Yang Pei, Zhang Zeao, Wei Jianan, Jiang Lisha, Yu Liqian, Cai Huawei, Li Lin, Guo Quan, Zhao Zhen
Department of Nuclear Medicine, West China Hospital of Sichuan University, No.37 Guo Xue Alley, Chengdu, 610041, China.
Machine Intelligence Laboratory, College of Computer Science, Sichuan University, No. 24 South Section 1, Yihuan Road, Chengdu, 610065, China.
BMC Med Imaging. 2025 Feb 4;25(1):38. doi: 10.1186/s12880-025-01570-y.
Computed tomography attenuation correction (CTAC) is commonly used in cardiac SPECT imaging to reduce soft-tissue attenuation artifacts. However, CTAC is prone to inaccuracies due to CT artifacts and SPECT-CT mismatch, along with additional radiation exposure to patients. Thus, these limitations have led to increasing interest in CT-free AC, with deep learning (DL) offering promising solutions. We proposed a new DL-based CT-free AC methods for cardiac SPECT.
We developed a feature alignment attenuation correction network (FA-ACNet) based on the 3D U-Net framework to generate predicted DL-based AC SPECT (Deep AC). The network was trained on 167 cardiac SPECT/CT studies using 5-fold cross validation and tested in an independent testing set (n = 35), with CTAC serving as the reference. During training, multi-scale features from non-attenuation-corrected (NAC) SPECT and CT were processed separately and then aligned with the encoded features from NAC SPECT using adversarial learning and distance metric learning techniques. The performance of FA-ACNet was evaluated using mean square error (MSE), structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR). Additionally, semi-quantitative evaluation of Deep AC images was performed and compared to CTAC using Bland-Altman plots.
FA-ACNet achieved an MSE of 16.94 ± 2.03 × 10, SSIM of 0.9955 ± 0.0006 and PSNR of 43.73 ± 0.50 after 5-fold cross validation. Compared to U-Net, MSE and PSNR improved by aligning multi-scale features from NAC SPECT and CT with those from NAC SPECT. In the testing set, FA-ACNet achieved an MSE of 11.98 × 10, SSIM of 0.9976 and PSNR of 45.54. The 95% limits of agreement (LoAs) between the Deep AC and CTAC images for the summed stress/rest scores (SSS/SRS) were [- 2.3, 2.8] and [-1.9,2.1] in the training set and testing set respectively. Changes in perfusion categories were observed in 4.19% and 5.9% of studies assessed for global perfusion scores in the training set and testing set.
We propose a novel DL-based CT-free AC approach for cardiac SPECT, which can generate AC images without the need for a CT scan. By leveraging multi-scale features from both NAC SPECT and CT, the performance of CT-free AC is significantly enhanced, offering a promising alternative for future DL-based AC strategies.
计算机断层扫描衰减校正（CTAC）常用于心脏SPECT成像，以减少软组织衰减伪影。然而，由于CT伪影和SPECT-CT不匹配，CTAC容易出现不准确情况，同时还会增加患者的辐射暴露。因此，这些局限性使得人们对无CT的衰减校正（AC）越来越感兴趣，深度学习（DL）提供了有前景的解决方案。我们提出了一种新的基于深度学习的心脏SPECT无CT AC方法。
我们基于3D U-Net框架开发了一种特征对齐衰减校正网络（FA-ACNet），以生成基于深度学习预测的AC SPECT（深度AC）。该网络使用5折交叉验证在167例心脏SPECT/CT研究上进行训练，并在一个独立测试集（n = 35）中进行测试，以CTAC作为参考。在训练过程中，对未进行衰减校正（NAC）的SPECT和CT的多尺度特征分别进行处理，然后使用对抗学习和距离度量学习技术将其与NAC SPECT的编码特征对齐。使用均方误差（MSE）、结构相似性指数（SSIM）和峰值信噪比（PSNR）评估FA-ACNet的性能。此外，对深度AC图像进行半定量评估，并使用Bland-Altman图与CTAC进行比较。
经过5折交叉验证后，FA-ACNet的MSE为16.94±2.03×10，SSIM为0.9955±0.0006，PSNR为43.73±0.50。与U-Net相比，通过将NAC SPECT和CT的多尺度特征与NAC SPECT的特征对齐，MSE和PSNR得到了改善。在测试集中，FA-ACNet的MSE为11.98×10，SSIM为0.9976，PSNR为45.54。在训练集和测试集中，深度AC与CTAC图像的总应力/静息评分（SSS/SRS）的95%一致性界限（LoA）分别为[-2.3, 2.8]和[-1.9, 2.1]。在训练集和测试集中，分别有4.19%和5.9%的评估整体灌注评分的研究观察到灌注类别发生变化。
我们提出了一种新颖的基于深度学习的心脏SPECT无CT AC方法，该方法无需CT扫描即可生成AC图像。通过利用NAC SPECT和CT的多尺度特征，无CT AC的性能得到显著增强，为未来基于深度学习的AC策略提供了有前景的替代方案。
