Brain change trajectories in healthy adults correlate with Alzheimer's related genetic variation and memory decline across life

Deep learning-based CAD system for Alzheimer's diagnosis using deep downsized KPLS

Alzheimer's disease (AD) is the most prevalent type of dementia. It is linked with a gradual decline in various brain functions, such as memory. Many research efforts are now directed toward non-invasive procedures for early diagnosis because early detection greatly benefits the patient care and treatment outcome. Additional to an accurate diagnosis and reduction of the rate of misdiagnosis; Computer-Aided Design (CAD) systems are built to give definitive diagnosis. This paper presents a novel CAD system to determine stages of AD. Initially, deep learning techniques are utilized to extract features from the AD brain MRIs. Then, the extracted features are reduced using a proposed feature reduction technique named Deep Downsized Kernel Partial Least Squares (DDKPLS). The proposed approach selects a reduced number of samples from the initial information matrix. The samples chosen give rise to a new data matrix further processed by KPLS to deal with the high dimensionality. The reduced feature space is finally classified using ELM. The implementation is named DDKPLS-ELM. Reference tests have been performed on the Kaggle MRI dataset, which exhibit the efficacy of the DDKPLS-based classifier; it achieves accuracy up to 95.4% and an F1 score of 95.1%.

Vulnerability to memory decline in aging - a mega-analysis of structural brain change

Brain atrophy is a key factor behind episodic memory loss in aging, but the nature and ubiquity of this relationship remains poorly understood. This study leveraged 13 longitudinal datasets, including 3,737 cognitively healthy adults (10,343 MRI scans; 13,460 memory assessments), to determine whether brain change-memory change associations are more pronounced with age and genetic risk for Alzheimer's Disease. Both factors are associated with accelerated brain decline, yet it remains unclear whether memory loss is exacerbated beyond what atrophy alone would predict. Additionally, we assessed whether memory decline aligns with a global pattern of atrophy or stems from distinct regional contributions. Our mega-analysis revealed a nonlinear relationship between memory decline and brain atrophy, primarily affecting individuals with above-average brain structural decline. The associations were stronger in the hippocampus but also spread across diverse cortical and subcortical regions. The associations strengthened with age, reaching moderate associations in participants in their eighties. While APOE ε4 carriers exhibited steeper brain and memory loss, genetic risk had no effect on the change-change associations. These findings support the presence of common biological macrostructural substrates underlying memory function in older age which are vulnerable to multiple age-related factors, even in the absence of overt pathological changes.

Research progress on brain network imaging biomarkers of subjective cognitive decline

Purpose

Subjective cognitive decline (SCD) is an early manifestation of the Alzheimer's disease (AD) continuum, and accurately diagnosing SCD to differentiate it from neurotypical aging in older adults is a common challenge for researchers.

Methods

This review examines and summarizes relevant studies regarding the neuroimaging of the AD continuum, and comprehensively summarizes and outlines the SCD clinical features characterizing along with the corresponding neuroimaging changes involving structural, functional, and metabolic networks.

Results

The clinical characteristics of SCD include a subjective decline in self-perceived cognitive function, and there are significant imaging changes, such as reductions in gray matter volume in certain brain regions, abnormalities in the integrity of white matter tracts and diffusion metrics, alterations in functional connectivity between different sub-networks or within networks, as well as abnormalities in brain metabolic networks and cerebral blood flow perfusion.

Conclusion

The 147 referenced studies in this paper indicate that exploring the structural, functional, and metabolic network changes in the brain related to SCD through neuroimaging aims to enhance the goals and mission of brain science development programs: "Understanding the Brain," "Protecting the Brain," and "Creating the Brain," thereby strengthening researchers' investigation into the mechanisms of brain function. Early diagnosis of SCD, along with prompt intervention, can reduce the incidence of AD spectrum while improving patients' quality of life, even integrating numerous scientific research achievements into unified and established standards and applying them in clinical practice by doctors, thus all encouraging researchers to further investigate SCD issues in older adults.