Instituto de Biofísica e Engenharia Biomédica, Faculdade de Ciências da Universidade de Lisboa, Lisbon, Portugal.
Faculdade de Ciências e Tecnologia e UNINOVA-CTS, Universidade Nova de Lisboa, Caparica, Portugal.
J Alzheimers Dis. 2024;101(4):1293-1305. doi: 10.3233/JAD-240366.
Early detection of amyloid-β (Aβ) positivity is essential for an accurate diagnosis and treatment of Alzheimer's disease (AD), but it is currently costly and/or invasive.
We aimed to classify Aβ positivity (Aβ+) using morphometric features from magnetic resonance imaging (MRI), a more accessible and non-invasive technique, in two clinical population scenarios: one containing AD, mild cognitive impairment (MCI) and cognitively normal (CN) subjects, and another only cognitively impaired subjects (AD and MCI).
Demographic, cognitive (Mini-Mental State Examination [MMSE] scores), regional morphometry MRI (volumes, areas, and thicknesses), and derived morphometric graph theory (GT) features from all subjects (302 Aβ+, age: 73.3±7.2, 150 male; 246 Aβ-, age: 71.1±7.1, 131 male) were combined in different feature sets. We implemented a machine learning workflow to find the best Aβ+ classification model.
In an AD+MCI+CN population scenario, the best-performing model selected 120 features (107 GT features, 12 regional morphometric features and the MMSE total score) and achieved a negative predictive value (NPVadj) of 68.4%, and a balanced accuracy (BAC) of 66.9%. In a AD+MCI scenario, the best model obtained NPVadj of 71.6%, and BAC of 70.7%, using 180 regional morphometric features (98 volumes, 52 areas and 29 thicknesses from temporal, parietal, and frontal brain regions).
Although with currently limited clinical applicability, regional MRI morphometric features have clinical usefulness potential for detecting Aβ status, which may be augmented by a combination with cognitive data when cognitively normal subjects make up a substantial part of the population presenting for diagnosis.
早期发现淀粉样蛋白-β（Aβ）阳性对于阿尔茨海默病（AD）的准确诊断和治疗至关重要，但目前这种方法既昂贵又具有侵入性。
我们旨在使用磁共振成像（MRI）的形态特征对两种临床人群中的 Aβ 阳性（Aβ+）进行分类，这是一种更易获取且非侵入性的技术：一种包含 AD、轻度认知障碍（MCI）和认知正常（CN）受试者，另一种仅包含认知障碍（AD 和 MCI）受试者。
对所有受试者（302 名 Aβ+，年龄：73.3±7.2，150 名男性；246 名 Aβ-，年龄：71.1±7.1，131 名男性）的人口统计学、认知（简易精神状态检查[MMSE]评分）、区域性形态测量 MRI（体积、面积和厚度）和衍生形态测量图论（GT）特征进行了组合，并将其纳入不同的特征集。我们实施了机器学习工作流程，以找到最佳的 Aβ+分类模型。
在 AD+MCI+CN 人群场景中，表现最佳的模型选择了 120 个特征（107 个 GT 特征、12 个区域性形态学特征和 MMSE 总分），并获得了 68.4%的阴性预测值（NPVadj）和 66.9%的平衡准确率（BAC）。在 AD+MCI 场景中，最佳模型使用来自颞叶、顶叶和额叶脑区的 180 个区域性形态学特征（98 个体积、52 个面积和 29 个厚度），获得了 71.6%的 NPVadj 和 70.7%的 BAC。
尽管目前的临床适用性有限，但区域性 MRI 形态学特征具有检测 Aβ 状态的临床应用潜力，当认知正常的受试者构成就诊人群的很大一部分时，这种方法可能会通过与认知数据相结合而得到增强。
