文献速递胸部CT

深度学习超分辨率CT与超高分辨率CT在尸体人肺中的直接比较

Deep Learning Super-Resolution CT Versus Ultra-High-Resolution CT: A Direct Comparison in Cadaveric Human Lungs.
PubMed 文献 · Acad Radiol · 2026-10-22

本研究回顾性纳入10例尸体人肺,在9 mGy和2 mGy两个剂量水平下比较深度学习超分辨率CT(CCT-1024-PIQE)与超高分辨率CT衍生图像(UHR-1024-AiCE)的图像质量。结果显示9 mGy时UHR-1024-AiCE在磨玻璃影和小叶内网格影评分更高,2 mGy时两者多数征象无显著差异,且CCT-1024-PIQE较512矩阵重建视觉评分更高、噪声更低。

要点

  • 低剂量(2 mGy)下深度学习超分辨率CT与UHR-CT对多数肺部征象显示无显著差异。
  • 9 mGy时UHR-1024-AiCE对磨玻璃影和小叶内网格影评分优于CCT-1024-PIQE。
  • CCT-1024-PIQE较常规512矩阵重建视觉评分更高且噪声更低。

关键影像表现/征象

  • 评估征象包括细支气管、7种异常表现及整体图像质量。
  • 9 mGy时UHR-1024-AiCE在磨玻璃影和小叶内网格影评分高于CCT-1024-PIQE(P ≤ 0.007)。
  • 2 mGy时CCT-1024-PIQE与UHR-1024-AiCE在多数征象上无显著差异。
  • CCT-1024-PIQE在两种剂量下视觉评分均高于512矩阵重建(多数比较P < 0.05)。
  • 2 mGy时所有方法图像噪声增加,但PIQE重建噪声更低(P < 0.001)。

诊断标准与关键数值

  • 采用5分法评估细支气管、7种异常表现及整体图像质量。
  • 9 mGy时UHR-1024-AiCE对磨玻璃影和小叶内网格影评分高于CCT-1024-PIQE(P ≤ 0.007)。
  • 2 mGy时CCT-1024-PIQE与UHR-1024-AiCE多数征象无显著差异。
  • CCT-1024-PIQE视觉评分高于512矩阵重建(多数比较P < 0.05)。
  • PIQE重建噪声低于其他方法(P < 0.001)。

临床应用与阅片要点

  • 低剂量条件下深度学习超分辨率CT可替代UHR-CT显示多数肺部征象。
  • 评估磨玻璃影和小叶内网格影时,高剂量下UHR-1024-AiCE可能更优。
  • 深度学习超分辨率CT较512矩阵重建可提升图像视觉质量并降低噪声。

局限性

  • 回顾性研究,样本量较小(10例尸体人肺)。
  • 使用尸体肺标本,未在活体患者中验证。

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: Deep learning-based high-resolution computed tomography (CT) of the lung parenchyma has not been directly compared with ultra-high-resolution CT (UHR-CT). We compared image quality between deep learning-based super-resolution CT and UHR-CT using identical cadaveric human lungs.

MATERIALS AND METHODS: This retrospective study included 10 cadaveric human lungs scanned using conventional CT and UHR-CT at two dose levels (9 mGy, 2 mGy). Five reconstruction methods were evaluated, including deep learning-based synthetic super-resolution CT (CCT-1024-PIQE) and UHR-CT-derived high-resolution images reconstructed using a deep learning-based denoising algorithm (UHR-1024-AiCE). Two radiologists independently assessed the bronchioles, seven abnormal findings, and overall image quality using a 5-point scale. The objective image noise was also quantified. Statistical comparisons were performed using the Wilcoxon signed-rank test with Benjamini-Hochberg correction.

RESULTS: At 9 mGy, no significant differences were observed in the bronchioles, whereas UHR-1024-AiCE demonstrated higher scores than CCT-1024-PIQE for ground-glass opacities and intralobular reticulation (all P ≤ 0.007). At 2 mGy, CCT-1024-PIQE showed no significant differences from UHR-1024-AiCE for most findings. Compared with the 512-matrix reconstructions, CCT-1024-PIQE achieved consistently higher visual scores at both dose levels (most comparisons, P < 0.05). Image noise increased at 2 mGy across all methods, while PIQE-based reconstructions showed lower noise (P < 0.001).

CONCLUSION: Deep learning-based super-resolution CT showed no significant differences from UHR-CT in many pulmonary findings, particularly under low-dose conditions, while improving visualization compared to conventional 512-matrix reconstructions.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Ueno M, Yanagawa M, Hata A, et al. Deep Learning Super-Resolution CT Versus Ultra-High-Resolution CT: A Direct Comparison in Cadaveric Human Lungs. Acad Radiol. 2026. PMID: 42918706. doi:10.1016/j.acra.2026.09.072

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。