文献速递心血管CTDSA

超分辨率深度学习重建改善冠状动脉CT血管成像图像质量

Super-Resolution Deep Learning Reconstruction for Improved Image Quality of Coronary CT Angiography.
PubMed 文献 · Radiol Cardiothorac Imaging · 2023-08-17

回顾性纳入58例患者,比较超分辨率深度学习重建(SR-DLR)与常规深度学习重建(C-DLR)的冠脉CTA图像噪声、边缘锐利度及狭窄分级与有创冠脉造影的一致性。SR-DLR使图像噪声降低31%,信噪比与边缘锐利度显著提高,支架FWHM更薄,狭窄分级一致性加权κ值为0.83(C-DLR为0.77)。

要点

  • SR-DLR较C-DLR图像噪声降低31%(12.6 HU vs 18.2 HU),信噪比与边缘锐利度显著提高。
  • SR-DLR支架FWHM为0.72 mm,较C-DLR的1.01 mm显著变薄。
  • SR-DLR的冠脉狭窄分级与ICA一致性加权κ=0.83,高于C-DLR的κ=0.77。

核心结论

  • 与C-DLR相比,SR-DLR改善了血管锐利度、图像噪声及冠状动脉狭窄分级的准确性。

研究设计与样本

  • 回顾性研究纳入58例患者(平均年龄69.0岁±12.8,男38例、女20例),2022年4月至9月使用320排CT行CCTA,所有图像分别以SR-DLR和C-DLR重建,以有创冠状动脉造影(ICA)为参考标准。

关键影像表现/征象

  • SR-DLR图像噪声为12.6 HU±2.3,C-DLR为18.2 HU±1.9,SR-DLR降低31%(P<.001)。
  • SR-DLR信噪比为38.7±8.3,C-DLR为26.2±4.6(P<.001)。
  • SR-DLR边缘锐利度为560 HU/mm±191,C-DLR为463 HU/mm±164(P<.001)。
  • SR-DLR支架FWHM为0.72 mm±0.22,C-DLR为1.01 mm±0.21(P<.001)。

诊断标准与关键数值

  • 狭窄程度视觉分级为0至5级,5级表示闭塞。
  • CCTA与ICA狭窄分级一致性:SR-DLR加权κ=0.83,C-DLR加权κ=0.77。

临床应用与阅片要点

  • 原文结论为SR-DLR较C-DLR改善了血管锐利度、图像噪声和冠状动脉狭窄分级准确性。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

PURPOSE: To investigate image noise and edge sharpness of coronary CT angiography (CCTA) with super-resolution deep learning reconstruction (SR-DLR) compared with conventional DLR (C-DLR) and to evaluate agreement in stenosis grading using CCTA with that from invasive coronary angiography (ICA) as the reference standard.

MATERIALS AND METHODS: This retrospective study included 58 patients (mean age, 69.0 years ± 12.8 [SD]; 38 men, 20 women) who underwent CCTA using 320-row CT between April and September 2022. All images were reconstructed with two different algorithms: SR-DLR and C-DLR. Image noise, signal-to-noise ratio, edge sharpness, full width at half maximum (FWHM) of stent, and agreement in stenosis grading with that from ICA were compared. Stenosis was visually graded from 0 to 5, with 5 indicating occlusion.

RESULTS: SR-DLR significantly decreased image noise by 31% compared with C-DLR (12.6 HU ± 2.3 vs 18.2 HU ± 1.9; P < .001). Signal-to-noise ratio and edge sharpness were significantly improved by SR-DLR compared with C-DLR (signal-to-noise ratio, 38.7 ± 8.3 vs 26.2 ± 4.6; P < .001; edge sharpness, 560 HU/mm ± 191 vs 463 HU/mm ± 164; P < .001). The FWHM of stent was significantly thinner on SR-DLR (0.72 mm ± 0.22) than on C-DLR (1.01 mm ± 0.21; P < .001). Agreement in stenosis grading between CCTA and ICA was improved on SR-DLR compared with C-DLR (weighted κ = 0.83 vs 0.77).

CONCLUSION: SR-DLR improved vessel sharpness, image noise, and accuracy of coronary stenosis grading compared with the C-DLR technique.Keywords: CT Angiography, Cardiac, Coronary Arteries Supplemental material is available for this article. © RSNA, 2023.

来源:Radiol Cardiothorac Imaging,查看原文。版权归原作者所有。

引用

  1. Takafuji M, Kitagawa K, Mizutani S, et al. Super-Resolution Deep Learning Reconstruction for Improved Image Quality of Coronary CT Angiography. Radiol Cardiothorac Imaging. 2023. PMID: 37693207. doi:10.1148/ryct.230085

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。