DeepVBM: Implementing and Integrating Deep-Learning Models for Time-Efficient and Accurate Voxel-Based Morphology in an Open-Source Toolbox

Motivation: VBM analysis can benefit from deep learning advances, enhancing accuracy and efficiency. Our goal is to create a fully automated open-source pipeline for MRI-based VBM analysis. Goal(s): This study aims to develop an end-to-end VBM pipeline using deep learning to improve speed and accuracy, focusing on Alzheimer's research. Approach: We implemented the core components of voxel-based morphology using deep learning, including skull stripping, brain segmentation, and deformable registration. The open-source pipeline combines pre- and post-processing steps with deep learning models to generate VBM results. Results: The pipeline automates VBM analysis, achieving accuracy comparable to FSL while significantly improving efficiency through deep learning. Impact: Applied DeepVBM to Alzheimer's research, it demonstrates accuracy comparable to FSL with reduced computing time. The open-source toolbox is compatible with major operating systems, accelerating neuroimaging studies and enabling more efficient, large-scale analyses.