MRI Patterns of the Hippocampus and Amygdala for Predicting Stages of Alzheimer's Progression: A Minimal Feature Machine Learning Framework
Aswini Kumar Patra, Soraisham Elizabeth Devi, Tejashwini Gajurel
TL;DR
This work tackles the challenge of staging Alzheimer's progression (EMCI, LMCI, AD) using compact MRI features from the hippocampus and amygdala. It proposes a minimal-feature ML framework that combines ROI-based voxel extraction with dimensionality reduction (PCA or t-SNE) and evaluation across multiple classifiers, highlighting PCA+KNN as the top approach. The best-performing configuration achieves about 88.5% accuracy, demonstrating efficient, interpretable staging with reduced data and noise. The methodology holds promise for clinical deployment in pre-dementia treatment planning by providing a streamlined workflow focused on region-specific structural changes.
Abstract
Alzheimer's disease (AD) progresses through distinct stages, from early mild cognitive impairment (EMCI) to late mild cognitive impairment (LMCI) and eventually to AD. Accurate identification of these stages, especially distinguishing LMCI from EMCI, is crucial for developing pre-dementia treatments but remains challenging due to subtle and overlapping imaging features. This study proposes a minimal-feature machine learning framework that leverages structural MRI data, focusing on the hippocampus and amygdala as regions of interest. The framework addresses the curse of dimensionality through feature selection, utilizes region-specific voxel information, and implements innovative data organization to enhance classification performance by reducing noise. The methodology integrates dimensionality reduction techniques such as PCA and t-SNE with state-of-the-art classifiers, achieving the highest accuracy of 88.46%. This framework demonstrates the potential for efficient and accurate staging of AD progression while providing valuable insights for clinical applications.