NeATB

NeATB performs linear and nonlinear analysis of neuroimaging data to enable non-linear model estimation and characterization of voxel-level tissue dynamics.

Key Features:

• Modular Design: Modular architecture enables selection of analysis modules tailored to specific study designs.
• Implementation: Implemented in Python.
• Linear and Nonlinear Dynamics Analysis: Analyzes linear and nonlinear dynamics at the voxel level to characterize complex tissue behaviors.
• Statistical Significance Testing: Provides methods to assess the statistical significance of observed dynamics.
• Advanced Metrics: Includes curve fitting techniques and complexity metrics to support model inference.
• Machine Learning and Non-linear Statistics: Employs non-linear statistical methods and machine learning algorithms for model estimation.

Scientific Applications:

• Alzheimer's Disease: Analysis of nonlinear effects on brain morphology, including changes in volume and cortical thickness.
• APOE-ε4 Genotype Effects: Investigation of how the APOE-ε4 genotype influences brain aging and its interaction with age.

Methodology:

Application of non-linear statistical methods and machine learning algorithms for model estimation, using curve fitting techniques and complexity metrics applied to voxel-level linear and nonlinear dynamics analysis.