Fast 3D registration with accurate optimisation and little learning for Learn2Reg 2021

TL;DR

This paper presents a fast, accurate, and versatile deformable medical image registration method that decouples feature learning from geometric alignment, achieving high performance with minimal learning and efficient optimization.

Contribution

It introduces a novel optimization approach using discretised displacements and convex optimization, combined with hand-crafted and semantic features for improved registration.

Findings

Achieved second place in the Learn2Reg2021 challenge overall.

Robustly handles large deformations with a coupled convex optimization.

Provides smooth, plausible deformation fields through regularization.

Abstract

Current approaches for deformable medical image registration often struggle to fulfill all of the following criteria: versatile applicability, small computation or training times, and the being able to estimate large deformations. Furthermore, end-to-end networks for supervised training of registration often become overly complex and difficult to train. For the Learn2Reg2021 challenge, we aim to address these issues by decoupling feature learning and geometric alignment. First, we introduce a new very fast and accurate optimisation method. By using discretised displacements and a coupled convex optimisation procedure, we are able to robustly cope with large deformations. With the help of an Adam-based instance optimisation, we achieve very accurate registration performances and by using regularisation, we obtain smooth and plausible deformation fields. Second, to be versatile for different registration tasks, we extract hand-crafted features that are modality and contrast invariant and complement them with semantic features from a task-specific segmentation U-Net. With our results we were able to achieve the overall Learn2Reg2021 challenge's second place, winning Task 1 and being second and third in the other two tasks.