Fast Predictive Simple Geodesic Regression
This work addresses the problem of enabling large-scale medical image analysis for clinical applications by reducing computational dependency, though it is incremental as it builds on existing registration and regression methods.
The authors tackled the computational expense of deformable image registration and regression in medical image analysis by proposing a fast predictive approach, which achieved orders of magnitude speedup on a single GPU compared to standard optimization-based models, as evaluated on 3D brain MRI from ADNI datasets.
Deformable image registration and regression are important tasks in medical image analysis. However, they are computationally expensive, especially when analyzing large-scale datasets that contain thousands of images. Hence, cluster computing is typically used, making the approaches dependent on such computational infrastructure. Even larger computational resources are required as study sizes increase. This limits the use of deformable image registration and regression for clinical applications and as component algorithms for other image analysis approaches. We therefore propose using a fast predictive approach to perform image registrations. In particular, we employ these fast registration predictions to approximate a simplified geodesic regression model to capture longitudinal brain changes. The resulting method is orders of magnitude faster than the standard optimization-based regression model and hence facilitates large-scale analysis on a single graphics processing unit (GPU). We evaluate our results on 3D brain magnetic resonance images (MRI) from the ADNI datasets.