Department of Biomedical Engineering, National University of Singapore, Singapore; The N.1 Institute for Health, National University of Singapore, Singapore; Institute of Data Science, National University of Singapore, Singapore; NUS (Suzhou) Research Institute, Suzhou, China; School of Computer Engineering and Science, Shanghai University, China; Department of Biomedical Engineering, the Johns Hopkins University, USA.
School of Computer Engineering and Science, Shanghai University, China.
Neuroimage Clin. 2022;34:102993. doi: 10.1016/j.nicl.2022.102993. Epub 2022 Mar 24.
This study employed a deep learning longitudinal model, graph convolutional and recurrent neural network (graph-CNN-RNN), on a series of brain structural MRI scans for AD prognosis. It characterized whole-brain morphology via incorporating longitudinal cortical and subcortical morphology and defined a probabilistic risk for the prediction of AD as a function of age prior to clinical diagnosis. The graph-CNN-RNN model was trained on half of the Alzheimer's Disease Neuroimaging Initiative dataset (ADNI, n = 1559) and validated on the other half of the ADNI dataset and the Open Access Series of Imaging Studies-3 (OASIS-3, n = 930). Our findings demonstrated that the graph-CNN-RNN can reliably and robustly diagnose AD at the accuracy rate of 85% and above across all the time points for both datasets. The graph-CNN-RNN predicted the AD conversion from 0 to 4 years before the AD onset at ∼80% of accuracy. The AD probabilistic risk was associated with clinical traits, cognition, and amyloid burden assessed using [18F]-Florbetapir (AV45) positron emission tomography (PET) across all the time points. The graph-CNN-RNN provided the quantitative trajectory of brain morphology from prognosis to overt stages of AD. Such a deep learning tool and the AD probabilistic risk have great potential in clinical applications for AD prognosis.
本研究采用深度学习纵向模型，图卷积和递归神经网络（graph-CNN-RNN），对一系列脑结构 MRI 扫描进行 AD 预后分析。该模型通过结合纵向皮质和皮质下形态学特征，对全脑形态进行了描述，并定义了一种 AD 预测的概率风险，该风险作为临床诊断前年龄的函数。graph-CNN-RNN 模型在阿尔茨海默病神经影像学倡议数据集（ADNI，n=1559）的一半数据集上进行了训练，并在 ADNI 数据集的另一半和开放获取影像学研究系列 3（OASIS-3，n=930）上进行了验证。研究结果表明，该模型在两个数据集的所有时间点上都能以 85%以上的准确率可靠而稳健地诊断 AD。graph-CNN-RNN 能够在 AD 发病前 0 到 4 年的时间内以约 80%的准确率预测 AD 转化。AD 概率风险与临床特征、认知和使用 [18F]-Florbetapir（AV45）正电子发射断层扫描（PET）评估的淀粉样蛋白负荷相关，在所有时间点均如此。graph-CNN-RNN 提供了从预后到 AD 明显阶段的脑形态定量轨迹。这种深度学习工具和 AD 概率风险在 AD 预后的临床应用中具有很大的潜力。
