基于深度学习的投影域和重建域的低剂量心肌灌注 SPECT 去噪。
Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT.
机构信息
Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Macau SAR, China.
Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan, ROC.
出版信息
J Nucl Cardiol. 2023 Jun;30(3):970-985. doi: 10.1007/s12350-022-03045-x. Epub 2022 Aug 18.
BACKGROUND
Low-dose (LD) myocardial perfusion (MP) SPECT suffers from high noise level, leading to compromised diagnostic accuracy. Here we investigated the denoising performance for MP-SPECT using a conditional generative adversarial network (cGAN) in projection-domain (cGAN-prj) and reconstruction-domain (cGAN-recon).
METHODS
Sixty-four noisy SPECT projections were simulated for a population of 100 XCAT phantoms with different anatomical variations and Tc-sestamibi distributions. Series of LD projections were obtained by scaling the full dose (FD) count rate to be 1/20 to 1/2 of the original. Twenty patients with Tc-sestamibi stress SPECT/CT scans were retrospectively analyzed. For each patient, LD SPECT images (7/10 to 1/10 of FD) were generated from the FD list mode data. All projections were reconstructed by the quantitative OS-EM method. A 3D cGAN was implemented to predict FD images from their corresponding LD images in the projection- and reconstruction-domain. The denoised projections were reconstructed for analysis in various quantitative indices along with cGAN-recon, Gaussian, and Butterworth-filtered images.
RESULTS
cGAN denoising improves image quality as compared to LD and conventional post-reconstruction filtering. cGAN-prj can further reduce the dose level as compared to cGAN-recon without compromising the image quality.
CONCLUSIONS
Denoising based on cGAN-prj is superior to cGAN-recon for MP-SPECT.
背景
低剂量（LD）心肌灌注（MP）单光子发射计算机断层扫描（SPECT）的噪声水平较高，导致诊断准确性受损。在此，我们研究了基于条件生成对抗网络（cGAN）的投影域（cGAN-prj）和重建域（cGAN-recon）MP-SPECT 的去噪性能。
方法
使用不同解剖变异和 Tc-sestamibi 分布的 100 个 XCAT 体模的人群模拟了 64 个噪声 SPECT 投影。通过将全剂量（FD）计数率缩小到原始计数率的 1/20 到 1/2 来获得一系列 LD 投影。对 20 名接受 Tc-sestamibi 应激 SPECT/CT 扫描的患者进行了回顾性分析。对于每位患者，从 FD 列表模式数据生成 FD 的 7/10 到 1/10 的 LD SPECT 图像。所有投影均由定量 OS-EM 方法重建。实现了一个 3D cGAN，用于从相应的 LD 图像预测 FD 图像，分别在投影域和重建域中进行。对去噪投影进行了重建，以便在各种定量指标中进行分析，并与 cGAN-recon、高斯和 Butterworth 滤波图像进行比较。
结果
与 LD 和传统的后重建滤波相比，cGAN 去噪可提高图像质量。与不影响图像质量的 cGAN-recon 相比，cGAN-prj 可以进一步降低剂量水平。
结论
基于 cGAN-prj 的去噪对于 MP-SPECT 优于 cGAN-recon。
Zotero 插件