Prieto Canalejo Mariana Andrea, Palau San Pedro Aley, Geronazzo Ricardo, Minsky Daniel Mauricio, Juárez-Orozco Luis Eduardo, Namías Mauro
Facultad Regional Buenos Aires, Universidad Tecnológica Nacional, Buenos Aires C1179AAS, Argentina.
Fundación Centro Diagnóstico Nuclear (FCDN), Buenos Aires C1417CVE, Argentina.
Diagnostics (Basel). 2023 Jun 29;13(13):2214. doi: 10.3390/diagnostics13132214.
(1) Background: The CT-based attenuation correction of SPECT images is essential for obtaining accurate quantitative images in cardiovascular imaging. However, there are still many SPECT cameras without associated CT scanners throughout the world, especially in developing countries. Performing additional CT scans implies troublesome planning logistics and larger radiation doses for patients, making it a suboptimal solution. Deep learning (DL) offers a revolutionary way to generate complementary images for individual patients at a large scale. Hence, we aimed to generate linear attenuation coefficient maps from SPECT emission images reconstructed without attenuation correction using deep learning. (2) Methods: A total of 384 SPECT myocardial perfusion studies that used Tc-sestamibi were included. A DL model based on a 2D U-Net architecture was trained using information from 312 patients. The quality of the generated synthetic attenuation correction maps (ACMs) and reconstructed emission values were evaluated using three metrics and compared to standard-of-care data using Bland-Altman plots. Finally, a quantitative evaluation of myocardial uptake was performed, followed by a semi-quantitative evaluation of myocardial perfusion. (3) Results: In a test set of 66 test patients, the ACM quality metrics were MSSIM = 0.97 ± 0.001 and NMAE = 3.08 ± 1.26 (%), and the reconstructed emission quality metrics were MSSIM = 0.99 ± 0.003 and NMAE = 0.23 ± 0.13 (%). The 95% limits of agreement (LoAs) at the voxel level for reconstructed SPECT images were: [-9.04; 9.00]%, and for the segment level, they were [-11; 10]%. The 95% LoAs for the Summed Stress Score values between the images reconstructed were [-2.8, 3.0]. When global perfusion scores were assessed, only 2 out of 66 patients showed changes in perfusion categories. (4) Conclusion: Deep learning can generate accurate attenuation correction maps from non-attenuation-corrected cardiac SPECT images. These high-quality attenuation maps are suitable for attenuation correction in myocardial perfusion SPECT imaging and could obviate the need for additional imaging in standalone SPECT scanners.
（1）背景：基于CT的单光子发射计算机断层扫描（SPECT）图像衰减校正对于在心血管成像中获得准确的定量图像至关重要。然而，全球仍有许多SPECT相机没有配套的CT扫描仪，尤其是在发展中国家。进行额外的CT扫描意味着麻烦的规划后勤工作以及给患者带来更大的辐射剂量，这使其成为一个次优解决方案。深度学习（DL）提供了一种革命性的方法，可以大规模为个体患者生成补充图像。因此，我们旨在使用深度学习从未进行衰减校正重建的SPECT发射图像生成线性衰减系数图。（2）方法：总共纳入了384项使用锝-甲氧基异丁基异腈的SPECT心肌灌注研究。基于二维U-Net架构的深度学习模型使用来自312名患者的信息进行训练。使用三个指标评估生成的合成衰减校正图（ACM）的质量和重建的发射值，并使用布兰德-奥特曼图与标准护理数据进行比较。最后，对心肌摄取进行定量评估，随后对心肌灌注进行半定量评估。（3）结果：在66名测试患者的测试集中，ACM质量指标为结构相似性指数（MSSIM）=0.97±0.001，归一化平均绝对误差（NMAE）=3.08±1.26（%），重建发射质量指标为MSSIM=0.99±0.003，NMAE=0.23±0.13（%）。重建的SPECT图像在体素水平的95%一致性界限（LoA）为：[-9.04；9.00]%，在节段水平为：[-11；10]%。重建图像之间的总应力评分值的95% LoA为[-2.8，3.0]。当评估整体灌注评分时，66名患者中只有2名患者的灌注类别出现变化。（4）结论：深度学习可以从未经衰减校正的心脏SPECT图像生成准确的衰减校正图。这些高质量的衰减图适用于心肌灌注SPECT成像中的衰减校正，并且可以避免在独立的SPECT扫描仪中进行额外成像的需要。
