Efficient Brain Imaging Analysis for Alzheimer's and Dementia Detection Using Convolution-Derivative Operations

TL;DR

Sobel kernel angle difference (SKAD) is a derivative operation that offers an optimized approach to quantifying volumetric alterations through localized analysis of the gradients and is an efficient and competitive approach in neuroimaging research and clinical practice.

Abstract

Alzheimer's disease (AD) is characterized by progressive neurodegeneration and results in detrimental structural changes in human brains. Detecting these changes is crucial for early diagnosis and timely intervention of disease progression. Jacobian maps, derived from spatial normalization in voxel-based morphometry (VBM), have been instrumental in interpreting volume alterations associated with AD. However, the computational cost of generating Jacobian maps limits its clinical adoption. In this study, we explore alternative methods and propose Sobel kernel angle difference (SKAD) as a computationally efficient alternative. SKAD is a derivative operation that offers an optimized approach to quantifying volumetric alterations through localized analysis of the gradients. By efficiently extracting gradient amplitude changes at critical spatial regions, this derivative operation captures regional volume variations Evaluation of SKAD over various medical datasets demonstrates that it is 6.3x faster than Jacobian maps while still maintaining comparable accuracy. This makes it an efficient and competitive approach in neuroimaging research and clinical practice.

Figures (6)

• Figure 1: Visualization of a deformation field from 6 view angles through deforming overlaid grids.
• Figure 2: Schematic illustration of the 3D 3$\times$3 Sobel kernels used in this work. These kernels are applied to both the moving and fixed images to perform convolutions in the x, y, and z directions. The resulting gradients are then used to compute the 3D angle difference.
• Figure 3: Visualization of MRI-derived heat maps depicting the scans after registration, Jacobian Maps, and SKAD. Four cognitive stages are shown.
• Figure 4: The MRI preprocessing pipeline depicted across three orthogonal views of 3D MRI images.
• Figure 5: Comparison of Floating-Point Operations (note the log scale).