A Deep Learning Approach to Neuroanatomical Characterisation of Alzheimer's Disease.

Stud Health Technol Inform

Medical Computing Laboratory, School of Computing, National University of Singapore, Singapore.

Published: June 2018

Alzheimer's disease (AD) is a neurological degenerative disorder that leads to progressive mental deterioration. This work introduces a computational approach to improve our understanding of the progression of AD. We use ensemble learning methods and deep neural networks to identify salient structural correlations among brain regions that degenerate together in AD; this provides an understanding of how AD progresses in the brain. The proposed technique has a classification accuracy of 81.79% for AD against healthy subjects using a single modality imaging dataset.

Download full-text PDF

Source

Publication Analysis

Top Keywords

alzheimer's disease
8
deep learning
4
learning approach
4
approach neuroanatomical
4
neuroanatomical characterisation
4
characterisation alzheimer's
4
disease alzheimer's
4
disease neurological
4
neurological degenerative
4
degenerative disorder
4

Similar Publications

β-secretase (BACE1) is instrumental in amyloid-β (Aβ) production, with overexpression noted in Alzheimer's disease (AD) neuropathology. The interaction of Aβ with the receptor for advanced glycation endproducts (RAGE) facilitates cerebral uptake of Aβ and exacerbates its neurotoxicity and neuroinflammation, further augmenting BACE1 expression. Given the limitations of previous BACE1 inhibition efforts, the study explores reducing BACE1 expression to mitigate AD pathology.

View Article and Find Full Text PDF

Dementia refers to an umbrella phenotype of many different underlying pathologies with Alzheimer's disease (AD) being the most common type. Neuropathological examination remains the gold standard for accurate AD diagnosis, however, most that we know about AD genetics is based on Genome-Wide Association Studies (GWAS) of clinically defined AD. Such studies have identified multiple AD susceptibility variants with a significant portion of the heritability unexplained and highlighting the phenotypic and genetic heterogeneity of the clinically defined entity.

View Article and Find Full Text PDF

Amyloidogenic protein aggregation is a pathological hallmark of Alzheimer's Disease (AD). As such, this critical feature of the disease has been instrumental in guiding research on the mechanistic basis of disease, diagnostic biomarkers and preventative and therapeutic treatments. Here we review identified molecular triggers and modulators of aggregation for two of the proteins associated with AD: amyloid beta and tau.

View Article and Find Full Text PDF

Background: Certain peripheral proteins are believed to be involved in the development of Alzheimer's disease (AD), but the roles of other new protein biomarkers are still unclear. Current treatments aim to manage symptoms, but they are not effective in stopping the progression of the disease. New drug targets are needed to prevent Alzheimer's disease.

View Article and Find Full Text PDF

The Trail of axonal protein Synthesis: Origins and current functional Landscapes.

Neuroscience

January 2025

Departamento de Genómica, Instituto de Investigaciones Biológicas Clemente Estable, MEC, Av. Italia 3318, Montevideo, CP 11600, Uruguay; Departamento de Biología Celular y Molecular, Facultad de Ciencias, Universidad de la República, Iguá, Montevideo, 4225, CP 11400, Uruguay. Electronic address:

Local protein synthesis (LPS) in axons is now recognized as a physiological process, participating both in the maintenance of axonal function and diverse plastic phenomena. In the last decades of the 20th century, the existence and function of axonal LPS were topics of significant debate. Very early, axonal LPS was thought not to occur at all and was later accepted to play roles only during development or in response to specific conditions.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!