Deformable Image Registration with Multi-scale Feature Fusion from Shared Encoder, Auxiliary and Pyramid Decoders

TL;DR

This paper introduces a novel unsupervised deformable image registration method using a multi-scale feature fusion pyramid network with shared auxiliary decoder, improving accuracy and deformation plausibility.

Contribution

It presents a new deformable convolutional pyramid network with an auxiliary decoder and multi-scale feature fusion for enhanced image registration.

Findings

Achieves higher registration accuracy

Captures complex deformations effectively

Maintains smooth and plausible deformations

Abstract

In this work, we propose a novel deformable convolutional pyramid network for unsupervised image registration. Specifically, the proposed network enhances the traditional pyramid network by adding an additional shared auxiliary decoder for image pairs. This decoder provides multi-scale high-level feature information from unblended image pairs for the registration task. During the registration process, we also design a multi-scale feature fusion block to extract the most beneficial features for the registration task from both global and local contexts. Validation results indicate that this method can capture complex deformations while achieving higher registration accuracy and maintaining smooth and plausible deformations.