Learning Conditional Deformable Templates with Convolutional Networks

TL;DR

This paper introduces a probabilistic learning framework using convolutional networks to create deformable templates for image analysis, enabling efficient, conditional template generation and alignment, especially useful in neuroimaging and clinical applications.

Contribution

The authors propose a novel neural network-based method for learning deformable templates that are either universal or conditional, improving efficiency over traditional iterative approaches.

Findings

Effective on neuroimaging datasets

Enables creation of conditional templates

Integrates with existing VoxelMorph library

Abstract

We develop a learning framework for building deformable templates, which play a fundamental role in many image analysis and computational anatomy tasks. Conventional methods for template creation and image alignment to the template have undergone decades of rich technical development. In these frameworks, templates are constructed using an iterative process of template estimation and alignment, which is often computationally very expensive. Due in part to this shortcoming, most methods compute a single template for the entire population of images, or a few templates for specific sub-groups of the data. In this work, we present a probabilistic model and efficient learning strategy that yields either universal or conditional templates, jointly with a neural network that provides efficient alignment of the images to these templates. We demonstrate the usefulness of this method on a variety of domains, with a special focus on neuroimaging. This is particularly useful for clinical applications where a pre-existing template does not exist, or creating a new one with traditional methods can be prohibitively expensive. Our code and atlases are available online as part of the VoxelMorph library at http://voxelmorph.csail.mit.edu.