文献速递核素与放射性配体治疗放射性药物与辐射防护

深度学习生成合成中间投影改善稀疏采集177Lu SPECT图像重建

Deep-Learning Generation of Synthetic Intermediate Projections Improves 177Lu SPECT Images Reconstructed with Sparsely Acquired Projections.
PubMed 文献 · J Nucl Med · 2020-08-28

本研究构建深度卷积U-net神经网络生成合成中间投影(CUSIPs),用于减少177Lu-SPECT投影数量以缩短采集时间。测试集15例,输入每第4个投影(共30个),输出30个合成中间投影(SIPs),重建120投影或30投影或30-120SIPs图像。结果显示30-120SIPs较30投影显著提高SSIM和PSNR,图像质量与120投影无显著差异,肾脏活度浓度相似。

要点

  • 深度学习生成SIPs可恢复稀疏采集投影的图像质量。
  • 30-120SIPs与120投影的图像质量无显著差异。
  • 该方法有望缩短临床剂量学方案中的SPECT采集时间。

核心结论

  • 采用SIPs处理稀疏采集投影可显著恢复图像质量,并可能缩短临床剂量学方案中的SPECT采集时间。

研究设计与样本

  • 构建深度卷积U-net神经网络生成合成中间投影(CUSIPs),训练集352例、验证集37例、测试集15例SPECT检查。
  • 输入为120个采集投影中的每第4个投影(共30个),每个CUSIP输出30个合成中间投影(SIPs)。
  • 使用3个CUSIPs从30个投影生成90个SIPs,与原始30个投影合成120投影(30-120SIPs)。
  • 重建采用衰减校正OSEM(AC-OSEM)和衰减、散射及准直器响应校正OSEM(ASCC-OSEM)两种算法。

主要发现

  • 生成的SIPs平均SSIM值为0.926(SD,0.061)。
  • AC-OSEM重建中,30-120SIPs较30投影具有更高的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值高于AC-OSEM(P < 0.001)。
  • 30-120SIPs较30投影恢复值略有损失,但SNR明显改善。
  • 观察者评估30投影重建的30幅图像中27幅噪声不可接受,而30-120SIPs和120投影的60幅中仅2幅不可接受,且30-120SIPs与120投影图像质量无显著差异。

临床怎么用

  • 在临床剂量学方案中,可考虑采用深度学习生成SIPs以减少177Lu-SPECT的投影数量,从而缩短采集时间。
  • ASCC-OSEM重建的SSIM和PSNR优于AC-OSEM,可根据需求选择重建算法。

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

The aims of this study were to decrease the 177Lu-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.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Rydén T, Van Essen M, Marin I, et al. Deep-Learning Generation of Synthetic Intermediate Projections Improves 177Lu SPECT Images Reconstructed with Sparsely Acquired Projections. J Nucl Med. 2020. PMID: 32859710. doi:10.2967/jnumed.120.245548

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。