Deep residual learning for neuroimaging: An application to predict progression to Alzheimer's disease
Deep residual learning for neuroimaging: An application to predict progression to Alzheimer's disease
复制标题
DOI：
10.1016/j.jneumeth.2020.108701
复制
发表时间：
2020-06-01
影响因子：
3
通讯作者：
Calhoun, Vince
中科院分区：
文献类型：
--
作者：
Abrol, Anees;Bhattarai, Manish;Calhoun, Vince
背景：深度学习方法在通用图像处理中无与伦比的性能促使其扩展到神经成像数据。这些方法学习抽象的神经解剖学和脑功能改变，可以在脑疾病分类、预测疾病进展和定位脑异常方面取得卓越的表现。新方法：这项工作研究了一种改进形式的深度残差神经网络（ResNet）在预测从轻度认知障碍（MCI）到阿尔茨海默病（AD）进展的特定应用中研究神经影像学数据的适用性。预测首先通过只使用MCI个体训练深度模型进行，然后是一个额外训练AD和控制的领域迁移学习版本。我们还演示了一种基于网络遮挡的方法来定位异常。结果：实施的框架捕获了成功预测AD进展的非线性特征，并符合各种临床评分的谱。在重复的交叉验证设置中，学习到的预测模型显示出与先前AD报告相对应的高度相似的峰值激活。与现有方法的比较：与经典支持向量机和堆叠自编码器框架相比，实现的架构实现了显着的性能改进（p < 0.005），在数字上优于单独使用sMRI数据的最先进性能（比第二好的性能方法高出7%），并且在考虑使用多种神经成像模式学习的最先进性能的1%以内。结论：所探索的框架反映了深度学习架构在学习细微预测特征方面的巨大潜力，以及在预测和理解疾病进展等关键应用中的实用性。
Background: The unparalleled performance of deep learning approaches in generic image processing has motivated its extension to neuroimaging data. These approaches learn abstract neuroanatomical and functional brain alterations that could enable exceptional performance in classification of brain disorders, predicting disease progression, and localizing brain abnormalities.New Method: This work investigates the suitability of a modified form of deep residual neural networks (ResNet) for studying neuroimaging data in the specific application of predicting progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD). Prediction was conducted first by training the deep models using MCI individuals only, followed by a domain transfer learning version that additionally trained on AD and controls. We also demonstrate a network occlusion based method to localize abnormalities.Results: The implemented framework captured non-linear features that successfully predicted AD progression and also conformed to the spectrum of various clinical scores. In a repeated cross-validated setup, the learnt predictive models showed highly similar peak activations that corresponded to previous AD reports.Comparison with existing methods: The implemented architecture achieved a significant performance improvement over the classical support vector machine and the stacked autoencoder frameworks (p < 0.005), numerically better than state-of-the-art performance using sMRI data alone ( > 7% than the second-best performing method) and within 1% of the state-of-the-art performance considering learning using multiple neuroimaging modalities as well.Conclusions: The explored frameworks reflected the high potential of deep learning architectures in learning subtle predictive features and utility in critical applications such as predicting and understanding disease progression.