Analyzing subcortical structures in Alzheimer's disease using ensemble learning

Alzheimer's disease (AD) is a neurological condition that causes significant cognitive deterioration within the brain. Early detection can lead to an early diagnosis of the illness. Structural and subcortical analyses are required for better diagnosis of disease and detection to gain a deeper understanding of the connections between neuroregions. As a result, in this paper, we have included the fusion of PET and MRI modalities, which can provide better visualization of the result. Second, we used the Ensemble Model (EM) and other machine learning (ML) methods to analyze the different subcortical structures to determine which region is more critical in the detection of AD when compared to other subtypes. The results revealed that the Hippocampus, the Amygdala in the left and right Hemispheres, and the neuroregion were the most effective in detecting AD, Mild Cognitive Impairment (MCI), and Cognitive Normal (CN).