Initialize globally before acting locally: Enabling Landmark-free 3D US to MRI Registration

TL;DR

This paper introduces a landmark-free initialization method for 3D US to MRI registration using Euclidean distance maps from coarse segmentations, improving robustness and suitability for deformable registration.

Contribution

The novel approach eliminates the need for landmarks by using Euclidean distance maps, enhancing robustness and ease of initialization in 3D US to MRI registration.

Findings

Robust initialization across varying overlaps and positions.

Suitable for nonlinear deformable registration algorithms.

Validated on the RESECT dataset.

Abstract

Registration of partial-view 3D US volumes with MRI data is influenced by initialization. The standard of practice is using extrinsic or intrinsic landmarks, which can be very tedious to obtain. To overcome the limitations of registration initialization, we present a novel approach that is based on Euclidean distance maps derived from easily obtainable coarse segmentations. We evaluate our approach quantitatively on the publicly available RESECT dataset and show that it is robust regarding overlap of target area and initial position. Furthermore, our method provides initializations that are suitable for state-of-the-art nonlinear, deformable image registration algorithm's capture ranges.