ISSN 1004-4140
CN 11-3017/P
潘志杰, 刘玲, 李卿瑶, 等. 深度学习图像重建提升标准肝脏密度体模CT扫描图像质量[J]. CT理论与应用研究(中英文), xxxx, x(x): 1-10. DOI: 10.15953/j.ctta.2024.056.
引用本文: 潘志杰, 刘玲, 李卿瑶, 等. 深度学习图像重建提升标准肝脏密度体模CT扫描图像质量[J]. CT理论与应用研究(中英文), xxxx, x(x): 1-10. DOI: 10.15953/j.ctta.2024.056.
PAN Z J, Liu L, Li Q Y, et al. Deep Learning Image Reconstruction to Improve Computed Tomography Image Quality of the Phantom with Standard Liver Density[J]. CT Theory and Applications, xxxx, x(x): 1-10. DOI: 10.15953/j.ctta.2024.056. (in Chinese).
Citation: PAN Z J, Liu L, Li Q Y, et al. Deep Learning Image Reconstruction to Improve Computed Tomography Image Quality of the Phantom with Standard Liver Density[J]. CT Theory and Applications, xxxx, x(x): 1-10. DOI: 10.15953/j.ctta.2024.056. (in Chinese).

深度学习图像重建提升标准肝脏密度体模CT扫描图像质量

Deep Learning Image Reconstruction to Improve Computed Tomography Image Quality of the Phantom with Standard Liver Density

  • 摘要: 目的:通过使用不同的扫描剂量,扫描模拟标准肝脏密度体模,比较深度学习重建技术(DLIR)与自适应统计迭代重建技术(ASIR-V)重建图像的质量。方法:使用Gammex标准CT体模模拟标准肝脏密度的插入物(ρew=1.06),在6种不同辐射剂量水平(CTDIvol:30、20、15、10、7.5和4.5mGy)下进行CT扫描。随后,使用DLIR和ASIR-V算法,对每种剂量下获得的图像进行重建。通过imQuest软件对图像进行质量分析,使用Bland-Altman方法比较DLIR算法在4.5mGy(本实验采用的最低辐射剂量)和ASIR-V在15mGy(肝脏扫描推荐剂量)下的图像质量。结果:在6种剂量水平下,DLIR在噪声(P<0.001)、信噪比(P<0.001)、对比噪声比(P<0.001)和可检测度(P<0.001)等关键指标上,均显著优于ASIR-V。Bland-Altman分析结果表明,在4.5mGy的剂量水平下,DLIR的图像质量显著优于ASIR-V在15mGy剂量水平下的表现。在4.5mGy下DLIR图像的噪声为17.41±0.32,显著低于ASIR-V在15mGy的21.17±0.67(P<0.001)。在4.5mGy下DLIR的信噪比、对比噪声比和可检测度分别为3.21±0.24,3.42±0.35和8.81±0.63,显著高于ASIR-V在15mGy剂量下的2.69±0.14,2.87±0.11和5.61±1.28(P值分别为0.006、0.029和0.005)。结论:在模拟标准肝脏密度的局灶性病变体模CT扫描实验中,DLIR相较于ASIR-V,不仅显著提升信噪比,对比噪声比和可检测度值,而且大幅度降低图像噪声。DLIR技术能够在4.5mGy的较低辐射剂量下,实现优于常规15mGy剂量下ASIR-V重建图像的质量效果。

     

    Abstract: Objective: This study aimed to compare the quality of reconstructed images by deep learning image reconstruction (DLIR) and adaptive statistical iterative reconstruction-V (ASIR-V) techniques at different scan doses using a phantom with liver density. Methods: The Gammex computed tomography (CT) phantom with a standard liver-density insert (ρew=1.06) was scanned at six different radiation doses (CTDIvol; 30, 20, 15, 10, 7.5, and 4.5 mGy). Images obtained at each dose were reconstructed using DLIR and ASIR-V. Image quality was analyzed through the imQuest software. The quality of reconstructed images by DLIR at 4.5 mGy (lowest radiation dose) and ASIR-V at 15 mGy (recommended scan dose) were compared using the Bland–Altman method. Results: Across the six doses, DLIR significantly outperformed ASIR-V in key metrics, such as noise (P<0.001), signal-to-noise ratio (SNR) (P<0.001), contrast-to-noise ratio (CNR) (P<0.001), and detectability index (d') (P<0.001). Bland–Altman analysis indicated that the quality of reconstructed images by DLIR at 4.5 mGy was significantly better to those by ASIR-V at 15 mGy. The noise level of DLIR images at 4.5 mGy was 17.41±0.32, which is significantly lower than that of ASIR-V at 15 mGy (21.17±0.67) (P<0.001). At 4.5 mGy, DLIR SNR, CNR, and d' were 3.21±0.24, 3.42±0.35, and 8.81±0.63, respectively, which are significantly higher than that of ASIR-V at 15 mGy (2.69±0.14, 2.87±0.11, and 5.61±1.28, respectively) (P=0.006, 0.029, and 0.005 respectively). Conclusion: In CT scan of focal liver-density lesions using a phantom, DLIR significantly improved the SNR, CNR, and d' values and reduced image noise compared to ASIR-V. DLIR was able to achieve better quality image reconstruction at 4.5 mGy than the conventional ASIR-V reconstruction at 15 mGy.

     

/

返回文章
返回