Background: Standard methods for deriving Centiloid scales from amyloid PET images are time-consuming and require considerable expert knowledge. We aimed to develop a deep learning method of automating Centiloid scale calculations from amyloid PET images with 11C-Pittsburgh Compound-B (PiB) tracer and assess its applicability to 18F-labeled tracers without retraining. Methods: We trained models on 231 11C-PiB amyloid PET images using a 50-layer 3D ResNet architecture. The models predicted the Centiloid scale, and accuracy was assessed using mean absolute error (MAE), linear regression analysis, and Bland–Altman plots. Results: The MAEs for Alzheimer’s disease (AD) and young controls (YC) were 8.54 and 2.61, respectively, using 11C-PiB, and 8.66 and 3.56, respectively, using 18F-NAV4694. The MAEs for AD and YC were higher with 18F-florbetaben (39.8 and 7.13, respectively) and 18F-florbetapir (40.5 and 12.4, respectively), and the error rate was moderate for 18F-flutemetamol (21.3 and 4.03, respectively). Linear regression yielded a slope of 1.00, intercept of 1.26, and R2 of 0.956, with a mean bias of −1.31 in the Centiloid scale prediction. Conclusions: We propose a deep learning means of directly predicting the Centiloid scale from amyloid PET images in a native space. Transferring the model trained on 11C-PiB directly to 18F-NAV4694 without retraining was feasible.

中文翻译：

---

使用 11C-PiB 和 18F 标记示踪剂从淀粉样蛋白 PET 图像中深度学习驱动的阿尔茨海默氏病质体尺度估计

背景：从淀粉样蛋白 PET 图像中获取质心尺度的标准方法非常耗时，并且需要大量的专业知识。我们的目标是开发一种深度学习方法，使用 11C-匹兹堡化合物-B (PiB) 示踪剂从淀粉样蛋白 PET 图像中自动计算 Centiloid 尺度，并评估其在无需重新训练的情况下对 18F 标记示踪剂的适用性。方法：我们使用 50 层 3D ResNet 架构在 231 个 11C-PiB 淀粉样蛋白 PET 图像上训练模型。该模型预测了质心尺度，并使用平均绝对误差 (MAE)、线性回归分析和 Bland-Altman 图评估了准确性。结果：使用 11C-PiB 时，阿尔茨海默病 (AD) 和年轻对照 (YC) 的 MAE 分别为 8.54 和 2.61，使用 18F-NAV4694 时分别为 8.66 和 3.56。 18F-florbetaben（分别为 39.8 和 7.13）和 18F-florbetapir（分别为 40.5 和 12.4）的 AD 和 YC MAE 较高，18F-flutemetamol 的错误率适中（分别为 21.3 和 4.03）。线性回归的斜率为 1.00，截距为 1.26，R2 为 0.956，质心尺度预测的平均偏差为 -1.31。结论：我们提出了一种深度学习方法，可以直接从本地空间中的淀粉样蛋白 PET 图像预测质心尺度。将 11C-PiB 上训练的模型直接转移到 18F-NAV4694 上而无需重新训练是可行的。