Deformable Registration through Learning of Context-Specific Metric Aggregation

TL;DR

This paper introduces a weakly supervised learning method to optimize local, context-specific registration metrics by combining traditional similarity measures, improving accuracy across diverse datasets and tissue types.

Contribution

It presents a novel algorithm for learning local, context-aware registration metrics as a linear combination of conventional measures, optimized via a difference of convex functions.

Findings

Improved registration accuracy on three challenging datasets

Effective local, tissue-specific metric weighting

Demonstrated benefits over global metric tuning

Abstract

We propose a novel weakly supervised discriminative algorithm for learning context specific registration metrics as a linear combination of conventional similarity measures. Conventional metrics have been extensively used over the past two decades and therefore both their strengths and limitations are known. The challenge is to find the optimal relative weighting (or parameters) of different metrics forming the similarity measure of the registration algorithm. Hand-tuning these parameters would result in sub optimal solutions and quickly become infeasible as the number of metrics increases. Furthermore, such hand-crafted combination can only happen at global scale (entire volume) and therefore will not be able to account for the different tissue properties. We propose a learning algorithm for estimating these parameters locally, conditioned to the data semantic classes. The objective function of our formulation is a special case of non-convex function, difference of convex function, which we optimize using the concave convex procedure. As a proof of concept, we show the impact of our approach on three challenging datasets for different anatomical structures and modalities.