-by":"publisher","first-page":"929","DOI":"10.1007\/s00062-024-01439-7","volume":"34","author":"F St\u00e5hl","year":"2024","unstructured":"St\u00e5hl F, Almqvist H, Aspelin \u00c5, Kolloch J, Ghalamkari O, Gontu V et al (2024) Stroke Evaluation in the Interventional Suite Using Dual-Layer Detector Cone-Beam CT: a First-in-human Prospective Cohort Study (the Next Generation X-ray Imaging System Trial). Clin Neuroradiol 34(4):929\u2013937. https:\/\/doi.org\/10.1007\/s00062-024-01439-7","journal-title":"Clin Neuroradiol"},{"key":"4148_CR8","doi-asserted-by":"publisher","unstructured":"Cancelliere NM, Hummel E, van Nijnatten F, van de Haar P, Withagen P, van Vlimmeren M et al (2022) The butterfly effect: improving brain cone-beam CT image artifacts for stroke assessment using a novel dual-axis trajectory. J Neurointerv Surg Neurintsurg\u20132021. https:\/\/doi.org\/10.1136\/neurintsurg-2021-018553","DOI":"10.1136\/neurintsurg-2021-018553"},{"key":"4148_CR9","doi-asserted-by":"publisher","DOI":"10.1136\/neurintsurg-2021-018312","author":"VD Petroulia","year":"2022","unstructured":"Petroulia VD, Kaesmacher J, Piechowiak EI, Dobrocky T, Pilgram-Pastor SM, Gralla J et al (2022) Evaluation of Sine Spin flat detector CT imaging compared with multidetector CT. J neurointerventional Surg. https:\/\/doi.org\/10.1136\/neurintsurg-2021-018312","journal-title":"J neurointerventional Surg"},{"key":"4148_CR10","doi-asserted-by":"publisher","unstructured":"Cancelliere NM, Nijnatten Fv, Hummel E, Withagen P, Haar Pvd, Nishi H et al Motion artifact correction for cone beam CT stroke imaging: a prospective series. J Neurointerv Surg. https:\/\/doi.org\/10.1136\/jnis-2021-018201.\u00a02022:neurintsurg-2021-018201","DOI":"10.1136\/jnis-2021-018201"},{"issue":"3","key":"4148_CR11","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s00234-015-1631-4","volume":"58","author":"T Nakaura","year":"2016","unstructured":"Nakaura T, Iyama Y, Kidoh M, Yokoyama K, Oda S, Tokuyasu S et al (2016) Comparison of iterative model, hybrid iterative, and filtered back projection reconstruction techniques in low-dose brain CT: impact of thin-slice imaging. Neuroradiology 58(3):245\u2013251. https:\/\/doi.org\/10.1007\/s00234-015-1631-4","journal-title":"Neuroradiology"},{"issue":"6","key":"4148_CR12","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1007\/s00234-020-02574-x","volume":"63","author":"I Kim","year":"2021","unstructured":"Kim I, Kang H, Yoon HJ, Chung BM, Shin NY (2021) Deep learning-based image reconstruction for brain CT: improved image quality compared with adaptive statistical iterative reconstruction-Veo (ASIR-V). Neuroradiology 63(6):905\u2013912. https:\/\/doi.org\/10.1007\/s00234-020-02574-x","journal-title":"Neuroradiology"},{"issue":"4","key":"4148_CR13","doi-asserted-by":"publisher","first-page":"1536","DOI":"10.1007\/s00261-023-03845-w","volume":"48","author":"JJ Xu","year":"2023","unstructured":"Xu JJ, L\u00f6nn L, Budtz-J\u00f8rgensen E, Jawad S, Ulriksen PS, Hansen KL (2023) Evaluation of thin-slice abdominal DECT using deep-learning image reconstruction in 74\u00a0keV virtual monoenergetic images: an image quality comparison. Abdom Radiol 48(4):1536\u20131544. https:\/\/doi.org\/10.1007\/s00261-023-03845-w","journal-title":"Abdom Radiol"},{"issue":"8","key":"4148_CR14","doi-asserted-by":"publisher","first-page":"5052","DOI":"10.1002\/mp.15807","volume":"49","author":"J Greffier","year":"2022","unstructured":"Greffier J, Si-Mohamed S, Frandon J, Loisy M, de Oliveira F, Beregi JP et al (2022) Impact of an artificial intelligence deep-learning reconstruction algorithm for CT on image quality and potential dose reduction: A phantom study. Med Phys 49(8):5052\u20135063. https:\/\/doi.org\/10.1002\/mp.15807","journal-title":"Med Phys"},{"issue":"6","key":"4148_CR15","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1364\/JOSAA.1.000612","volume":"1","author":"LA Feldkamp","year":"1984","unstructured":"Feldkamp LA, Davis LC, Kress JW (1984) Practical cone-beam algorithm. J Opt Soc Am A 1(6):612\u2013619. https:\/\/doi.org\/10.1364\/JOSAA.1.000612","journal-title":"J Opt Soc Am A"},{"issue":"7","key":"4148_CR16","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","volume":"26","author":"K Zhang","year":"2017","unstructured":"Zhang K, Zuo W, Chen Y, Meng D, Zhang L (2017) Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Trans Image Process 26(7):3142\u20133155. https:\/\/doi.org\/10.1109\/TIP.2017.2662206","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"4148_CR17","doi-asserted-by":"publisher","first-page":"031102","DOI":"10.1118\/1.4789628","volume":"40","author":"S \u017dabi\u0107","year":"2013","unstructured":"\u017dabi\u0107 S, Wang Q, Morton T, Brown KM (2013) A low dose simulation tool for CT systems with energy integrating detectors. Med Phys 40(3):031102. https:\/\/doi.org\/10.1118\/1.4789628","journal-title":"Med Phys"},{"issue":"1","key":"4148_CR18","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1148\/radiol.12111604","volume":"266","author":"SR Pomerantz","year":"2013","unstructured":"Pomerantz SR, Kamalian S, Zhang D, Gupta R, Rapalino O, Sahani DV et al (2013) Virtual monochromatic reconstruction of dual-energy unenhanced head CT at 65\u201375\u00a0keV maximizes image quality compared with conventional polychromatic CT. Radiology 266(1):318\u2013325. https:\/\/doi.org\/10.1148\/radiol.12111604","journal-title":"Radiology"},{"issue":"8","key":"4148_CR19","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1097\/rli.0000000000000367","volume":"52","author":"V Neuhaus","year":"2017","unstructured":"Neuhaus V, Abdullayev N, Grosse Hokamp N, Pahn G, Kabbasch C, Mpotsaris A et al (2017) Improvement of Image Quality in Unenhanced Dual-Layer CT of the Head Using Virtual Monoenergetic Images Compared With Polyenergetic Single-Energy CT. Invest Radiol 52(8):470\u2013476. https:\/\/doi.org\/10.1097\/rli.0000000000000367","journal-title":"Invest Radiol"},{"issue":"1","key":"4148_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006X126600","volume":"61","author":"KL Gwet","year":"2008","unstructured":"Gwet KL (2008) Computing inter-rater reliability and its variance in the presence of high agreement. Br J Math Stat Psychol 61(1):29\u201348. https:\/\/doi.org\/10.1348\/000711006X126600","journal-title":"Br J Math Stat Psychol"},{"issue":"12","key":"4148_CR21","doi-asserted-by":"publisher","first-page":"8776","DOI":"10.1002\/mp.17379","volume":"51","author":"E Eulig","year":"2024","unstructured":"Eulig E, Ommer B, Kachelrie\u00df M (2024) Benchmarking deep learning-based low-dose CT image denoising algorithms. Med Phys 51(12):8776\u20138788. https:\/\/doi.org\/10.1002\/mp.17379","journal-title":"Med Phys"},{"issue":"2","key":"4148_CR22","doi-asserted-by":"publisher","first-page":"e14270","DOI":"10.1002\/acm2.14270","volume":"25","author":"RT Sadia","year":"2024","unstructured":"Sadia RT, Chen J, Zhang J (2024) CT image denoising methods for image quality improvement and radiation dose reduction. J Appl Clin Med Phys 25(2):e14270. https:\/\/doi.org\/10.1002\/acm2.14270","journal-title":"J Appl Clin Med Phys"},{"key":"4148_CR23","doi-asserted-by":"publisher","first-page":"107708","DOI":"10.1016\/j.cmpb.2023.107708","volume":"240","author":"K Kim","year":"2023","unstructured":"Kim K, Lim CY, Shin JB, Chung MJ, Jung YG (2023) Enhanced artificial intelligence-based diagnosis using CBCT with internal denoising: clinical validation for discrimination of fungal ball, sinusitis, and normal cases in the maxillary sinus. Comput Methods Programs Biomed 240:107708. https:\/\/doi.org\/10.1016\/j.cmpb.2023.107708","journal-title":"Comput Methods Programs Biomed"}],"container-title":["Neuroradiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00234-026-04148-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00234-026-04148-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00234-026-04148-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T05:54:33Z","timestamp":1792389273000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00234-026-04148-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,24]]},"references-count":23,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["4148"],"URL":"https:\/\/doi.org\/10.1007\/s00234-026-04148-9","relation":{},"ISSN":["0028-3940","1432-1920"],"issn-type":[{"value":"0028-3940","type":"print"},{"value":"1432-1920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,24]]},"assertion":[{"value":"11 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Partial financial support was received from Philips Healthcare. The funder had no involvement in the collection, analysis, or interpretation of the data, nor in the decision to submit the paper for publication. Co-authors NDS, MvV and EH are employees of Philips. The other authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}]}}