Multiscale Analysis of Alzheimer's Disease Using Feature Fusion in Cognitive and Sensory Brain Regions

Abstract

Introduction: This research is focused on early detection of Alzheimer's disease (AD) using a multiscale feature fusion framework, combining biomarkers from memory, vision, and speech regions extracted from magnetic resonance imaging and positron emission tomography images.

Methods: Using 2D gray level co-occurrence matrix (2D-GLCM) texture features, volume, standardized uptake value ratios (SUVR), and obesity from different neuroimaging modalities, the study applies various classifiers, demonstrating a feature importance analysis in each region of interest. The research employs four classifiers, namely linear support vector machine, linear discriminant analysis, logistic regression (LR), and logistic regression with stochastic gradient descent (LRSGD) classifiers, to determine feature importance, leading to subsequent validation using a probabilistic neural network classifier.

Results: The research highlights the critical role of brain texture features, particularly in memory regions, for AD detection. Significant sex-specific differences are observed, with males showing significance in texture features in memory regions, volume in vision regions, and SUVR in speech regions, while females exhibit significance in texture features in memory and speech regions, and SUVR in vision regions. Additionally, the study analyzes how obesity affects features used in AD prediction models, clarifying its effects on speech and vision regions, particularly brain volume.

Conclusion: The findings contribute valuable insights into the effectiveness of feature fusion, sex-specific differences, and the impact of obesity on AD-related biomarkers, paving the way for future research in early AD detection strategies and cognitive impairment classification.

Keywords: Feature importance analysis and Alzheimer’s disease; Multiscale feature fusion in Alzheimer’s disease; Sex differences in Alzheimer’s disease.

Fig. 1.

The visual pathways from the retina in the eyes to the primary visual cortex at the rear of the brain are shown schematically.

Fig. 2.

Visual cortices V1-V5.

Fig. 3.

Block diagram.

Fig. 4.

Feature processing pipeline.

Fig. 5.

Feature importance analysis by classifier for memory, vision, and speech regions. The figure shows feature ranking patterns for L-SVM, LDA, LR, and LRSGD.

Fig. 6.

Memory, vision, speech feature importance analysis. Texture features are the most important in the memory and vision regions, while they are the least significant in the speech regions.

Fig. 7.

Memory, vision, speech feature importance analysis – females. Texture features are the most important in the memory and speech regions, while SUVR is the most significant in the vision regions for females.

Fig. 8.

Memory, vision, speech feature importance analysis – males. Texture features are the most important in the memory regions, volume is the most significant in the vision regions, and SUVR is the most significant in the speech regions for males.

Fig. 9.

Linear regression analysis: used to find how the independent variable (obesity status) affects various brain-extracted features obtained from different ROIs.