Weakly-Supervised Learning of Metric Aggregations for Deformable Image Registration

TL;DR

This paper introduces a weakly supervised learning method that combines anatomical segmentation maps with traditional metrics to improve deformable image registration accuracy in biomedical imaging.

Contribution

It proposes a novel approach using latent structured SVMs to learn domain-specific metric aggregations conditioned on anatomical structures for registration.

Findings

Learned multi-metric registration outperforms single-metric methods.

Incorporating semantic information improves registration accuracy.

Extensive evaluation on CT and MRI datasets demonstrates effectiveness.

Abstract

Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines the optimal transformation to align two given images. The definition of this metric function is among the most critical aspects of the registration process. We argue that incorporating semantic information (in the form of anatomical segmentation maps) into the registration process will further improve the accuracy of the results. In this paper, we propose a novel weakly supervised approach to learn domain specific aggregations of conventional metrics using anatomical segmentations. This combination is learned using latent structured support vector machines (LSSVM). The learned matching criterion is integrated within a metric free optimization framework based on graphical models, resulting in a multi-metric algorithm endowed with a spatially varying similarity metric function conditioned on the anatomical structures. We provide extensive evaluation on three different datasets of CT and MRI images, showing that learned multi-metric registration outperforms single-metric approaches based on conventional similarity measures.