Manifold regularized multi-task feature selection for multi-modality classification in Alzheimer's disease.
Manifold regularized multi-task feature selection for multi-modality classification in Alzheimer's disease.
复制标题
DOI：
10.1007/978-3-642-40811-3_35
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Shen, Dinggang
中科院分区：
文献类型：
--
作者：
Jie, Biao;Zhang, Daoqiang;Cheng, Bo;Shen, Dinggang
阿尔茨海默病（AD）及其前驱期（即，轻度认知障碍（MCI）对于疾病的可能延迟和早期治疗非常重要。近来，多模态方法已经被用于融合来自多个不同且互补的成像和非成像模态的信息。虽然有一些现有的多模态方法，他们中的一些已经解决了问题的联合识别疾病相关的大脑区域从多模态数据进行分类。在本文中，我们提出了一个流形正则化的多任务学习框架，以联合选择多模态数据的特征。具体来说，我们制定的多模态分类作为一个多任务的学习框架，其中每个任务的重点是基于每个模态的分类。为了捕获多个任务之间的内在相关性（即，模态），我们采用了一个组稀疏正则化，它确保只有少量的功能被联合选择。此外，我们引入了一个新的基于流形的拉普拉斯正则化项，以保持每个任务的原始数据的几何分布，这可以导致选择更具鉴别力的特征。此外，我们将我们的方法扩展到半监督设置，这是非常重要的，因为获取大量的标记数据（即，疾病诊断）通常是昂贵和耗时的，而未标记数据的收集相对容易得多。为了验证我们的方法，我们已经进行了广泛的评估基线磁共振成像（MRI）和氟脱氧葡萄糖正电子发射断层扫描（FDG-PET）数据的阿尔茨海默病神经影像倡议（ADNI）数据库。我们的实验结果证明了所提出的方法的有效性。
Accurate diagnosis of Alzheimer’s disease (AD), as well as its pro-dromal stage (i.e., mild cognitive impairment, MCI), is very important for possible delay and early treatment of the disease. Recently, multi-modality methods have been used for fusing information from multiple different and complementary imaging and non-imaging modalities. Although there are a number of existing multi-modality methods, few of them have addressed the problem of joint identification of disease-related brain regions from multi-modality data for classification. In this paper, we proposed a manifold regularized multi-task learning framework to jointly select features from multi-modality data. Specifically, we formulate the multi-modality classification as a multi-task learning framework, where each task focuses on the classification based on each modality. In order to capture the intrinsic relatedness among multiple tasks (i.e., modalities), we adopted a group sparsity regularizer, which ensures only a small number of features to be selected jointly. In addition, we introduced a new manifold based Laplacian regularization term to preserve the geometric distribution of original data from each task, which can lead to the selection of more discriminative features. Furthermore, we extend our method to the semi-supervised setting, which is very important since the acquisition of a large set of labeled data (i.e., diagnosis of disease) is usually expensive and time-consuming, while the collection of unlabeled data is relatively much easier. To validate our method, we have performed extensive evaluations on the baseline Magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET) data of Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our experimental results demonstrate the effectiveness of the proposed method.
登录
查看更多内容
影响因子：
14
作者：
Brookmeyer, Ron;Johnson, Elizabeth;Arrighi, H. Michael
通讯作者：
Arrighi, H. Michael
用于 MCI 转换预测的域迁移学习
DOI：
10.1007/978-3-642-33415-3_11
发表时间：
2012
期刊：
LECTURE NOTES IN ARTIFICIAL INTELLIGENCE
影响因子：
--
作者：
Cheng, Bo;Zhang, Daoqiang;Shen, Dinggang
通讯作者：
Shen, Dinggang
影响因子：
10.6
作者：
Shen, DG;Davatzikos, C
通讯作者：
Davatzikos, C
影响因子：
5.1
作者：
PUDIL, P;NOVOVICOVA, J;KITTLER, J
通讯作者：
KITTLER, J
影响因子：
5.7
作者：
Zhang D;Wang Y;Zhou L;Yuan H;Shen D;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative