Recurrence With Correlation Network for Medical Image Registration

TL;DR

RWCNet is a novel medical image registration network that leverages multi-scale features, a cost volume layer, and recurrence to improve accuracy on large-displacement datasets, outperforming existing methods.

Contribution

The paper introduces RWCNet, a new architecture combining multi-scale features, a cost volume layer, and recurrence, demonstrating improved registration accuracy over prior models.

Findings

Achieves 2.11mm TRE on NLST dataset.

Attains 81.7% dice overlap on OASIS dataset.

Outperforms LapIRN on both datasets.

Abstract

We present Recurrence with Correlation Network (RWCNet), a medical image registration network with multi-scale features and a cost volume layer. We demonstrate that these architectural features improve medical image registration accuracy in two image registration datasets prepared for the MICCAI 2022 Learn2Reg Workshop Challenge. On the large-displacement National Lung Screening Test (NLST) dataset, RWCNet is able to achieve a total registration error (TRE) of 2.11mm between corresponding keypoints without instance fine-tuning. On the OASIS brain MRI dataset, RWCNet is able to achieve an average dice overlap of 81.7% for 35 different anatomical labels. It outperforms another multi-scale network, the Laplacian Image Registration Network (LapIRN), on both datasets. Ablation experiments are performed to highlight the contribution of the various architectural features. While multi-scale features improved validation accuracy for both datasets, the cost volume layer and number of recurrent steps only improved performance on the large-displacement NLST dataset. This result suggests that cost volume layer and iterative refinement using RNN provide good support for optimization and generalization in large-displacement medical image registration. The code for RWCNet is available at https://github.com/vigsivan/optimization-based-registration.