Keywords: Meta Learning, Image Registration, Numerical Optimization
TL;DR: Neural network predictions for robust starting points to assist classical registration schemes.
Abstract: We propose a trainable architecture for affine image registration to produce robust starting points for conventional image registration methods. Learning-based methods for image registration often require networks with many parameters and heavily engineered cost functions and thus are complex and computationally expensive. Despite their success in recent years, these methods often lack the accuracy of classical iterative image registration and struggle with large deformations. On the other hand, iterative methods depend on good initial estimates and tuned hyperparameters. We tackle this problem by combining effective shallow networks and classical optimization algorithms using strategies from the field of meta-learning. The architecture presented in this work incorporates only first-order gradient information of the given registration problems, making it highly flexible and particularly well-suited as an initialization step for classical image registration.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
Paper Type: methodological development
Primary Subject Area: Image Registration
Secondary Subject Area: Meta Learning
Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
Code And Data: https://github.com/FredKanter/ML-Model-ImageRegistration