Scholarlink

<p>To 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&#xa0;mm/0.4&#xa0;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 <i>p</i> &lt; 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 <i>p</i> &gt; 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 <i>p</i> &lt; 0.001). Denoising did not alter PDS values in phantom or in vivo plaques (all pairwise <i>p</i> &gt; 0.006). Subjective image noise and diagnostic confidence improved across all reconstructions (all pairwise <i>p</i> &lt; 0.001). CNN-based denoising of UHR PCD-CT improves image quality of non-calcified coronary plaques, while preserving sharpness and quantitative stenosis metrics.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月10日

查看全文
  • Sardi Hyska,
  • Muhammad Taha Hagar,
  • José Osoria-Velasquez,
  • Nicola Fink,
  • Jens Ricke,
  • Moritz C. Halfmann,
  • Hugo Marques,
  • Elliot McVeigh,
  • George Wesbey,
  • Pál Maurovich-Horvat,
  • Bálint Szilveszter,
  • Tilman Emrich,
  • Akos Varga-Szemes,
  • Milan Vecsey-Nagy

摘要

To 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.