Alzheimer disease (AD) exhibits spatially heterogeneous 3- or 4-repeat tau deposition across participants. Our overall goal was to develop an automated method to quantify the heterogeneous burden of tau deposition into a single number that would be clinically useful. Methods: We used tau PET scans from 3 independent cohorts: the Mayo Clinic Study of Aging and Alzheimer’s Disease Research Center (Mayo, n = 1,290), the Alzheimer’s Disease Neuroimaging Initiative (ADNI, n = 831), and the Open Access Series of Imaging Studies (OASIS-3, n = 430). A machine learning binary classification model was trained on Mayo data and validated on ADNI and OASIS-3 with the goal of predicting visual tau positivity (as determined by 3 raters following Food and Drug Administration criteria for ¹⁸F-flortaucipir). The machine learning model used region-specific SUV ratios scaled to cerebellar crus uptake. We estimated feature contributions based on an artificial intelligence–explainable method (Shapley additive explanations) and formulated a global tau summary measure, Tau Heterogeneity Evaluation in Alzheimer’s Disease (THETA) score, using SUV ratios and Shapley additive explanations for each participant. We compared the performance of THETA with that of commonly used meta–regions of interest (ROIs) using the Mini-Mental State Examination, the Clinical Dementia Rating–Sum of Boxes, clinical diagnosis, and histopathologic staging. Results: The model achieved a balanced accuracy of 95% on the Mayo test set and at least 87% on the validation sets. It classified tau-positive and -negative participants with an AUC of 1.00, 0.96, and 0.94 on the Mayo, ADNI, and OASIS-3 cohorts, respectively. Across all cohorts, THETA showed a better correlation with the Mini-Mental State Examination and the Clinical Dementia Rating–Sum of Boxes (ρ ≥ 0.45, P < 0.05) than did meta-ROIs (ρ < 0.44, P < 0.05) and discriminated between participants who were cognitively unimpaired and those who had mild cognitive impairment with an effect size of 10.09, compared with an effect size of 3.08 for meta-ROIs. Conclusion: Our proposed approach identifies positive tau PET scans and provides a quantitative summary measure, THETA, that effectively captures heterogeneous tau deposition observed in AD. The application of THETA for quantifying tau PET in AD exhibits great potential.

阿尔茨海默病 (AD) 在参与者中表现出空间异质的 3 或 4 重复 tau 沉积。我们的总体目标是开发一种自动化方法，将 tau 沉积的异质负担量化为临床有用的单一数字。方法：我们使用来自 3 个独立队列的 tau PET 扫描：梅奥诊所衰老研究和阿尔茨海默病研究中心（Mayo， n = 1,290）、阿尔茨海默病神经影像计划（ADNI， n = 831）和开放获取系列影像学研究（OASIS-3， n = 430）。机器学习二元分类模型在 Mayo 数据上进行了训练，并在 ADNI 和 OASIS-3 上进行了验证，目的是预测视觉 tau 阳性率（由 3 名评估者根据¹⁸ F-flortaucipir 标准确定）。机器学习模型使用了根据小脑小腿吸收程度调整的区域特定 SUV 比率。我们基于人工智能可解释的方法（Shapley 附加解释）估计了特征贡献，并使用每个参与者的 SUV 比率和 Shapley 附加解释，制定了全局 tau 汇总测量、阿尔茨海默病 Tau 异质性评估 (THETA) 评分。我们使用简易精神状态检查、临床痴呆评分框总和、临床诊断和组织病理学分期，将 THETA 的性能与常用的元感兴趣区域 (ROI) 的性能进行了比较。结果：该模型在 Mayo 测试集上实现了 95% 的平衡准确度，在验证集上实现了至少 87% 的平衡准确度。它将 Mayo、ADNI 和 OASIS-3 队列中的 tau 阳性和阴性参与者分类，AUC 分别为 1.00、0.96 和 0.94。 在所有队列中，THETA 与简易精神状态检查和临床痴呆评分框总和 (ρ ≥ 0.45， P < 0.05) 的相关性优于荟​​萃 ROI (ρ < 0.44， P < 0.05) ）并区分认知未受损的参与者和轻度认知受损的参与者，效果大小为 10.09，而元 ROI 的效果大小为 3.08。结论：我们提出的方法可识别阳性 tau PET 扫描，并提供定量汇总测量 THETA，该测量可有效捕获 AD 中观察到的异质 tau 沉积。 THETA 在 AD 中定量 tau PET 的应用展现出巨大的潜力。