基于深度卷积残差神经网络从半时采集的SPECT心肌灌注图像进行标准估计
本研究纳入363例因各种临床指征接受MPI-SPECT的前瞻性队列患者,使用固定90°双探头心脏SPECT相机采集32个投影、每个投影20秒。通过残差网络在投影域从半时(10秒)图像预测全时图像、从16个半投影预测32个全投影。结果显示减少每投影采集时间显著增加误差指标,深度神经网络可有效恢复图像质量并减少定量指标偏倚。
要点
- 减少每投影采集时间(从20秒至10秒)显著增加误差指标。
- 深度神经网络可有效恢复图像质量并减少定量指标的偏倚。
- 预测的全时图像图像质量优于预测的全投影图像。
核心结论
- 减少每投影采集时间显著增加误差指标,深度神经网络可有效恢复图像质量并减少定量指标偏倚,需进一步研究探索门控MPI-SPECT中时间减少的影响。
研究设计与样本
- 前瞻性队列研究纳入363例因各种临床指征(正常、缺血、梗死)转诊行MPI-SPECT的患者,使用固定90°专用双探头心脏SPECT相机采集。
- 每位患者采集32个投影、每个投影20秒,采用步进-拍摄协议从右前斜位至左后斜位采集,投影数据使用OSEM算法重建(6次迭代、4个子集、Butterworth后重建滤波)。
- 每位患者生成四个数据集:全时(20秒)投影(FT)、半时(10秒)每投影采集(HT)、32个全投影(FP)和16个半投影(HP)。
- 通过残差网络在投影域实现图像到图像的变换,从HT预测FT、从HP预测FP,采用十折交叉验证方案进行定性和定量评估。
主要发现
- 预测的FT图像质量优于预测的FP图像。
- 预测的FT图像误差指标最低(RMSE = 6.8 ± 2.7,ARE = 3.1 ± 1.1%),相似性指数和信噪比最高(SSIM = 0.97 ± 1.1,PSNR = 36.0 ± 1.4)。
- HT图像的误差指标最高(RMSE = 32.8 ± 12.8,ARE = 16.2 ± 4.9%),相似性和信噪比最低(SSIM = 0.93 ± 2.6,PSNR = 31.7 ± 2.9)。
- 预测的FT(8.0 ± 3.6)相对于预测的FP(6.8 ± 2.7)的RMSE显著降低(P值 < .05)。
局限性
- 需进一步研究探索门控MPI-SPECT中时间减少的影响。
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)。
原文
INTRODUCTION: The purpose of this work was to assess the feasibility of acquisition time reduction in MPI-SPECT imaging using deep leering techniques through two main approaches, namely reduction of the acquisition time per projection and reduction of the number of angular projections. METHODS: SPECT imaging was performed using a fixed 90° angle dedicated dual-head cardiac SPECT camera. This study included a prospective cohort of 363 patients with various clinical indications (normal, ischemia, and infarct) referred for MPI-SPECT. For each patient, 32 projections for 20 seconds per projection were acquired using a step and shoot protocol from the right anterior oblique to the left posterior oblique view. SPECT projection data were reconstructed using the OSEM algorithm (6 iterations, 4 subsets, Butterworth post-reconstruction filter). For each patient, four different datasets were generated, namely full time (20 seconds) projections (FT), half-time (10 seconds) acquisition per projection (HT), 32 full projections (FP), and 16 half projections (HP). The image-to-image transformation via the residual network was implemented to predict FT from HT and predict FP from HP images in the projection domain. Qualitative and quantitative evaluations of the proposed framework was performed using a tenfold cross validation scheme using the root mean square error (RMSE), absolute relative error (ARE), structural similarity index, peak signal-to-noise ratio (PSNR) metrics, and clinical quantitative parameters. RESULTS: The results demonstrated that the predicted FT had better image quality than the predicted FP images. Among the generated images, predicted FT images resulted in the lowest error metrics (RMSE = 6.8 ± 2.7, ARE = 3.1 ± 1.1%) and highest similarity index and signal-to-noise ratio (SSIM = 0.97 ± 1.1, PSNR = 36.0 ± 1.4). The highest error metrics (RMSE = 32.8 ± 12.8, ARE = 16.2 ± 4.9%) and the lowest similarity and signal-to-noise ratio (SSIM = 0.93 ± 2.6, PSNR = 31.7 ± 2.9) were observed for HT images. The RMSE decreased significantly (P value < .05) for predicted FT (8.0 ± 3.6) relative to predicted FP (6.8 ± 2.7). CONCLUSION: Reducing the acquisition time per projection significantly increased the error metrics. The deep neural network effectively recovers image quality and reduces bias in quantification metrics. Further research should be undertaken to explore the impact of time reduction in gated MPI-SPECT.
引用
- Shiri I, AmirMozafari Sabet K, Arabi H, et al. Standard SPECT myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks. J Nucl Cardiol. 2020. PMID: 32347527. doi:10.1007/s12350-020-02119-y
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。