CSF tau protein and FDG PET in patients with aging-associated cognitive decline and Alzheimer's disease

The mediational effects of FDG hypometabolism on the association between cerebrospinal fluid biomarkers and neurocognitive function

Positive cerebrospinal fluid (CSF) biomarkers of tau and amyloid beta42 suggest possible active underlying Alzheimer's disease (AD) including neurometabolic dysfunction and neurodegeneration leading to eventual cognitive decline. But the temporal relationship between CSF, imaging markers of neural function, and cognition has not been described. Using a statistical mediation model, we examined relationships between cerebrospinal fluid (CSF) analytes (hyperphosphorylated tau (p-Tau(181p)), β-amyloid peptides 1-42 (Aβ(1-42)), total tau (t-Tau), and their ratios); change in cognitive function; and change in [18F]fluorodeoxyglucose (FDG) uptake using positron emission tomography (PET). We hypothesized that a) abnormal CSF protein values at baseline, result in cognitive declines by decreasing neuronal glucose metabolism across time, and b) the role of altered glucose metabolism in the assumed causal chain varies by brain region and the nature of CSF protein alteration. Data from 412 individuals participating in Alzheimer's Disease Neuroimaging (ADNI) cohort studies were included in analyses. At baseline, individuals were cognitively normal (N = 82), or impaired: 241 with mild cognitive impairment, and 89 with Alzheimer's disease. A parallel-process latent growth curve model was used to test mediational effects of changes in regional FDG-PET uptake over time in relation to baseline CSF biomarkers and changes in cognition, measured with the 13-item Alzheimer Disease's Assessment Scale-cognitive subscale (ADAS-Cog). Findings suggested a causal sequence of events; specifically, FDG hypometabolism acted as a mediator between antecedent CSF biomarker alterations and subsequent cognitive impairment. Higher baseline concentrations of t-Tau, and p-Tau(181p) were more predictive of decline in cerebral glucose metabolism than lower baseline concentrations of Aβ(1-42). FDG-PET changes appeared to mediate t-Tau or t-Tau/Aβ(1-42)-associated cognitive change across all brain regions examined. Significant direct effects of alterations in Aβ(1-42) levels on hypometabolism were observed in a single brain region: middle/inferior temporal gyrus. Results support a temporal framework model in which reduced CSF amyloid-related biomarkers occur earlier in the pathogenic pathway, ultimately leading to detrimental cognitive effects. Also consistent with this temporal framework model, baseline markers of neurofibrillary degeneration predicted changes in brain glucose metabolism in turn causing longitudinal cognitive changes, suggesting that tau-related burden precedes neurometabolic dysfunction. While intriguing, the hypothesized mediational relationships require further validation.

Manifold regularized multitask feature learning for multimodality disease classification

Multimodality based methods have shown great advantages in classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Recently, multitask feature selection methods are typically used for joint selection of common features across multiple modalities. However, one disadvantage of existing multimodality based methods is that they ignore the useful data distribution information in each modality, which is essential for subsequent classification. Accordingly, in this paper we propose a manifold regularized multitask feature learning method to preserve both the intrinsic relatedness among multiple modalities of data and the data distribution information in each modality. Specifically, we denote the feature learning on each modality as a single task, and use group-sparsity regularizer to capture the intrinsic relatedness among multiple tasks (i.e., modalities) and jointly select the common features from multiple tasks. Furthermore, we introduce a new manifold-based Laplacian regularizer to preserve the data distribution information from each task. Finally, we use the multikernel support vector machine method to fuse multimodality data for eventual classification. Conversely, we also extend our method to the semisupervised setting, where only partial data are labeled. We evaluate our method using the baseline magnetic resonance imaging (MRI), fluorodeoxyglucose positron emission tomography (FDG-PET), and cerebrospinal fluid (CSF) data of subjects from AD neuroimaging initiative database. The experimental results demonstrate that our proposed method can not only achieve improved classification performance, but also help to discover the disease-related brain regions useful for disease diagnosis.

Inter-modality relationship constrained multi-modality multi-task feature selection for Alzheimer's Disease and mild cognitive impairment identification

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 potentially 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.