Multi-modal deformable image registration using untrained neural networks

TL;DR

This paper introduces a versatile image registration method using untrained neural networks that can adapt to various data types and registration tasks without needing model modifications.

Contribution

The proposed approach is the first to employ untrained neural networks as a universal implicit prior for both rigid and non-rigid, single- and multi-modal image registration.

Findings

Effective across diverse datasets and registration scenarios

Handles multiple registration types without model adjustments

Demonstrates promising registration accuracy

Abstract

Image registration techniques usually assume that the images to be registered are of a certain type (e.g. single- vs. multi-modal, 2D vs. 3D, rigid vs. deformable) and there lacks a general method that can work for data under all conditions. We propose a registration method that utilizes neural networks for image representation. Our method uses untrained networks with limited representation capacity as an implicit prior to guide for a good registration. Unlike previous approaches that are specialized for specific data types, our method handles both rigid and non-rigid, as well as single- and multi-modal registration, without requiring changes to the model or objective function. We have performed a comprehensive evaluation study using a variety of datasets and demonstrated promising performance.