sMRI-PatchNet: A Novel Efficient Explainable Patch-Based Deep Learning Network for Alzheimer's Disease Diagnosis With Structural MRI
sMRI-PatchNet: A Novel Efficient Explainable Patch-Based Deep Learning Network for Alzheimer's Disease Diagnosis With Structural MRI
复制标题
DOI：
10.1109/access.2023.3321220
复制
发表时间：
2023-01-01
期刊：
影响因子：
3.9
通讯作者：
Zhang，Daoqiang
中科院分区：
文献类型：
--
作者：
Zhang，Xin;Han，Liangxiu;Zhang，Daoqiang
结构磁共振成像（sMRI）由于其对软组织的高对比度和高空间分辨率，可以识别细微的大脑变化。它已被广泛用于诊断神经系统脑疾病，如阿尔茨海默病（AD）。然而，三维高分辨率数据的大小对数据分析和处理提出了重大挑战。由于大脑中只有少数区域显示出与AD高度相关的结构变化，因此将整个数据划分为几个规则块的基于块的方法已显示出更有效的图像分析的前景。基于块的方法的主要挑战包括识别的歧视补丁，从离散的歧视补丁的组合功能，并设计适当的分类器。这项工作提出了一种新的高效的基于补丁的深度学习网络（sMRI PatchNet），具有可解释的补丁定位和选择用于AD诊断。具体来说，它由两个主要组成部分组成：1）一个快速有效的可解释的补丁选择方法，用于确定最具鉴别力的补丁;和2）一种新的基于补丁的网络，用于提取深度特征和AD分类，并使用位置嵌入来保留位置信息，能够捕获补丁间和补丁内的全局和局部信息。该方法已应用于AD分类和预测过渡状态中度认知障碍（MCI）转换与真实的数据集。实验结果表明，与现有方法相比，该方法能够有效地识别具有鉴别力的病变部位，并显著减少了所使用的斑块数量，在准确性、计算性能和可推广性方面具有更好的性能。
Structural magnetic resonance imaging (sMRI) can identify subtle brain changes due to its high contrast for soft tissues and high spatial resolution. It has been widely used in diagnosing neurological brain diseases, such as Alzheimer’s disease (AD). However, the size of 3D high-resolution data poses a significant challenge for data analysis and processing. Since only a few areas of the brain show structural changes highly associated with AD, the patch-based methods dividing the whole data into several regular patches have shown promising for more efficient image analysis. The major challenges of the patch-based methods include identifying the discriminative patches, combining features from the discrete discriminative patches, and designing appropriate classifiers. This work proposes a novel efficient patch-based deep learning network (sMRI-PatchNet) with explainable patch localisation and selection for AD diagnosis. Specifically, it consists of two primary components: 1) A fast and efficient explainable patch selection method for determining the most discriminative patches; and 2) A novel patch-based network for extracting deep features and AD classification with position embeddings to retain position information, capable of capturing the global and local information of inter- and intra-patches. This method has been applied for the AD classification and the prediction of the transitional state moderate cognitive impairment (MCI) conversion with real datasets. The experimental evaluation shows that the proposed method can identify discriminative pathological locations effectively with a significant reduction on patch numbers used, providing better performance in terms of accuracy, computing performance, and generalizability, in contrast to the state-of-the-art methods.