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.

中文翻译：

---

用于阿尔茨海默病分类的 tau PET 信息特征的深度学习检测

阿尔茨海默病 (AD) 是最常见的痴呆类型，通常以记忆丧失为特征，随后是进行性认知衰退和功能障碍。许多针对 AD 潜在疗法的临床试验都失败了，目前还没有批准的疾病改善疗法。用于早期检测和疾病过程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，我们开发了一个基于深度学习的框架，以使用 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 3D 卷积神经网络 (CNN) 的认知正常 (CN) AD 分类模型基于五重交叉验证产生了 90.8% 的平均准确度。LRP 模型识别了 tau PET 图像中对 CN 的 AD 分类贡献最大的大脑区域。最常见的区域包括海马、海马旁、丘脑和梭形。逐层相关性传播 (LRP) 结果与 SPM12 中体素分析的结果一致，显示在包括内嗅皮质在内的双侧颞叶中存在显着的局灶性 AD 相关区域 tau 沉积。分类器计算的 AD 概率分数与 MCI 参与者内侧颞叶的脑 tau 沉积相关（早期 MCI r = 0.43，晚期 MCI r = 0.49）。