Attention-Guided Autoencoder for Automated Progression Prediction of Subjective Cognitive Decline With Structural MRI.
Attention-Guided Autoencoder for Automated Progression Prediction of Subjective Cognitive Decline With Structural MRI.
复制标题
DOI：
10.1109/jbhi.2023.3257081
复制
发表时间：
2023-06
影响因子：
7.7
通讯作者：
中科院分区：
文献类型：
--
作者：
主观认知衰退（SCD）是阿尔茨海默病（AD）的临床前阶段，其发生甚至早于轻度认知障碍（MCI）。渐进式 SCD 将转化为 MCI，并有可能进一步演变为 AD。因此，利用神经影像技术（如结构MRI）早期识别进展性SCD对于AD的早期干预具有重要的临床价值。然而，现有的基于 MRI 的机器/深度学习方法通常存在小样本问题且缺乏可解释性。为此，我们提出了一种具有域转移学习（IADT）的可解释自动编码器模型，用于 SCD 的进展预测。首先，所提出的模型可以利用目标域（即 SCD）和辅助域（例如 AD 和 NC）的 MRI 来进行渐进式 SCD 识别。此外，它可以通过注意力机制自动定位与疾病相关的大脑感兴趣区域（在大脑图集中定义），具有良好的可解释性。此外，IADT模型训练和测试简单，在CPU上仅需5~10秒，适合小数据集的医疗任务。在公开的 ADNI 数据集和私有 CLAS 数据集上进行的大量实验证明了该方法的有效性。
Subjective cognitive decline (SCD) is the preclinical stage of Alzheimer’s disease (AD) which happens even earlier than mild cognitive impairment (MCI). Progressive SCD will convert to MCI with the potential of further evolving to AD. Therefore, early identification of progressive SCD with neuroimaging techniques (e.g., structural MRI) is of great clinical value for early intervention of AD. However, existing MRI-based machine/deep learning methods usually suffer the small-sample-size problem and lack interpretability. To this end, we propose an interpretable autoencoder model with domain transfer learning (IADT) for progression prediction of SCD. Firstly, the proposed model can leverage MRIs from both the target domain (i.e., SCD) and auxiliary domains (e.g., AD and NC) for progressive SCD identification. Besides, it can automatically locate the disease-related brain regions of interest (defined in brain atlases) through an attention mechanism, which shows good interpretability. In addition, the IADT model is straightforward to train and test with only 5~10 seconds on CPUs and is suitable for medical tasks with small datasets. Extensive experiments on the publicly available ADNI dataset and a private CLAS dataset have demonstrated the effectiveness of the proposed method.