Structural magnetic resonance imaging (MRI) studies have shown that Alzheimer's Disease (AD) induces both localised and widespread neural degenerative changes throughout the brain. However, the absence of segmentation that highlights brain degenerative changes presents unique challenges for training CNN-based classifiers in a supervised fashion. In this work, we evaluated several unsupervised methods to train a feature extractor for downstream AD vs. CN classification. Using the 3D T1-weighted MRI data of cognitive normal (CN) subjects from the synthetic neuroimaging LDM100K dataset, lightweight 3D CNN-based models are trained for brain age prediction, brain image rotation classification, brain image reconstruction and a multi-head task combining all three tasks into one. Feature extractors trained on the LDM100K synthetic dataset achieved similar performance compared to the same model using real-world data. This supports the feasibility of utilising large-scale synthetic data for pretext task training. All the training and testing splits are performed on the subject-level to prevent data leakage issues. Alongside the simple preprocessing steps, the random cropping data augmentation technique shows consistent improvement across all experiments.

翻译：结构磁共振成像研究表明，阿尔茨海默病会引发大脑局部及广泛的神经退行性改变。然而，由于缺乏能够突显脑退行性变化的标注分割，这为以监督方式训练基于CNN的分类器带来了独特挑战。本研究评估了多种无监督方法，以训练用于下游AD与认知正常分类任务的特征提取器。利用合成神经影像数据集LDM100K中认知正常受试者的3D T1加权MRI数据，我们训练了轻量级3D CNN模型，分别用于脑龄预测、脑图像旋转分类、脑图像重建以及将三项任务结合的多头联合任务。基于LDM100K合成数据集训练的特征提取器，与使用真实世界数据的相同模型相比取得了相近的性能，这证实了利用大规模合成数据进行预训练任务可行性。所有训练集与测试集的划分均在受试者层面进行，以避免数据泄露问题。在简单预处理步骤的基础上，随机裁剪数据增强技术在所有实验中均展现出稳定的性能提升。