Zou James, Park David, Johnson Aubrey, Feng Xinyang, Pardo Michelle, France Jeanelle, Tomljanovic Zeljko, Brickman Adam M, Devanand Devangere P, Luchsinger José A, Kreisl William C, Provenzano Frank A
The Taub Institute for Research on Alzheimer's Disease and the Aging Brain New York New York USA.
Department of Medicine Columbia University Medical Center New York New York USA.
Alzheimers Dement (Amst). 2021 Dec 31;13(1):e12264. doi: 10.1002/dad2.12264. eCollection 2021.
Positron emission tomography (PET) imaging targeting neurofibrillary tau tangles is increasingly used in the study of Alzheimer's disease (AD), but its utility may be limited by conventional quantitative or qualitative evaluation techniques in earlier disease states. Convolutional neural networks (CNNs) are effective in learning spatial patterns for image classification.
18F-MK6240 (n = 320) and AV-1451 (n = 446) PET images were pooled from multiple studies. We performed iterations with differing permutations of radioligands, heuristics, and architectures. Performance was compared to a standard region of interest (ROI)-based approach on prediction of memory impairment. We visualized attention of the network to illustrate decision making.
Overall, models had high accuracy (> 80%) with good average sensitivity and specificity (75% and 82%, respectively), and had comparable or higher accuracy to the ROI standard. Visualizations of model attention highlight known characteristics of tau radioligand binding.
CNNs could improve tau PET's role in early disease and extend the utility of tau PET across generations of radioligands.
针对神经纤维缠结的正电子发射断层扫描（PET）成像在阿尔茨海默病（AD）研究中的应用日益广泛，但其在疾病早期状态下的效用可能受到传统定量或定性评估技术的限制。卷积神经网络（CNN）在学习用于图像分类的空间模式方面很有效。
从多项研究中汇总了18F-MK6240（n = 320）和AV-1451（n = 446）的PET图像。我们对放射性配体、启发式方法和架构的不同排列进行了迭代。在预测记忆障碍方面，将模型性能与基于标准感兴趣区域（ROI）的方法进行了比较。我们可视化了网络的注意力以说明决策过程。
总体而言，模型具有较高的准确率（> 80%），平均敏感性和特异性良好（分别为75%和82%），并且与ROI标准相比具有相当或更高的准确率。模型注意力的可视化突出了tau放射性配体结合的已知特征。
CNN可以改善tau PET在疾病早期的作用，并扩展tau PET在几代放射性配体中的效用。
