Meeting Banner
Abstract #0192

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

Pei-Mao Sun1, Teng-Yi Huang1, Tzu-Chao Chuang2, Yi-Ru Lin3, and Hsiao-Wen Chung4
1Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2Department of Electrical Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan, 3Department of Electronic and Computer Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 4Department of Electrical Engineering, National Taiwan University, Taipei, Taiwan

Synopsis

Keywords: Alzheimer's Disease, AI/ML Software, Voxel-based Morphometry, Gray Matter, Automated MRI Pipeline

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords