Deep-Learning Generation of Synthetic Intermediate Projections Improves 177Lu SPECT Images Reconstructed with Sparsely Acquired Projections
Deep-Learning Generation of Synthetic Intermediate Projections Improves 177Lu SPECT Images Reconstructed with Sparsely Acquired Projections
复制标题
DOI：
10.2967/jnumed.120.245548
复制
发表时间：
2021-04-01
影响因子：
9.3
通讯作者：
Bernhardt, Peter
中科院分区：
文献类型：
--
作者：
Ryden, Tobias;Van Essen, Martijn;Bernhardt, Peter
这项研究的目的是通过减少投影数量来减少Lu-177-SPECT的采集时间，并通过添加深度学习生成的合成投影来避免图像退化。方法：我们构建了一个用于生成合成中间投影（CUSIP）的深度卷积U形神经网络。SPECT研究的数量为352次培训，37次验证和15次测试。输入是120个采集的SPECT投影的每第四个投影，即30个投影。每个CUSIP的输出是30个合成中间预测（SIP）。用120或30个投影重建SPECT图像，或当从30个投影（30- 120个SIP）生成90个SIP时，用3个CUSIP重建SPECT图像。使用2种有序子集期望最大化（OSEM）算法进行重建：衰减校正（AC）OSEM和衰减、散射和准直器响应校正（ASCC）OSEM。用均方根误差、峰值信噪比（PSNR）和结构相似性（SSIM）指标定量评价SIP和SPECT图像的质量。从Jaszczak SPECT体模，回收率和信噪比（SNR）进行了测定。此外，由一名经验丰富的观察员对测试集的SPECT图像质量进行了定性评估。比较从不同SPECT图像确定的肾活性浓度。结果：生成的SIP的平均SSIM值为0.926（SD，0.061）。对于AC-OSEM，使用30- 120个SIP的重建比使用30个投影的重建具有更高的SSIM（0.993 vs. 0.989，P < 0.001）和PSNR（49.5 vs. 47.2，P < 0.001）。ASCC-OSEM的SSIM和PSNR值均高于AC-OSEM（P < 0.001）。对于30- 120个SIP，恢复有轻微损失，但与30个投影相比，SNR明显改善。观察者评估了30个投影重建的30个图像中的27个具有不可接受的噪声水平，而30- 120 SIP和120个投影的相应值为60个中的2个。30- 120次SIP和120次投影之间的图像质量没有显著差异。除了ASCC-OSEM 30- 120 SIP轻微降低2.5%外，不同投影集之间的肾脏活性浓度相似。结论：采用SIP稀疏采集的投影大大恢复图像质量，并可以允许减少SPECT采集时间在临床剂量测定协议。
The aims of this study were to decrease the Lu-177-SPECT acquisition time by reducing the number of projections and to circumvent image degradation by adding deep-learning-generated synthesized projections. Methods: We constructed a deep convolutional U-net-shaped neural network for generation of synthetic intermediate projections (CUSIPs). The number of SPECT investigations was 352 for training, 37 for validation, and 15 for testing. The input was every fourth projection of 120 acquired SPECT projections, that is, 30 projections. The output was 30 synthetic intermediate projections (SIPs) per CUSIP. SPECT images were reconstructed with 120 or 30 projections, or with 120 projections when 90 SIPs were generated from 30 projections (30-120SIPs), using 3 CUSIPs. The reconstructions were performed with 2 ordered-subset expectation maximization (OSEM) algorithms: attenuation-corrected (AC) OSEM, and attenuation, scatter, and collimator response-corrected (ASCC) OSEM. The quality of the SIPs and SPECT images was quantitatively evaluated with root-mean-square error, peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) index metrics. From a Jaszczak SPECT phantom, the recovery and signal-to-noise ratio (SNR) were determined. In addition, an experienced observer qualitatively assessed the SPECT image quality of the test set. Kidney activity concentrations, as determined from the different SPECT images, were compared. Results: The generated SIPs had a mean SSIM value of 0.926 (SD, 0.061). For AC-OSEM, the reconstruction with 30-120SIPs had higher SSIM (0.993 vs. 0.989, P < 0.001) and PSNR (49.5 vs. 47.2, P < 0.001) values than the reconstruction with 30 projections. ASCC-OSEM had higher SSIM and PSNR values than AC-OSEM (P < 0.001). There was a minor loss in recovery for 30-120SIPs, but SNR was clearly improved compared with 30 projections. The observer assessed 27 of 30 images reconstructed with 30 projections as having unacceptable noise levels, whereas the corresponding values were 2 of 60 for 30-120SIPs and 120 projections. Image quality did not differ significantly between 30-120SIPs and 120 projections. The kidney activity concentration was similar between the different projection sets, excepting a minor reduction of 2.5% for ASCC-OSEM 30-120SIPs. Conclusion: Adopting SIPs for sparsely acquired projections considerably recovers image quality and could allow a reduced SPECT acquisition time in clinical dosimetry protocols.