Fast Predictive Simple Geodesic Regression

TL;DR

This paper introduces a rapid predictive method for deformable image registration and geodesic regression in medical imaging, significantly reducing computation time and enabling large-scale analysis on standard hardware.

Contribution

It presents a novel fast predictive approach for image registration and geodesic regression, making large-scale brain MRI analysis feasible on a single GPU.

Findings

Method is orders of magnitude faster than traditional models.

Enables large-scale longitudinal brain studies with minimal computational resources.

Validated on 3D brain MRI datasets from ADNI.

Abstract

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.