文献速递腹部CT

基于深度学习重建提升低剂量CT结肠成像的图像质量

Deep Learning-Based Reconstruction Improves the Image Quality of Low-Dose CT Colonography.
PubMed 文献 · Acad Radiol · 2024-01-29

本研究纳入270名成人志愿者,按体重指数分为四组,比较常规剂量迭代重建、低剂量迭代重建与低剂量深度学习重建的CT结肠成像图像质量。低剂量深度学习重建的主观评分优于低剂量迭代重建(3.61±0.56 vs 2.70±0.51,P<0.001),与常规剂量迭代重建相当(3.61±0.56 vs 3.74±0.52,P=0.486),且噪声最低、信噪比与对比噪声比最高,低剂量有效剂量约降低83.18%。

要点

  • 低剂量深度学习重建CT结肠成像主观评分3.61±0.56,与常规剂量迭代重建3.74±0.52无统计学差异(P=0.486)。
  • 低剂量深度学习重建噪声最低、信噪比与对比噪声比最高,均优于常规剂量迭代重建和低剂量迭代重建(均P<0.001)。
  • 低剂量CT结肠成像有效剂量约0.86mSv±0.05,较常规剂量5.18mSv±0.86降低约83.18%(P<0.001)。

核心结论

  • 与迭代重建相比,深度学习重建在平均辐射剂量0.86mSv下提供图像质量更优的低剂量CT结肠成像,未来可能有望用于结直肠癌筛查。

研究设计与样本

  • 研究纳入270名成人志愿者(平均年龄47.94岁±11.57,男性115名),按体重指数分为四组;常规剂量(120kVp)图像用迭代重建,低剂量(100kVp)图像分别用迭代重建和深度学习重建;由两名放射科医生独立进行5分制主观图像质量评分,客观指标包括噪声、信噪比和对比噪声比。

诊断标准与关键数值

  • 主观图像质量采用5分制评分,由两名放射科医生独立完成。
  • 低剂量深度学习重建主观评分3.61±0.56,优于低剂量迭代重建2.70±0.51(P<0.001),与常规剂量迭代重建3.74±0.52无统计学差异(P=0.486)。
  • 低剂量深度学习重建噪声最低、信噪比和对比噪声比最高,与常规剂量迭代重建和低剂量迭代重建相比均P<0.001。
  • 低剂量深度学习重建图像的噪声在不同体重指数组间无统计学差异(均P>0.05)。
  • 低剂量CT结肠成像有效剂量0.86mSv±0.05,常规剂量5.18mSv±0.86,低剂量降低约83.18%(P<0.001)。

临床应用与阅片要点

  • 作者认为深度学习重建用于低剂量CT结肠成像在未来结直肠癌筛查中可能具有前景。

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

RATIONALE AND OBJECTIVES: To evaluate the image quality of low-dose CT colonography (CTC) using deep learning-based reconstruction (DLR) compared to iterative reconstruction (IR).

MATERIALS AND METHODS: Adults included in the study were divided into four groups according to body mass index (BMI). Routine-dose (RD: 120 kVp) CTC images were reconstructed with IR (RD-IR); low-dose (LD: 100kVp) images were reconstructed with IR (LD-IR) and DLR (LD-DLR). The subjective image quality was rated on a 5-point scale by two radiologists independently. The parameters for objective image quality included noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR). The Friedman test was used to compare the image quality among RD-IR, LD-IR and LD-DLR. The KruskalWallis test was used to compare the results among different BMI groups.

RESULTS: A total of 270 volunteers (mean age: 47.94 years ± 11.57; 115 men) were included. The effective dose of low-dose CTC was decreased by approximately 83.18% (5.18mSv ± 0.86 vs. 0.86mSv ± 0.05, P < 0.001). The subjective image quality score of LD-DLR was superior to that of LD-IR (3.61 ± 0.56 vs. 2.70 ± 0.51, P < 0.001) and on par with the RD- IR's (3.61 ± 0.56 vs. 3.74 ± 0.52, P = 0.486). LD-DLR exhibited the lowest noise, and the maximum SNR and CNR compared to RD-IR and LD-IR (all P < 0.001). No statistical difference was found in the noise of LD-DLR images between different BMI groups (all P > 0.05).

CONCLUSION: Compared to IR, DLR provided low-dose CTC with superior image quality at an average radiation dose of 0.86mSv, which may be promising in future colorectal cancer screening.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Chen Y, Huang Z, Feng L, et al. Deep Learning-Based Reconstruction Improves the Image Quality of Low-Dose CT Colonography. Acad Radiol. 2024. PMID: 38290889. doi:10.1016/j.acra.2024.01.021

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。