文献速递腹部技术与安全CT

深度学习降噪对低剂量腹部CT诊断急性阑尾炎图像质量与诊断效能的影响

Effectiveness of deep learning-based denoising on image quality and diagnostic performance of low-dose abdominal CT for acute appendicitis.
PubMed 文献 · Eur J Radiol · 2026-06-24

本单中心回顾性研究纳入100例疑似急性阑尾炎行低剂量腹部CT的患者,比较FBP、IR及其经深度学习降噪处理后的四组图像。结果显示降噪后图像噪声、信噪比及主观质量均改善,降噪FBP总体质量最佳。各组诊断急性阑尾炎的敏感度与特异度无显著差异,降噪组特异度数值上更高。

要点

  • 降噪FBP主观总体图像质量最佳,可优先用于低剂量腹部CT阅片
  • 深度学习降噪未显著改变急性阑尾炎诊断效能,降噪组特异度数值上更高
  • 降噪IR定量噪声最低,信噪比最高

核心结论

  • 深度学习降噪可改善低剂量腹部CT的定量与定性图像质量,但诊断急性阑尾炎的效能无显著差异
  • 降噪FBP主观图像质量最优,其次为降噪IR、IR、FBP

研究设计与样本

  • 单中心回顾性研究,纳入100例疑似急性阑尾炎行低剂量腹部CT患者(男40例,女60例,中位年龄31岁)
  • 每例患者重建FBP、降噪FBP、IR、降噪IR四组图像,降噪采用供应商中立的深度学习降噪软件
  • 两名放射科医师独立评估图像噪声、锐利度、伪影和总体质量(4分制)并判断有无急性阑尾炎
  • 在参考组织圆形感兴趣区测量定量噪声和信噪比

诊断标准与关键数值

  • 四组序列间噪声和信噪比差异显著,p值均小于0.001
  • 定量噪声最低为降噪IR,其次为降噪FBP、IR、FBP;信噪比趋势相反
  • 降噪序列的定性噪声和锐利度评分显著更高
  • 总体图像质量降噪FBP最高,其次为降噪IR、IR、FBP
  • 诊断急性阑尾炎的敏感度和特异度序列间无显著差异,降噪序列特异度数值上更高

临床应用与阅片要点

  • 低剂量腹部CT可优先选择降噪FBP序列进行阅片,兼顾图像质量与重建流程
  • 降噪处理不改变诊断结论,阅片时无需因降噪改变急性阑尾炎诊断阈值

局限性

  • 单中心回顾性研究

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 evaluate the effect of deep learning-based denoising on image quality and diagnostic performance of low-dose abdominal CT in diagnosing acute appendicitis, and to determine whether filtered back projection (FBP) or iterative reconstruction (IR) provides more suitable input images for denoising.

MATERIALS AND METHODS: This single-center retrospective study included 100 patients (40 men, 60 women; median age, 31 years) who underwent low-dose abdominal CT (median effective dose, 1.34 mSv) for suspected acute appendicitis between May 2023 and December 2024. Images were reconstructed using FBP and IR, then processed with vendor-neutral, deep learning-based denoising software, generating four image series per patient (FBP, denoised FBP, IR, and denoised IR). Two radiologists independently analyzed image noise, sharpness, artifacts, and overall quality using 4-point scales and assessed the presence of acute appendicitis. Quantitative noise and signal-to-noise ratio (SNR) were measured from circular regions of interest in reference tissues. Diagnostic performance and image quality metrics were compared across series using appropriate statistical methods.

RESULTS: Noise and SNR differed significantly among series (both p < 0.001). Quantitative noise was lowest for denoised IR, followed by denoised FBP, IR, and FBP, while SNR showed the opposite trend. Qualitative noise and sharpness scores were significantly higher for denoised series. Overall image quality was highest for denoised FBP, followed by denoised IR, IR, and FBP. Sensitivity and specificity for diagnosing acute appendicitis showed no significant inter-series differences; however, specificities were numerically higher for denoised series.

CONCLUSION: Deep learning-based denoising improved quantitative and qualitative image quality in low-dose abdominal CT for acute appendicitis, although no significant differences in diagnostic performance were observed. Denoised FBP showed the most favorable subjective image quality.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Shin, Kim, Lee, et al. Effectiveness of deep learning-based denoising on image quality and diagnostic performance of low-dose abdominal CT for acute appendicitis. Eur J Radiol. 2026. PMID: 42361706. doi:10.1016/j.ejrad.2026.113037

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。