Real-time multimodal image registration with partial intraoperative point-set data

TL;DR

This paper introduces Free Point Transformer (FPT), a deep learning model for real-time, non-rigid, multimodal point-set registration that handles unordered data without explicit constraints, demonstrating superior accuracy and speed in medical imaging applications.

Contribution

The paper presents FPT, a novel flexible neural network architecture for non-rigid point-set registration that does not rely on explicit point proximity constraints and supports various supervision modes.

Findings

Achieved registration errors around 4.7 mm in prostate MRI-TRUS data.

Demonstrated superior accuracy over existing registration algorithms.

Enabled real-time registration suitable for intraoperative use.

Abstract

We present Free Point Transformer (FPT) - a deep neural network architecture for non-rigid point-set registration. Consisting of two modules, a global feature extraction module and a point transformation module, FPT does not assume explicit constraints based on point vicinity, thereby overcoming a common requirement of previous learning-based point-set registration methods. FPT is designed to accept unordered and unstructured point-sets with a variable number of points and uses a "model-free" approach without heuristic constraints. Training FPT is flexible and involves minimizing an intuitive unsupervised loss function, but supervised, semi-supervised, and partially- or weakly-supervised training are also supported. This flexibility makes FPT amenable to multimodal image registration problems where the ground-truth deformations are difficult or impossible to measure. In this paper, we demonstrate the application of FPT to non-rigid registration of prostate magnetic resonance (MR) imaging and sparsely-sampled transrectal ultrasound (TRUS) images. The registration errors were 4.71 mm and 4.81 mm for complete TRUS imaging and sparsely-sampled TRUS imaging, respectively. The results indicate superior accuracy to the alternative rigid and non-rigid registration algorithms tested and substantially lower computation time. The rapid inference possible with FPT makes it particularly suitable for applications where real-time registration is beneficial.