Advanced searches left 3/3

Alzheimer's Disease - Astrophysics Data System

Summarized by Plex Scholar
Last Updated: 14 April 2022

* If you want to update the article please login/register

Multi-task multi-level feature adversarial network for joint Alzheimer's disease diagnosis and atrophy localization using sMRI

Specifically, the linear-aligned T1 MR images were first processed by a lightweight CNN backbone to capture the shared intermediate feature representations, which were then extended to a global subnet for preliminary dementia diagnosis and a multi-task learning network for brain atrophy localization in a multi-task learning mode. To maintain global visibility against the local/instance features that can be used to enhance disease diagnosis, we further developed a module of multi-level feature adversarial learning that accounts for regularization to make global characteristics robust against the adversarial perturbation synthesized by the local/instance features to raise the diagnostic quality.

Source link: https://ui.adsabs.harvard.edu/abs/2022PMB....67h5002H/abstract


Bifurcation Analysis and Finite-Time Contraction Stability of an Alzheimer Disease Model

The stability of the unique positive balance and the Hopf bifurcation are investigated in the deterministic AD model. Modified by Markov switching process On the other hand, we investigate the finite-time contractive stability for the stochastic AD model modified by Markov switching process, which is focusing on the effects of unknown variables in the climate on AD.

Source link: https://ui.adsabs.harvard.edu/abs/2022IJBC...3250060H/abstract


Label-free Raman and fluorescence imaging of amyloid plaques in human Alzheimer's disease brain tissue reveal carotenoid accumulations

Alzheimer's disease is a neurodegenerative disease characterized by the presence of extracellular deposits of amyloid-beta peptide and intracellular aggregates of phosphorylated tau. A series of label-free and non-invasive techniques is used in this study to determine AD human brain tissue's biomolecular composition. Here, we report further information on cored plaques, exhibiting blue and green autofluorescence emission emanating from the same plaque site. In the hexane solution, but also adsorbed on aggregated A42 peptides; the latter comply better with the Raman spectra present in plaques. Lycopene matched closest to peak positions found in the cored plaques from the six single carotenoids measured. In these human AD brain samples, we also looked for the presence of a lipid halo around plaque, as described in the literature for transgenic AD mice, but such a halo was not present in these human AD brain samples.

Source link: https://ui.adsabs.harvard.edu/abs/2022JOpt...24e4005E/abstract


ASMFS: Adaptive-similarity-based multi-modality feature selection for classification of Alzheimer's disease

Multimodal classification techniques employing various technologies have huge advantages over single-modality-based ones for Alzheimer's disease diagnosis and prodromal stage mild cognitive impairment. However, traditional approaches often depict the data structure as a priori, despite the fact that it is impossible to accurately measure the intrinsic relationship in high-dimensional space using a pre-defined similarity matrix. We present a new multimodality feature selection scheme in this paper that performs adaptive similarity discovery and feature selection simultaneously.

Source link: https://ui.adsabs.harvard.edu/abs/2022PatRe.12608566S/abstract


Feature robustness and sex differences in medical imaging: a case study in MRI-based Alzheimer's disease detection

In this paper, we compare two classification methods on the ADNI MRI dataset: a simple logistic regression model that uses manually selected volumetric parameters as inputs, and a convolutional neural network built on 3D MRI results. In comparison to earlier research on diagnosing lung diseases based on chest x-ray results, we do not find a strong correlation between model results for male and female test subjects on the training dataset's sex composition.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220401737P/abstract


MRI-based Multi-task Decoupling Learning for Alzheimer's Disease Detection and MMSE Score Prediction: A Multi-site Validation

Since the MMSE score, which is a primary basis for AD diagnosis, can also reflect cognitive decline's changes, several studies have begun to apply multi-task learning techniques to these two tasks. A multi-task learning network is being developed in the United States to support AD detection and MMSE score prediction, which takes advantage of feature correlation by adding three multi-task interaction layers between the two tasks' backbones. Two feature decoupling modules and one feature interaction module are included in each multi-task interaction layer's multi-tasking layer. In addition, we recommend the feature consistency loss constrained feature decoupling module to raise the generalization between tasks of the feature decoupling module's tasks. Lastly, a distribution loss is suggested to raise the model's results in order to tap the specific distribution results of MMSE scores in various groups.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220401708T/abstract


Automatic Classification of Alzheimer's Disease using brain MRI data and deep Convolutional Neural Networks

Alzheimer's disease is one of the most common public health problems the world faces today. MRI scans reveal high-intensity visible features, making these scans the most commonly used brain imaging procedure. In recent years, deep learning has achieved the highest success in medical image analysis. However, only a small amount of research has been done to introduce deep learning techniques for the brain MRI classification. This paper explores the construction of several deep learning architectures based on brain MRI images and segmented images. The motivation behind segmented photographs investigates the effect of image segmentation step on deep learning classification.

Source link: https://ui.adsabs.harvard.edu/abs/2022arXiv220400068A/abstract


A human tau seeded neuronal cell model recapitulates molecular responses associated with Alzheimer's disease

Cellular models recapitulating tauopathies' key characteristics are useful tools to investigate tau tauopathies' causes and effects, as well as the identification of novel treatments. To stimulate a time-dependent rise in endogenous tau inclusions, we seeded rat primary cortical neurons with tau isolated from Alzheimer's disease brains. Tau inclusion formation at both transcriptomic and proteomic levels, as well as several microtubule and cytoskeleton-related proteins, including tubb2a, Tubb4a, Nefl, and Snca were correlated with tau inclusion formation at both transcriptomic and proteomic levels, as well as several microtubule and cytoskeleton-related proteins, including several microtubule and cytoskeleton-related proteins, such as Tubb2a, Tubb4a.

Source link: https://ui.adsabs.harvard.edu/abs/2022NatSR..12.2673F/abstract


Predictive classification of Alzheimer's disease using brain imaging and genetic data

For prediction, the majority of the current research methods use single or multimodal imaging techniques; only a few studies combine brain imaging with genetic information for disease diagnosis. We recommend an integrated Fisher score and multi-task feature selection study technique in order to accurately identify AD, healthy control, and the two stages of mild cognitive impairment combined with brain imaging and genetic characteristics. In order to solve the problem of the large difference between the feature scales of genetic and brain imaging, we discovered first genetic features with Fisher score to perform dimensionality reduction in order to solve the problem of the large difference between the two feature scales of genetic and brain imaging. The classification accuracy has been enhanced to a certain degree when compared to only using imaging technologies, and a collection of interrelated characteristics of brain imaging phenotypes and genetic factors was chosen.

Source link: https://ui.adsabs.harvard.edu/abs/2022NatSR..12.2405S/abstract


FSH blockade improves cognition in mice with Alzheimer's disease

Here we show that FSH stimulates amyloid- and Tau deposition and impair cognition in mice with Alzheimer's disease features. These results not only point to an increase in serum FSH levels in the exaggerated Alzheimer's disease pathophysiology during menopause, but also show a potential for treating Alzheimer's disease, overweight, osteoporosis, and dyslipidaemia with a single FSH-blocking agent.

Source link: https://ui.adsabs.harvard.edu/abs/2022Natur.603..470X/abstract

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions

* Please keep in mind that all text is summarized by machine, we do not bear any responsibility, and you should always check original source before taking any actions