Logo do repositório
 
Publicação

Deep-learning denoising for ultrahigh-resolution photon-counting detector CT: phantom and in vivo evaluation of non-calcified coronary plaques

2026-07-10Artigo de investigação Acesso aberto
Ver registo simples
dc.contributor.authorHyska, Sardi
dc.contributor.authorHagar, Muhammad Taha
dc.contributor.authorOsoria-Velasquez, José
dc.contributor.authorFink, Nicola
dc.contributor.authorRicke, Jens
dc.contributor.authorHalfmann, Moritz C.
dc.contributor.authorMarques, Hugo
dc.contributor.authorMcVeigh, Elliot
dc.contributor.authorWesbey, George
dc.contributor.authorMaurovich-Horvat, Pál
dc.contributor.authorSzilveszter, Bálint
dc.contributor.authorEmrich, Tilman
dc.contributor.authorVarga-Szemes, Akos
dc.contributor.authorVecsey-Nagy, Milan
dc.date.accessioned2026-07-17T16:07:32Z
dc.date.available2026-07-17T16:07:32Z
dc.date.issued2026-07-10
dc.description.abstractTo assess the value of convolutional neural network (CNN)-based denoising for the evaluation of non-calcified coronary plaques on ultrahigh-resolution (UHR) photon-counting detector (PCD) coronary CT angiography (CCTA). A dynamic phantom containing lipid-rich and fibrotic plaques with 50%-diameter stenosis (PDS) was scanned on PCD-CT under varying conditions. For in-vivo imaging, consecutive patients with non-calcified coronary plaques (NCPs) who underwent CCTA with PCD-CT were included. Image series were reconstructed using a sharp vascular kernel (Bv64) with slice thicknesses of 0.2 mm/0.4 mm, quantum iterative reconstruction (QIR) levels 3/4, and with/without CNN denoising. Phantom-based line-profile analysis yielded edge-width at half maximum (EWHM) and 10–90% rise distance as sharpness metrics. Plaque contrast-to-noise ratio (CNR) and PDS were assessed in the phantom and in patients. Two readers evaluated subjective image quality (noise, diagnostic confidence) using a four-point Likert scale. Pairwise comparisons were performed using a Bonferroni-corrected p < 0.002 for significance. Fifty-five patients (median age 74 [66.5–78] years; 19 women) with 97 NCPs were included. Phantom-based sharpness metrics remained unchanged after denoising (all pairwise p > 0.051). CNN denoising increased plaque CNR consistently in the phantom (fibrotic: 0.80–1.64 to 0.92–2.06; lipid-rich: 0.21–0.34 to 0.35–0.46) and in vivo (0.99–2.07 to 1.37–2.92, all pairwise p < 0.001). Denoising did not alter PDS values in phantom or in vivo plaques (all pairwise p > 0.006). Subjective image noise and diagnostic confidence improved across all reconstructions (all pairwise p < 0.001). CNN-based denoising of UHR PCD-CT improves image quality of non-calcified coronary plaques, while preserving sharpness and quantitative stenosis metrics.eng
dc.identifier.doi10.1007/s10554-026-03774-x
dc.identifier.eid105044359482
dc.identifier.other52d107bc-c983-4cdb-ad50-2891c23cc901
dc.identifier.pmid42430068
dc.identifier.urihttp://hdl.handle.net/10400.14/58751
dc.identifier.wos001817364500001
dc.language.isoeng
dc.peerreviewedyes
dc.publisherSpringer Science and Business Media B.V.
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectCoronary artery diseaseeng
dc.subjectCoronary computed tomography angiographyeng
dc.subjectNon-calcified plaqueeng
dc.subjectPhoton-counting detectoreng
dc.subjectUltrahigh-resolutioneng
dc.titleDeep-learning denoising for ultrahigh-resolution photon-counting detector CT: phantom and in vivo evaluation of non-calcified coronary plaques
dc.typeresearch article
dspace.entity.typePublication
oaire.versionhttp://purl.org/coar/version/c_ab4af688f83e57aa

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
155725466.pdf
Tamanho:
1.65 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

FM - Contribuições em Revistas Científicas / Contribution to Journals