Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer's Disease and mild cognitive impairment identification.
Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer's Disease and mild cognitive impairment identification.
复制标题
DOI：
10.1016/j.neuroimage.2013.09.015
复制
发表时间：
2014-01-01
期刊：
影响因子：
5.7
通讯作者：
Shen D
中科院分区：
文献类型：
--
作者：
Liu F;Wee CY;Chen H;Shen D
先前的研究表明，使用多模态的综合信息可以显着改善阿尔茨海默病（AD）的诊断。然而，特征选择是分类中最重要的步骤之一，通常是针对每种模态单独执行的，这忽略了每个主题内潜在的强模态间关系。最近出现的多任务学习方法使得不同模态的联合特征选择成为可能。然而，不幸的是，联合特征选择可能会忽略不同方式传达的不同但互补的信息。我们提出了一种新颖的多任务特征选择方法来保留互补的模态间信息。具体来说，我们将每种模态的特征选择视为一项单独的任务，并进一步施加约束以保留模态间关系，此外还分别强制从每种模态选择的特征的稀疏性。在特征选择之后，进一步使用多核支持向量机（SVM）来集成从每种模态中选择的特征以进行分类。我们的方法使用从阿尔茨海默病神经影像倡议 (ADNI) 数据库获得的受试者基线 PET 和 MRI 图像进行评估。我们的方法取得了良好的性能，AD 识别准确率为 94.37%，ROC 曲线下面积 (AUC) 为 0.9724；轻度认知障碍 (MCI) 识别准确率为 78.80%，AUC 为 0.8284。此外，所提出的方法在MCI转换器和MCI非转换器（到AD）之间的分离方面实现了67.83%的准确度和0.6957的AUC。这些性能证明了所提出的方法相对于最先进的分类方法的优越性。
Previous studies have demonstrated that the use of integrated information from multi-modalities could significantly improve diagnosis of Alzheimer’s Disease (AD). However, feature selection, which is one of the most important steps in classification, is typically performed separately for each modality, which ignores the potential strong inter-modality relationship within each subject. Recent emergence of multi-task learning approach makes the joint feature selection from different modalities possible. However, joint feature selection may unfortunately overlook different yet complementary information conveyed by different modalities. We propose a novel multi-task feature selection method to preserve the complementary inter-modality information. Specifically, we treat feature selection from each modality as a separate task and further impose a constraint for preserving the inter-modality relationship, besides separately enforcing the sparseness of the selected features from each modality. After feature selection, a multi-kernel Support Vector Machine (SVM) is further used to integrate the selected features from each modality for classification. Our method is evaluated using the baseline PET and MRI images of subjects obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our method achieves a good performance, with an accuracy of 94.37% and an Area Under the ROC Curve (AUC) of 0.9724 for AD identification, and also an accuracy of 78.80% and an AUC of 0.8284 for Mild Cognitive Impairment (MCI) identification. Moreover, the proposed method achieves an accuracy of 67.83% and an AUC of 0.6957 for separating between MCI converters and MCI non-converters (to AD). These performances demonstrate the superiority of the proposed method over the state-of-the-art classification methods.
登录
查看更多内容
DOI：
10.1016/s0140-6736(20)32205-4
发表时间：
2021-04-24
期刊：
Lancet (London, England)
影响因子：
--
作者：
Scheltens P;De Strooper B;Kivipelto M;Holstege H;Chételat G;Teunissen CE;Cummings J;van der Flier WM
通讯作者：
van der Flier WM
影响因子：
14
作者：
Brookmeyer, Ron;Johnson, Elizabeth;Arrighi, H. Michael
通讯作者：
Arrighi, H. Michael
影响因子：
4.2
作者：
Busatto, GF;Garrido, GEJ;Bottino, CM
通讯作者：
Bottino, CM
影响因子：
5.7
作者：
Dai, Zhengjia;Yan, Chaogan;He, Yong
通讯作者：
He, Yong
影响因子：
4
作者：
Derflinger, Sabine;Sorg, Christian;Muehlau, Mark
通讯作者：
Muehlau, Mark