# Unsupervised 3D End-to-End Medical Image Registration with Volume Tweening Network

## TL;DR

This paper introduces Volume Tweening Network, an unsupervised end-to-end CNN framework for 3D medical image registration that is significantly faster and achieves state-of-the-art accuracy without manual annotations.

## Contribution

The paper presents a novel unsupervised CNN-based registration method with an end-to-end cascading scheme, integrated affine registration, and invertibility loss for improved accuracy and efficiency.

## Key findings

- 880x faster than traditional methods
- Achieves state-of-the-art registration accuracy
- Operates efficiently without manual annotations

## Abstract

3D medical image registration is of great clinical importance. However, supervised learning methods require a large amount of accurately annotated corresponding control points (or morphing), which are very difficult to obtain. Unsupervised learning methods ease the burden of manual annotation by exploiting unlabeled data without supervision. In this paper, we propose a new unsupervised learning method using convolutional neural networks under an end-to-end framework, Volume Tweening Network (VTN), for 3D medical image registration. We propose three innovative technical components: (1) An end-to-end cascading scheme that resolves large displacement; (2) An efficient integration of affine registration network; and (3) An additional invertibility loss that encourages backward consistency. Experiments demonstrate that our algorithm is 880x faster (or 3.3x faster without GPU acceleration) than traditional optimization-based methods and achieves state-of-theart performance in medical image registration.