Accurate diagnosis and prognosis of Alzheimer's disease are crucial to develop new therapies and reduce the associated costs. Recently, with the advances of convolutional neural networks, methods have been proposed to automate these two tasks using structural MRI. However, these methods often suffer from lack of interpretability, generalization, and can be limited in terms of performance. In this paper, we propose a novel deep framework designed to overcome these limitations. Our framework consists of two stages. In the first stage, we propose a deep grading model to extract meaningful features. To enhance the robustness of these features against domain shift, we introduce an innovative collective artificial intelligence strategy for training and evaluating steps. In the second stage, we use a graph convolutional neural network to better capture AD signatures. Our experiments based on 2074 subjects show the competitive performance of our deep framework compared to state-of-the-art methods on different datasets for both AD diagnosis and prognosis.
翻译:对阿尔茨海默氏病的准确诊断和预测对于发展新疗法和降低相关成本至关重要。最近,随着神经神经网络的进化,提出了利用结构性磁共振使这两项任务自动化的方法。然而,这些方法往往缺乏可解释性、概括性,在性能方面可能受到限制。在本文件中,我们提出了一个旨在克服这些限制的新颖的深层次框架。我们的框架由两个阶段组成。在第一阶段,我们提出一个深层次的分级模式,以提取有意义的特征。为了提高这些特征的稳健性,我们提出了针对域变换的创新性集体人工智能战略。在第二阶段,我们使用图表性神经网络更好地获取自动签名。我们基于2074年主题的实验显示了我们深层次框架的竞争性表现,与关于自动诊断和预测性病的不同数据集的最新方法相比。