• 2015-2024close
• Open Access close
• Closed Access close
• Restricted close
• Publications close
• Other research products close
• CA close
• Frontiers in Neuroscience close

IntroductionAlzheimer's disease (AD) is a neurodegenerative disease that significantly impacts the quality of life of patients and their families. Neuroimaging-driven brain age prediction has been proposed as a potential biomarker to detect mental disorders, such as AD, aiding in studying its effects on functional brain networks. Previous studies have shown that individuals with AD display impaired resting-state functional connections. However, most studies on brain age prediction have used structural magnetic resonance imaging (MRI), with limited studies based on resting-state functional MRI (rs-fMRI).MethodsIn this study, we applied a graph neural network (GNN) model on controls to predict brain ages using rs-fMRI in patients with AD. We compared the performance of the GNN model with traditional machine learning models. Finally, the post hoc model was also used to identify the critical brain regions in AD.ResultsThe experimental results demonstrate that our GNN model can predict brain ages of normal controls using rs-fMRI data from the ADNI database. Moreover the differences between brain ages and chronological ages were more significant in AD patients than in normal controls. Our results also suggest that AD is associated with accelerated brain aging and that the GNN model based on resting-state functional connectivity is an effective tool for predicting brain age.DiscussionOur study provides evidence that rs-fMRI is a promising modality for brain age prediction in AD research, and the GNN model proves to be effective in predicting brain age. Furthermore, the effects of the hippocampus, parahippocampal gyrus, and amygdala on brain age prediction are verified.

PurposeBrain 2-Deoxy-2-[18F]fluoroglucose ([18F]FDG-PET) is widely used in the diagnostic workup of Alzheimer’s disease (AD). Current tools for uptake analysis rely on non-personalized templates, which poses a challenge as decreased glucose uptake could reflect neuronal dysfunction, or heterogeneous brain morphology associated with normal aging. Overcoming this, we propose a deep learning method for synthesizing a personalized [18F]FDG-PET baseline from the patient’s own MRI, and showcase its applicability in detecting AD pathology.MethodsWe included [18F]FDG-PET/MRI data from 123 patients of a local cohort and 600 patients from ADNI. A supervised, adversarial model with two connected Generative Adversarial Networks (GANs) was trained on cognitive normal (CN) patients with transfer-learning to generate full synthetic baseline volumes (sbPET) (192 × 192 × 192) which reflect healthy uptake conditioned on brain anatomy. Synthetic accuracy was measured by absolute relative %-difference (Abs%), relative %-difference (RD%), and peak signal-to-noise ratio (PSNR). Lastly, we deployed the sbPET images in a fully personalized method for localizing metabolic abnormalities.ResultsThe model achieved a spatially uniform Abs% of 9.4%, RD% of 0.5%, and a PSNR of 26.3 for CN subjects. The sbPET images conformed to the anatomical information dictated by the MRI and proved robust in presence of atrophy. The personalized abnormality method correctly mapped the pathology of AD subjects while showing little to no anomalies for CN subjects.ConclusionThis work demonstrated the feasibility of synthesizing fully personalized, healthy-appearing [18F]FDG-PET images. Using these, we showcased a promising application in diagnosing AD, and theorized the potential value of sbPET images in other neuroimaging routines.

In Alzheimer's disease, the researchers found that if the patients were treated at the early stage of the disease, it could effectively delay the development of the disease. At present, multi-modal feature selection is widely used in the early diagnosis of Alzheimer's disease. However, existing multi-modal feature selection algorithms focus on learning the internal information of multiple modalities. They ignore the relationship between modalities, the importance of each modality and the local structure in the multi-modal data. In this paper, we propose a multi-modal feature selection algorithm with anchor graph for Alzheimer's disease. Specifically, we first use the least square loss and l2,1−norm to obtain the weight of the feature under each modality. Then we embed a modal weight factor into the objective function to obtain the importance of each modality. Finally, we use anchor graph to quickly learn the local structure information in multi-modal data. In addition, we also verify the validity of the proposed algorithm on the published ADNI dataset.

BackgroundAlzheimer’s Disease (AD) is an age-related neurodegenerative disease with a poorly understood etiology, shown to be partly genetic. Glucose hypometabolism, extracellular Amyloid-beta (Aβ) deposition, and intracellular Tau deposition are cardinal features of AD and display characteristic spatial patterns in the brain. We hypothesize that regional differences in underlying gene expression confer either resistance or susceptibility to AD pathogenic processes and are associated with these spatial patterns. Data-driven methods for the identification of genes involved in AD pathogenesis complement hypothesis-driven approaches that reflect current theories about the disease. Here we present a data driven method for the identification of genes involved in AD pathogenesis based on comparing spatial patterns of normal gene expression to Positron Emission Tomography (PET) images of glucose hypometabolism, Aβ deposition, and Tau deposition.MethodsWe performed correlations between the cerebral cortex microarray samples from the six cognitively normal (CN) post-mortem Allen Human Brain Atlas (AHBA) specimens and PET FDG-18, AV-45, and AV-1451 tracer images from AD and CN participants in the Alzheimer’s Disease and Neuroimaging Initiative (ADNI) database. Correlation coefficients for each gene by each ADNI subject were then entered into a partial least squares discriminant analysis (PLS-DA) to determine sets that best classified the AD and CN groups. Pathway analysis via BioPlanet 2019 was then used to infer the function of implicated genes.ResultsWe identified distinct sets of genes strongly associated with each PET modality. Pathway analyses implicated novel genes involved in mitochondrial function, and Notch signaling, as well as genes previously associated with AD.ConclusionUsing an unbiased approach, we derived sets of genes with expression patterns spatially associated with FDG hypometabolism, Aβ deposition, and Tau deposition in AD. This methodology may complement population-based approaches for identifying the genetic underpinnings of AD.

Non-negative matrix factorization, which decomposes the input non-negative matrix into product of two non-negative matrices, has been widely used in the neuroimaging field due to its flexible interpretability with non-negativity property. Nowadays, especially in the neuroimaging field, it is common to have at least thousands of voxels while the sample size is only hundreds. The non-negative matrix factorization encounters both computational and theoretical challenge with such high-dimensional data, i.e., there is no guarantee for a sparse and part-based representation of data. To this end, we introduce a co-sparse non-negative matrix factorization method to high-dimensional data by simultaneously imposing sparsity in both two decomposed matrices. Instead of adding some sparsity induced penalty such as l1 norm, the proposed method directly controls the number of non-zero elements, which can avoid the bias issues and thus yield more accurate results. We developed an alternative primal-dual active set algorithm to derive the co-sparse estimator in a computationally efficient way. The simulation studies showed that our method achieved better performance than the state-of-art methods in detecting the basis matrix and recovering signals, especially under the high-dimensional scenario. In empirical experiments with two neuroimaging data, the proposed method successfully detected difference between Alzheimer's patients and normal person in several brain regions, which suggests that our method may be a valuable toolbox for neuroimaging studies.

Background: In recent years, classification frameworks using imaging data have shown that multimodal classification methods perform favorably over the use of a single imaging modality for the diagnosis of Alzheimer’s Disease. The currently used clinical approach often emphasizes the use of qualitative MRI and/or PET data for clinical diagnosis. Based on the hypothesis that classification of isolated imaging modalities is not predictive of their respective value in combined approaches, we investigate whether the combination of T1 Weighted MRI and diffusion tensor imaging (DTI) can yield an equivalent performance as the combination of quantitative structural MRI (sMRI) with amyloid-PET.Methods: We parcellated the brain into regions of interest (ROI) following different anatomical labeling atlases. For each region of interest different metrics were extracted from the different imaging modalities (sMRI, PiB-PET, and DTI) to be used as features. Thereafter, the feature sets were reduced using an embedded-based feature selection method. The final reduced sets were then used as input in support vector machine (SVM) classifiers. Three different base classifiers were created, one for each imaging modality, and validated using internal (n = 41) and external data from the ADNI initiative (n = 330 for sMRI, n = 148 for DTI and n = 55 for PiB-PET) sources. Finally, the classifiers were ensembled using a weighted method in order to evaluate the performance of different combinations.Results: For the base classifiers the following performance levels were found: sMRI-based classifier (accuracy, 92%; specificity, 97% and sensitivity, 87%), PiB-PET (accuracy, 91%; specificity, 89%; and sensitivity, 92%) and the lowest performance was attained with DTI (accuracy, 80%; specificity, 76%; and sensitivity, 82%). From the multimodal approaches, when integrating two modalities, the following results were observed: sMRI+PiB-PET (accuracy, 98%; specificity, 98%; and sensitivity, 99%), sMRI+DTI (accuracy, 97%; specificity, 99%; and sensitivity, 94%) and PiB-PET+DTI (accuracy, 91%; specificity, 90%; and sensitivity, 93%). Finally, the combination of all imaging modalities yielded an accuracy of 98%, specificity of 97% and sensitivity of 99%.Conclusion: Although DTI in isolation shows relatively poor performance, when combined with structural MR, it showed a surprising classification performance which was comparable to MR combined with amyloid PET. These results are consistent with the notion that white matter changes are also important in Alzheimer’s Disease.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder. It is one of the leading sources of morbidity and mortality in the aging population AD cardinal symptoms include memory and executive function impairment that profoundly alters a patient’s ability to perform activities of daily living. People with mild cognitive impairment (MCI) exhibit many of the early clinical symptoms of patients with AD and have a high chance of converting to AD in their lifetime. Diagnostic criteria rely on clinical assessment and brain magnetic resonance imaging (MRI). Many groups are working to help automate this process to improve the clinical workflow. Current computational approaches are focused on predicting whether or not a subject with MCI will convert to AD in the future. To our knowledge, limited attention has been given to the development of automated computer-assisted diagnosis (CAD) systems able to provide an AD conversion diagnosis in MCI patient cohorts followed longitudinally. This is important as these CAD systems could be used by primary care providers to monitor patients with MCI. The method outlined in this paper addresses this gap and presents a computationally efficient pre-processing and prediction pipeline, and is designed for recognizing patterns associated with AD conversion. We propose a new approach that leverages longitudinal data that can be easily acquired in a clinical setting (e.g., T1-weighted magnetic resonance images, cognitive tests, and demographic information) to identify the AD conversion point in MCI subjects with AUC = 84.7. In contrast, cognitive tests and demographics alone achieved AUC = 80.6, a statistically significant difference (n = 669, p < 0.05). We designed a convolutional neural network that is computationally efficient and requires only linear registration between imaging time points. The model architecture combines Attention and Inception architectures while utilizing both cross-sectional and longitudinal imaging and clinical information. Additionally, the top brain regions and clinical features that drove the model’s decision were investigated. These included the thalamus, caudate, planum temporale, and the Rey Auditory Verbal Learning Test. We believe our method could be easily translated into the healthcare setting as an objective AD diagnostic tool for patients with MCI.