Department of Radiology and Imaging Sciences, Center for Neuroimaging, Indiana University School of Medicine, Indianapolis, IN, USA.
Indiana Alzheimer's Disease Research Center, Indiana University School of Medicine, Indianapolis, IN, USA.
BMC Bioinformatics. 2020 Dec 28;21(Suppl 21):496. doi: 10.1186/s12859-020-03848-0.
Alzheimer's disease (AD) is the most common type of dementia, typically characterized by memory loss followed by progressive cognitive decline and functional impairment. Many clinical trials of potential therapies for AD have failed, and there is currently no approved disease-modifying treatment. Biomarkers for early detection and mechanistic understanding of disease course are critical for drug development and clinical trials. Amyloid has been the focus of most biomarker research. Here, we developed a deep learning-based framework to identify informative features for AD classification using tau positron emission tomography (PET) scans.
The 3D convolutional neural network (CNN)-based classification model of AD from cognitively normal (CN) yielded an average accuracy of 90.8% based on five-fold cross-validation. The LRP model identified the brain regions in tau PET images that contributed most to the AD classification from CN. The top identified regions included the hippocampus, parahippocampus, thalamus, and fusiform. The layer-wise relevance propagation (LRP) results were consistent with those from the voxel-wise analysis in SPM12, showing significant focal AD associated regional tau deposition in the bilateral temporal lobes including the entorhinal cortex. The AD probability scores calculated by the classifier were correlated with brain tau deposition in the medial temporal lobe in MCI participants (r = 0.43 for early MCI and r = 0.49 for late MCI).
A deep learning framework combining 3D CNN and LRP algorithms can be used with tau PET images to identify informative features for AD classification and may have application for early detection during prodromal stages of AD.
阿尔茨海默病（AD）是最常见的痴呆症类型，通常以记忆丧失为特征，随后认知能力逐渐下降和功能障碍。许多针对 AD 潜在疗法的临床试验都失败了，目前尚无批准的疾病修饰治疗方法。用于早期检测和对疾病过程的机制理解的生物标志物对于药物开发和临床试验至关重要。淀粉样蛋白一直是大多数生物标志物研究的重点。在这里，我们开发了一种基于深度学习的框架，使用 tau 正电子发射断层扫描（PET）扫描来识别 AD 分类的信息特征。
基于五重交叉验证，基于 3D 卷积神经网络（CNN）的认知正常（CN）AD 分类模型的平均准确率为 90.8%。LRP 模型确定了 tau PET 图像中对 AD 从 CN 分类贡献最大的大脑区域。被识别出的最重要区域包括海马体、海马旁回、丘脑和梭状回。层间相关性传播（LRP）的结果与 SPM12 中的体素分析结果一致，显示双侧颞叶（包括内嗅皮质）存在与 AD 相关的显著局灶性 tau 沉积。分类器计算的 AD 概率评分与 MCI 参与者内侧颞叶的脑 tau 沉积相关（早期 MCI 为 r=0.43，晚期 MCI 为 r=0.49）。
结合 3D CNN 和 LRP 算法的深度学习框架可用于 tau PET 图像，以识别 AD 分类的信息特征，并且可能适用于 AD 前驱期的早期检测。
