文献速递心脏核医学

深度学习直接衰减校正用于心脏SPECT的可行性研究

Direct Attenuation Correction Using Deep Learning for Cardiac SPECT: A Feasibility Study.
PubMed 文献 · J Nucl Med · 2021-02-26

该回顾性研究收集100例99mTc-替曲膦心脏SPECT/CT数据集,用卷积神经网络从非校正SPECT直接生成深度学习衰减校正SPECT,并与CT-based AC比较。结果显示深度学习法显著降低衰减伪影,但性能在不同受试者间不一致。

要点

  • 深度学习可直接从非校正SPECT生成衰减校正图像,无需额外重建步骤。
  • 深度学习法体素相关性和节段误差均优于非校正SPECT。
  • 极图显示衰减伪影成功减少,但性能在不同受试者间不一致。

核心结论

  • 深度学习用于SPECT心肌灌注显像的直接衰减校正是可行的。
  • 与未校正SPECT相比,深度学习方法大幅减少衰减伪影。
  • 深度学习法的性能并非对所有受试者一致。

研究设计与样本

  • 经机构审查委员会批准的回顾性研究,在耶鲁纽黑文医院收集100例99mTc-替曲膦心脏SPECT/CT数据集,使用小视野专用扫描仪。
  • 采用卷积神经网络从非校正SPECT直接生成深度学习衰减校正SPECT,不经过额外图像重建步骤。
  • 以CT-based AC为参考,采用美国心脏协会17节段模型进行体素和节段分析,并视觉比较代表性极图。

主要发现

  • SPECTNC与SPECTCTAC的体素相关为92.2% ± 3.7%(斜率0.87;R2 = 0.81),SPECTDL为97.7% ± 1.8%(斜率0.94;R2 = 0.91)。
  • SPECTNC节段误差散布于-35%至21%(P < 0.001),SPECTDL误差大多在±10%以内(P < 0.001)。
  • 平均节段误差:SPECTNC为-6.11% ± 8.06%,SPECTDL为0.49% ± 4.35%。
  • 平均绝对节段误差:SPECTNC为7.96% ± 6.23%,SPECTDL为3.31% ± 2.87%。
  • 极图复核显示衰减伪影成功减少,但SPECTDL性能因衰减量和摄取模式不同而不一致。

临床怎么用

  • 对于无集成CT的专用心脏SPECT扫描仪,深度学习直接衰减校正有望减少衰减伪影。
  • 该方法性能在不同受试者间不一致,临床应用前需进一步研究确立安全性和一致性。

局限性

  • SPECTDL的性能并非对所有受试者一致,可能因衰减量和摄取模式不同而异。
  • 研究为回顾性单中心设计,样本量100例,需进一步研究确立临床安全性和一致性。

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

Dedicated cardiac SPECT scanners with cadmium-zinc-telluride cameras have shown capabilities for shortened scan times or reduced radiation doses, as well as improved image quality. Since most dedicated scanners do not have integrated CT, image quantification with attenuation correction (AC) is challenging and artifacts are routinely encountered in daily clinical practice. In this work, we demonstrated a direct AC technique using deep learning (DL) for myocardial perfusion imaging (MPI). Methods: In an institutional review board-approved retrospective study, 100 cardiac SPECT/CT datasets with 99mTc-tetrofosmin, obtained using a scanner specifically with a small field of view, were collected at the Yale New Haven Hospital. A convolutional neural network was used for generating DL-based attenuation-corrected SPECT (SPECTDL) directly from noncorrected SPECT (SPECTNC) without undergoing an additional image reconstruction step. The accuracy of SPECTDL was evaluated by voxelwise and segmentwise analyses against the reference, CT-based AC (SPECTCTAC), using the 17-segment myocardial model of the American Heart Association. Polar maps of representative (best, median, and worst) cases were visually compared to illustrate potential benefits and pitfalls of the DL approach. Results: The voxelwise correlations with SPECTCTAC were 92.2% ± 3.7% (slope, 0.87; R2 = 0.81) and 97.7% ± 1.8% (slope, 0.94; R2 = 0.91) for SPECTNC and SPECTDL, respectively. The segmental errors of SPECTNC scattered from -35% to 21% (P < 0.001), whereas the errors of SPECTDL stayed mostly within ±10% (P < 0.001). The average segmental errors (mean ± SD) were -6.11% ± 8.06% and 0.49% ± 4.35% for SPECTNC and SPECTDL, respectively. The average absolute segmental errors were 7.96% ± 6.23% and 3.31% ± 2.87% for SPECTNC and SPECTDL, respectively. Review of polar maps revealed successful reduction of attenuation artifacts; however, the performance of SPECTDL was not consistent for all subjects, likely because of different amounts of attenuation and different uptake patterns. Conclusion: We demonstrated the feasibility of direct AC using DL for SPECT MPI. Overall, our DL approach reduced attenuation artifacts substantially compared with SPECTNC, justifying further studies to establish safety and consistency for clinical applications in stand-alone SPECT systems suffering from attenuation artifacts.

来源:J Nucl Med,查看原文。版权归原作者所有。

引用

  1. Yang J, Shi L, Wang R, et al. Direct Attenuation Correction Using Deep Learning for Cardiac SPECT: A Feasibility Study. J Nucl Med. 2021. PMID: 33637586. doi:10.2967/jnumed.120.256396

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。