文献速递心血管胸部CT

深度学习降噪算法在经导管主动脉瓣植入CT成像中改善冠状动脉评估

Deep Learning Denoising Algorithm for Improved Assessment of Coronary Arteries in Transcatheter Aortic Valve Implantation CT Imaging.
PubMed 文献 · Acad Radiol · 2025-11-07

回顾性纳入200例严重主动脉瓣狭窄患者,评估深度学习降噪技术对TAVI术前CT冠状动脉图像质量和诊断准确性的影响。降噪图像信噪比和对比噪声比显著提高、噪声降低,主观评分更优,以侵入性冠状动脉造影为参考标准,降噪图像诊断冠状动脉疾病的AUC为90%,与标准图像无统计学显著差异(p=0.056)。

要点

  • 降噪重建显著提高信噪比(37.5±12.8 vs 12.3±4.1)和对比噪声比(45.3±15.4 vs 14.7±4.4),噪声降低(16.9±7.9 vs 47.9±11.6 HU)。
  • 降噪图像在锐利度、噪声、对比度和整体图像质量的主观评分均最高(均p<0.001)。
  • 降噪图像诊断冠状动脉疾病的每节段AUC为90%,与标准图像无统计学显著差异(p=0.056)。

核心结论

  • 深度学习降噪在TAVI术前CT中显著改善图像质量,且不影响冠状动脉评估的诊断准确性。

研究设计与样本

  • 回顾性纳入2022年10月至2024年4月间因严重主动脉瓣狭窄行TAVI术前CT扫描的200例患者,重建常规图像并使用专用软件生成降噪图像,以侵入性冠状动脉造影为参考标准。

关键影像表现/征象

  • 降噪重建较常规图像:信噪比37.5±12.8 vs 12.3±4.1,对比噪声比45.3±15.4 vs 14.7±4.4,噪声16.9±7.9 HU vs 47.9±11.6 HU(均p<0.001)。
  • 降噪图像在锐利度、噪声、对比度和整体图像质量的主观评分均最高(均p<0.001)。

诊断标准与关键数值

  • 共分析800支血管和1787个节段;降噪图像检测冠状动脉疾病的每节段AUC为90%(95%CI:88.5-91.3),准确率93.9%(95%CI:92.7-95),敏感度85.7%(95%CI:78.7-90.4),特异度94.7%(95%CI:93.5-95.7)。
  • 降噪图像与标准图像诊断性能比较无统计学显著差异(p=0.056)。

临床应用与阅片要点

  • 深度学习降噪可用于TAVI术前CT冠状动脉评估,在改善图像质量的同时不降低诊断准确性。

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

RATIONALE AND OBJECTIVES: To assess the impact of a deep learning-based noise reduction (DLD) technique on image quality and diagnostic accuracy for the evaluation of coronary arteries in transcatheter aortic valve implantation (TAVI) CT imaging.

MATERIALS AND METHODS: Two hundred patients with severe aortic stenosis who underwent CT scans for pre-TAVI planning between October 2022 and April 2024 were retrospectively enrolled. Conventional images were reconstructed and denoised images were generated using dedicated software. Objective image quality was evaluated by measuring the mean Hounsfield unit (HU) and standard deviation (SD) in regions of interest within the aortic root, coronary arteries, and subcutaneous fat to calculate signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). For subjective assessment, two readers used a 5-point Likert scoring system to evaluate sharpness, noise, contrast and overall image quality. The diagnostic performance of both datasets was assessed using invasive coronary angiography as reference standard.

RESULTS: Denoised reconstructions showed significantly higher SNR (37.5±12.8 vs.12.3±4.1) and CNR (45.3±15.4 vs. 14.7±4.4), and lower noise (16.9±7.9 vs. 47.9±11.6 HU) (all p<0.001). Subjective assessment demonstrated that denoised images received the highest score for sharpness, noise, contrast and overall image quality (all p<0.001). For the evaluation of diagnostic accuracy, a total of 800 vessels and 1787 segments were analyzed. The per-segment diagnostic performance of the DLD for detection of CAD revealed an AUC of 90% (95% CI: 88.5-91.3), with accuracy of 93.9% (95% CI: 92.7-95), 85.7% (95% CI: 78.7-90.4) sensitivity and 94.7% (95% CI: 93.5-95.7) specificity, in the absence of a statistically significant difference compared with the evaluation performed on standard images (p=0.056).

CONCLUSION: The DLD substantially improves image quality without affecting diagnostic accuracy for the evaluation of coronary arteries in patients undergoing pre-TAVI CT scans.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Lanzafame LRM, Steinmetz S, D'Angelo T, et al. Deep Learning Denoising Algorithm for Improved Assessment of Coronary Arteries in Transcatheter Aortic Valve Implantation CT Imaging. Acad Radiol. 2025. PMID: 41206269. doi:10.1016/j.acra.2025.10.030

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。