Hippocampal Subregion and Gene Detection in Alzheimer's Disease Based on Genetic Clustering Random Forest

Atrophy in subcortical gray matter in adult patients with moyamoya disease

BACKGROUND

Acute cerebrovascular accidents, long-term hypoperfusion, and/or remote neuronal degeneration may lead to structural alterations in patients with moyamoya disease (MMD). This study sought to comprehensively investigate the distribution characteristics of subcortical gray matter volume and their correlations with angiographic changes in the intracranial artery in patients with MMD.

METHOD

One hundred forty-two patients with MMD and 142 age- and sex-matched healthy controls underwent 3-dimensional high-resolution structural magnetic resonance imaging. Volumes of subcortical gray matter and subregions of the hippocampus and amygdala were calculated, and the degree of stenosis/occlusion of intracranial arteries in patients with MMD was evaluated on MR angiography.

RESULTS

Volume reductions in the thalamus, caudate, putamen, hippocampus, amygdala, pallidum, and nucleus accumbens were found in patients with MMD. Hippocampal subfields and amygdala subnuclei in patients with MMD showed distinct vulnerability, and morphological alterations in specific subregions were more obvious than in the whole hippocampus/amygdala. Volume loss in several subcortical areas was related to disease duration and intracranial arterial changes.

CONCLUSIONS

Our findings revealed structural alteration patterns of subcortical gray matter in MMD. The specific atrophy in subregions of the hippocampus and the amygdala suggested potential cognitive and affective impairments in MMD, which warrants further investigation. Chronic cerebral hemodynamic alterations in MMD may play a pivotal role in morphological changes in subcortical areas.

Detection of Association Features Based on Gene Eigenvalues and MRI Imaging Using Genetic Weighted Random Forest

In the studies of Alzheimer's disease (AD), jointly analyzing imaging data and genetic data provides an effective method to explore the potential biomarkers of AD. AD can be separated into healthy controls (HC), early mild cognitive impairment (EMCI), late mild cognitive impairment (LMCI) and AD. In the meantime, identifying the important biomarkers of AD progression, and analyzing these biomarkers in AD provide valuable insights into understanding the mechanism of AD. In this paper, we present a novel data fusion method and a genetic weighted random forest method to mine important features. Specifically, we amplify the difference among AD, LMCI, EMCI and HC by introducing eigenvalues calculated from the gene p-value matrix for feature fusion. Furthermore, we construct the genetic weighted random forest using the resulting fused features. Genetic evolution is used to increase the diversity among decision trees and the decision trees generated are weighted by weights. After training, the genetic weighted random forest is analyzed further to detect the significant fused features. The validation experiments highlight the performance and generalization of our proposed model. We analyze the biological significance of the results and identify some significant genes (CSMD1, CDH13, PTPRD, MACROD2 and WWOX). Furthermore, the calcium signaling pathway, arrhythmogenic right ventricular cardiomyopathy and the glutamatergic synapse pathway were identified. The investigational findings demonstrate that our proposed model presents an accurate and efficient approach to identifying significant biomarkers in AD.

Feature Fusion and Detection in Alzheimer's Disease Using a Novel Genetic Multi-Kernel SVM Based on MRI Imaging and Gene Data

Voxel-based morphometry provides an opportunity to study Alzheimer's disease (AD) at a subtle level. Therefore, identifying the important brain voxels that can classify AD, early mild cognitive impairment (EMCI) and healthy control (HC) and studying the role of these voxels in AD will be crucial to improve our understanding of the neurobiological mechanism of AD. Combining magnetic resonance imaging (MRI) imaging and gene information, we proposed a novel feature construction method and a novel genetic multi-kernel support vector machine (SVM) method to mine important features for AD detection. Specifically, to amplify the differences among AD, EMCI and HC groups, we used the eigenvalues of the top 24 Single Nucleotide Polymorphisms (SNPs) in a p-value matrix of 24 genes associated with AD for feature construction. Furthermore, a genetic multi-kernel SVM was established with the resulting features. The genetic algorithm was used to detect the optimal weights of 3 kernels and the multi-kernel SVM was used after training to explore the significant features. By analyzing the significance of the features, we identified some brain regions affected by AD, such as the right superior frontal gyrus, right inferior temporal gyrus and right superior temporal gyrus. The findings proved the good performance and generalization of the proposed model. Particularly, significant susceptibility genes associated with AD were identified, such as CSMD1, RBFOX1, PTPRD, CDH13 and WWOX. Some significant pathways were further explored, such as the calcium signaling pathway (corrected p-value = 1.35 × 10-6) and cell adhesion molecules (corrected p-value = 5.44 × 10-4). The findings offer new candidate abnormal brain features and demonstrate the contribution of these features to AD.