Meta-Learning Initializations for Interactive Medical Image Registration

TL;DR

This paper introduces a meta-learning framework for interactive medical image registration that enables rapid, real-time adaptation during procedures, specifically applied to MR and TRUS image registration, with promising accuracy and efficiency.

Contribution

The paper presents a novel meta-learning approach that learns a network initialization for interactive image registration, reducing data needs and enabling real-time intraoperative application.

Findings

Achieves registration error of 4.26 mm with less data than non-interactive methods.

Demonstrates real-time registration during image acquisition.

Interactive approach outperforms non-interactive methods with sparse data.

Abstract

We present a meta-learning framework for interactive medical image registration. Our proposed framework comprises three components: a learning-based medical image registration algorithm, a form of user interaction that refines registration at inference, and a meta-learning protocol that learns a rapidly adaptable network initialization. This paper describes a specific algorithm that implements the registration, interaction and meta-learning protocol for our exemplar clinical application: registration of magnetic resonance (MR) imaging to interactively acquired, sparsely-sampled transrectal ultrasound (TRUS) images. Our approach obtains comparable registration error (4.26 mm) to the best-performing non-interactive learning-based 3D-to-3D method (3.97 mm) while requiring only a fraction of the data, and occurring in real-time during acquisition. Applying sparsely sampled data to non-interactive methods yields higher registration errors (6.26 mm), demonstrating the effectiveness of interactive MR-TRUS registration, which may be applied intraoperatively given the real-time nature of the adaptation process.